Robot navigation in dense crowds requires understanding social cues that humans naturally use, yet existing methods struggle with real-world complexity. We investigate two questions: (1) Where do pedestrians look when navigating crowds? and (2) Can eye tracking improve robot navigation? To answer, we introduce GazeNav, an egocentric dataset collected via wearable eye trackers, featuring synchronized video, gaze, and trajectories in crowded environments. Analysis reveals that the gaze of pedestrians is closely related to the semantic presence and movement of other individuals, exhibiting distinct attention patterns across navigation behaviors. Building on this, we propose Gaze2Nav, a modular framework that first predicts human gaze to infer socially salient pedestrians, then incorporates the semantic attention into motion planning alongside visual inputs. Our method achieves 87.6% salient pedestrian prediction accuracy and reduces trajectory error by 15.4% over state-of-the-art baselines. By aligning with human gaze, our framework improves both performance and interpretability, advancing toward human-like, socially intelligent robot navigation.

We consider a general non-stochastic online pricing bandit setting in a procurement scenario where a buyer with a budget wants to procure items from a fixed set of sellers to maximize the buyer's reward by dynamically offering purchasing prices to the sellers, where the sellers' costs and values at each time period can change arbitrarily and the sellers determine whether to accept the offered prices to sell the items. This setting models online pricing scenarios of procuring resources or services in multi-agent systems. We first consider the offline setting when sellers' costs and values are known in advance and investigate the best fixed-price policy in hindsight. We show that it has a tight approximation guarantee with respect to the offline optimal solutions. In the general online setting, we propose an online pricing policy, Granularity-based Pricing (GAP), which exploits underlying side-information from the feedback graph when the budget is given as the input. We show that GAP achieves an upper bound of O(n{v_{max}}{c_{min}}sqrt{B/c_{min}}ln B) on the alpha-regret where n, v_{max}, c_{min}, and B are the number, the maximum value, the minimum cost of sellers, and the budget, respectively. We then extend it to the unknown budget case by developing a variant of GAP, namely Doubling-GAP, and show its alpha-regret is at most O(n{v_{max}}{c_{min}}sqrt{B/c_{min}}ln2 B). We also provide an alpha-regret lower bound Omega(v_{max}sqrt{Bn/c_{min}}) of any online policy that is tight up to sub-linear terms. We conduct simulation experiments to show that the proposed policy outperforms the baseline algorithms.

By exploiting the correlation between the structure and the solution of Mixed-Integer Linear Programming (MILP), Machine Learning (ML) has become a promising method for solving large-scale MILP problems. Existing ML-based MILP solvers mainly focus on end-to-end solution learning, which suffers from the scalability issue due to the high dimensionality of the solution space. Instead of directly learning the optimal solution, this paper aims to learn a reduced and equivalent model of the original MILP as an intermediate step. The reduced model often corresponds to interpretable operations and is much simpler, enabling us to solve large-scale MILP problems much faster than existing commercial solvers. However, current approaches rely only on the optimal reduced model, overlooking the significant preference information of all reduced models. To address this issue, this paper proposes a preference-based model reduction learning method, which considers the relative performance (i.e., objective cost and constraint feasibility) of all reduced models on each MILP instance as preferences. We also introduce an attention mechanism to capture and represent preference information, which helps improve the performance of model reduction learning tasks. Moreover, we propose a SetCover based pruning method to control the number of reduced models (i.e., labels), thereby simplifying the learning process. Evaluation on real-world MILP problems shows that 1) compared to the state-of-the-art model reduction ML methods, our method obtains nearly 20% improvement on solution accuracy, and 2) compared to the commercial solver Gurobi, two to four orders of magnitude speedups are achieved.

Real-time object detection is critical for the decision-making process for many real-world applications, such as collision avoidance and path planning in autonomous driving. This work presents an innovative real-time streaming perception method, Transtreaming, which addresses the challenge of real-time object detection with dynamic computational delays. The core innovation of Transtreaming lies in its adaptive delay-aware transformer, which can concurrently predict multiple future frames and select the output that best matches the real-world present time, compensating for any system-induced computational delays. The proposed model outperforms existing state-of-the-art methods, even in single-frame detection scenarios, by leveraging a transformer-based methodology. It demonstrates robust performance across a range of devices, from powerful V100 to modest 2080Ti, achieving the highest level of perceptual accuracy on all platforms. Unlike most state-of-the-art methods that struggle to complete computation within a single frame on less powerful devices, Transtreaming meets the stringent real-time processing requirements on all kinds of devices. The experimental results emphasize the system's adaptability and its potential to significantly improve the safety and reliability of many real-world systems, such as autonomous driving.

Federated Learning (FL) has recently garnered considerable attention because it allows multiple clients to collaboratively train machine learning models while keeping their local data private. However, most existing studies focus primarily on optimizing a single FL task, overlooking the dynamic nature of systems where tasks may arrive over time. To address this issue, this paper formulates a novel long-term multi-task FL optimization problem, aiming at balancing the learning quality and the penalties incurred from insufficient client participation in each communication round. To mitigate selection bias, a fairness queue is implemented, and a Lyapunov optimization model is developed to enhance both system stability and learning utility. Furthermore, we derive an upper bound for the objective function, reframing the client selection issue as a minimum weight bipartite matching problem within an auxiliary bipartite graph. The regret of the proposed strategy is theoretically analyzed to quantify the performance gap. Finally, extensive simulations on two real datasets demonstrate the effectiveness of the proposed scheme, highlighting its potential for improving both fairness and efficiency in dynamic, multi-task FL environments.

Human-in-the-loop (HIL) imitation learning enables agents to learn complex behaviors safely through real-time human intervention. However, existing methods struggle to efficiently leverage agent-generated data due to dynamically evolving trajectory distributions and imperfections caused by human intervention delays, often failing to faithfully imitate the human expert policy. In this work, we propose Faithful Dynamic Imitation Learning (FaithDaIL) to address these challenges. We formulate HIL imitation learning as an online non-convex problem and employ dynamic regret minimization to adapt to the shifting data distribution and track high-quality policy trajectories. To ensure faithful imitation of the human expert despite training on mixed agent and human data, we introduce an unbiased imitation objective and achieve it by weighting the behavior distribution relative to the human expert's as a proxy reward. Extensive experiments on MetaDrive and CARLA driving benchmarks demonstrate that FaithDaIL achieves state-of-the-art performance in safety and task success with significantly reduced human intervention data compared to prior HIL baselines.

This work studies the challenge of scheduling real-time control commands in Networked Control Systems (NCS), where control actions rely on the freshness of data collected from multiple sources. In dynamic environments, ensuring that control commands in an NCS are accurate and frequent is essential for maintaining the system responsiveness. For this aim, we introduce a new metric, Age of Result (AoR), which quantifies the time elapsed since the last control command was generated and executed. This metric reflects the system’s capability to adapt to real-time changes in the operational environment by considering both data freshness and control command frequency. We conduct a detailed analysis of AoR in NCS, paying special attention to the dependencies between sensing and computing phases. We first address computation-intensive and network-intensive scenarios, proposing random sampling (RS)-based approximate algorithms for each case. Subsequently, we develop another RS-based algorithm and a heuristic approach for the general model. Simulation results demonstrate that our approach can effectively minimize AoR and significantly enhance the system performance and real-time adaptability compared to existing strategies.

Understanding the movement of crowds is important to the management of public places and urban safety. Existing researches mostly focused on tracking pedestrians in video clips from a single camera or across multiple cameras (Multi-Object Tracking) by identifying individuals with similar appearance or spatial-temporal movement features. However, how crowds navigate through invisible area between cameras in crowded environments have been overlooked. Moreover, identifying individuals across camera in a crowded environment could be challenging due to cluttered pedestrian appearance and highly uncertain movements. In this paper, we focus on recovering crowd trajectories in the invisible area of sparse camera networks within crowded public environments. We achieve better spatial-temporal feature matching by estimating the most likely travel time between segmented tracklet observations of individuals with elaborate consideration of pedestrian interactions, which reduces the dependence on unreliable appearance features. Subsequently, we recover trajectories for matched tracklets in the invisible area with a high fidelity crowd simulation model. Extensive experiments on two real-world trajectory datasets show that our proposed method is superior to existing spatial-temporal based MOT methods and improves the appearance-based MOT models in terms of association accuracy and trajectory fidelity.

Video surveillance and crowd analysis are essential for urban public safety, particularly for accurate crowd counting and density estimation. Existing methods primarily use RGB modality, which limits their effectiveness in complex environments. With advancements in thermal sensors, some studies have combined RGB and thermal images to improve crowd counting accuracy. However, the existing studies face the risk of introducing redundant information during modality interaction and exacerbating the influence of non-uniform crowd density for modality fusion. Therefore, further advancements are needed to bridge the gap in crowd density estimation by RGB and thermal image interaction. To adequately capture information from both RGB and thermal crowd images and alleviate the above difficulties, we propose a Modality Interaction Attention Network (MIANet). Specifically, Modality Interaction Attention (MIA) module consists of two Multi-Scale Attention (MSA) and a Channel Direction Attention (CDA), which serve to remove redundant information and amplify modality attributes. The MSA incorporates multi-scale kernel factors, enabling its application to still images to solve non-uniform crowd density in one image. To combine modality-specific attributes, the Tri-level MIA modules are connected to the front-end network in a stacked manner. Polished fusion features are further extracted using the Grid Block that combine level-by-level features. On two real-world datasets, we conducted in-depth experiments. Results of the evaluation reveal that our MIANet works better than cutting-edge baseline methodologies and MIANet variants in relation to a variety of prediction inaccuracies, highlighting the efficiency of MIANet and each of its essential modules in crowd density estimation. Code is available at Github.

Efficient traffic signal control (TSC) has been one of the most useful ways for reducing urban road congestion. By modeling each intersection as an autonomous agent, multiagent reinforcement learning (MARL) shows remarkable performance in solving dynamic TSC. However, most of TSC methods based on MARL suffer from a non-stationarity problem since agents update their policies simultaneously. To resolve this issue, this paper considers multi-intersection TSC as a multi-agent sequential decision-making process with policy online learning. We utilize a sequential model such as Transformer architecture to learn the multi-agent joint policy. By carefully designing the advantage function of each agent, the monotonic improvement property can be guaranteed. Moreover, to fully exploit the advantages of both simultaneous and sequential MARL, we further propose a novel MARL network selection algorithm (MARL-NS) which selectively employs simultaneous MARL only at states that sequential MARL might fall into local optimum. Our theory proves that MARL-NS preserves cooperative MARL converge properties. Finally, we validate the proposed MARL-NS method on a unified TSC benchmark, LibSignal. Experimental results show that our method can outperform the baseline methods in network-level and arterial coordination.

Video streaming systems are critical for intelligent applications to transmit video data from end devices to servers for real-time analysis. In contrast to traditional human-centric streaming systems, which prioritize user-perceived metrics, machine-centric streaming systems are designed to continuously provide fresh and accurate information for analytics purposes. Although numerous studies have investigated policies to optimize streaming performance, most of them employ the segment-by-segment streaming framework from human-centric systems. Through comprehensive theoretical analysis and experimentation, we uncover that the segmented streaming approach is sub-optimal for machine-centric streaming systems compared to the straightforward frame-by-frame streaming approach. Furthermore, instead of relying on conventional frame-level metrics, we introduce a novel metric called the Age of Semantic Information (AoSI) to evaluate the performance of analytics-oriented streaming systems. This metric balances the quantity and timeliness of the semantic information. Consequently, we propose a compression ratio adaption method tailored to optimize AoSI performance for frame-by-frame streaming systems. This method leverages a deep learning (DL)-based predictor to discover the dynamic, latent relationships between compression and inference accuracy. Evaluated on actual streaming prototypes and real-world datasets, our method significantly surpasses both segmented and frame-by-frame baseline methods in terms of worst-case and average AoSI performance.

Unmanned aerial vehicles (UAVs) play a critical role in disaster response, swiftly gathering information from various points-of-interest (PoIs) across extensive areas. The freshness of this information is measured by the age of information (AoI), representing the time since the latest information acquisition of a specific PoI. However, devising AoI-minimizing routes for UAVs in obstructed post-disaster environments poses unique challenges that have yet to be fully overcome. Obstacles, like post-disaster barriers, can impede direct flight paths between PoIs, and limited battery life requires energy-conscious route planning. Additionally, existing solutions fail to universally minimize varying data freshness requirements. This research addresses the AoI-driven UAV travel problem, seeking to establish periodic routes that optimize AoI metrics while considering energy and general graph constraints. We develop a learning-based algorithm to enhance the current route iteratively, utilizing guidance from a deep reinforcement learning (DRL) agent and executing a series of operations to potentially decrease AoI while adhering to topological and energy constraints. The algorithm is validated on real post-disaster datasets, demonstrating significant improvements in various AoI metrics compared to other learning-based approaches. Furthermore, our algorithm outperforms approximation algorithms and can approach the global optimum when tailored to existing AoI-minimizing problems.

Mobile crowdsourcing has emerged as a popular approach for organizations to leverage the collective intelligence of a crowd of users to obtain services. Considering users’ costs for providing services, it is vital for the requester to design incentive mechanisms to encourage users’ participation in crowdsourcing under the budget constraint. This aligns with the concept of budget-feasible mechanism design. Existing budget-feasible mechanisms often assume immediate user reachability and willingness of joining the crowdsourcing, which is unrealistic. To address this issue, a promising approach is to have participating users diffuse auction information to potential users in the social network. However, this brings another challenge in that participating users can be strategic and therefore hesitant to invite more potential competitors to join the crowdsourcing platform. In this paper, we focus on developing diffusion mechanisms that incentivize strategic users to actively diffuse auction information through the social network. This helps to attract more informed users and ultimately increases the value of the procured services. Specifically, we propose optimal budget-feasible diffusion mechanisms that simultaneously guarantee individual rationality, budget-feasibility, strong budget-balance, incentive-compatibility (i.e., users report real costs and diffuse auction information to all their neighbors) and approximation. Experiment results under real datasets further demonstrate the efficiency of proposed mechanisms.

Information freshness, measured by the Age-of-Information (AoI) metric, is a crucial aspect of conventional network systems. However, the emergence of the Artificial Intelligence of Things (AIoT) introduces unique requirements for assessing information freshness, rendering the traditional AoI definition inadequate. This is because the traditional AoI metric operates under the presumption that each data packet bears equal significance. In contrast, AIoT systems must prioritize the transmission of event summaries from smart IoT devices. To promptly capture events as they occur at the sources, we propose a novel information freshness metric called Age of Event (AoE). Subsequently, we thoroughly investigate the problem of AoE-minimizing transmission scheduling. This issue presents a formidable challenge because the event occurrence pattern can be unpredictable, and more crucially, the base station only becomes aware of these occurrences post-transmission. In response, we formulate algorithms and conduct a theoretical analysis applicable to scenarios characterized by complete, zero, or partial knowledge of event occurrences. Evaluations performed on a real traffic event dataset reveal that even in the absence of complete knowledge, our algorithms exhibit competitive performance when compared against the clairvoyant benchmark and markedly outperform AoI baselines.

Ride-hailing platforms have been facing the challenge of balancing demand and supply. Existing vehicle reposition techniques often treat drivers as homogeneous agents and relocate them deterministically, assuming compliance with the reposition. In this paper, we consider a more realistic and driver-centric scenario where drivers have unique cruising preferences and can decide whether to take the recommendation or not on their own. We propose i-Rebalance, a personalized vehicle reposition technique with deep reinforcement learning (DRL). i-Rebalance estimates drivers' decisions on accepting reposition recommendations through an on-field user study involving 99 real drivers. To optimize supply-demand balance and enhance preference satisfaction simultaneously, i-Rebalance has a sequential reposition strategy with dual DRL agents: Grid Agent to determine the reposition order of idle vehicles, and Vehicle Agent to provide personalized recommendations to each vehicle in the pre-defined order. This sequential learning strategy facilitates more effective policy training within a smaller action space compared to traditional joint-action methods. Evaluation of real-world trajectory data shows that i-Rebalance improves driver acceptance rate by 38.07% and total driver income by 9.97%.

Navigation through crowded human environments is challenging for social robots. While reinforcement learning has been adopted for its capacity to capture complex interactions, the training process often relies on simulators to replicate realistic crowd behaviors, ensuring cost-efficiency. Existing crowd simulation methods typically rely on either handcrafted rules, which may lead to overly aggressive navigation, or learning from human trajectory demonstrations, which can be challenging to generalize effectively. In this paper, we introduce a data-driven crowd simulation method called SocialGAIL, which leverages Generative Adversarial Imitation Learning (GAIL) to emulate real pedestrian navigation in crowded environments. SocialGAIL utilizes an attention-based graph neural network to encode observations and employs a generator-discriminator architecture to closely mimic pedestrian behavior. We propose a set of metrics to evaluate the faithfulness of crowd simulation. Experimental results demonstrate that SocialGAIL outperforms baseline methods in terms of goal-reaching, intermediate state faithfulness, trajectory faithfulness, and adherence to global trajectory patterns. The code of our approach is available at https://github.com/William-island/SocialGAIL.

Metaverse has been viewed as the next generation of human-computer interaction, which requires collecting information from both the physical and virtual world. One potential way is to employ virtual service providers (VSPs) to finish collection tasks by designing posted-pricing mechanisms via the crowdsensing platform. As VSPs’ costs and values are usually unknown, learning the optimal posted-pricing policy under uncertainty is undoubtedly critical to utilize the budget efficiently. However, existing posted-pricing learning algorithms assume that agents provide services without blocking and agents’ attributes follow an independent identical distribution, both of which are unrealistic in Metaverse, e.g., VSPs should continuously sense the physical world to make provided services realistic, which makes the long working VSP unavailable/blocked for a certain period of time. In this paper, we address the budgeted pricing problem under uncertainty by considering blocking constraints and unknown non-identical VSPs’ attributes. The problem is modeled as a Budgeted-pricing Blocking Bandit (B2-bandit) problem, which remains unaddressed even for the oracle case with known VSPs’ information. We thus first propose a pricing policy for the oracle case with an instance-dependent approximation ratio to the global optimum. For the general B2-bandit problem with unknown information, we propose an online learning algorithm satisfying blocking constraints and incurring an accumulated regret up to$O(MK\log B)$as compared to the oracle approximation algorithm, where$M,K,B$are the number of VSPs, candidate prices and the budget, respectively. Experiments on real datasets validate that the proposed algorithm improves more than 172% accumulated value compared to baseline pricing algorithms.

Energy harvesting is a promising technique to address the energy hunger problem for thousands of wireless devices. In Radio Frequency (RF) energy harvesting systems, a wireless device first harvests energy and then transmits data with this energy, hence the ‘harvest-then-transmit’ (HTT) principle is widely adopted. We must carefully design the HTT schedule, i.e., schedule the timing between harvesting and transmission, and decide the data transmission power such that the throughput can be maximized with the limited harvested energy. Distinct from existing work, we assume energy harvested from RF sources is time-varying, which is more practical but more difficult to handle. We first discover a surprising result that the optimal transmission power is independent of the transmission time, but solely depends on the RF harvesting power, for a simple case when the energy harvesting is stable. We then obtain an optimal offline HTT-scheduling for the general case that allows the RF harvesting power to vary with time. To the best of our knowledge, it is the first optimal HTT-scheduling algorithm that achieves maximum data throughput for time-varying RF powered systems. Finally, an efficient online heuristic algorithm is designed based on the offline optimality properties. Simulations show that the proposed online algorithm has superior performance, which achieves more than 90% of the offline maximum throughput in most cases.

This work studies the Age-of-Information (AoI) optimization problem in the information-gathering wireless network systems, where time-sensitive data updates are collected from multiple information sources, and each source is equipped with a battery and harvests energy from ambient energy, such as solar, wind, etc. The arrival of the harvested energy can be modeled as the stochastic process, and an information source can deliver its data update only when 1) there is energy in the battery, and 2) this source is selected to transmit its data update based on the transmission policy. This work analyzes how the energy arrival pattern of each source and the transmission policy jointly influence the average AoI among multiple sources. To the best of our knowledge, this is the first work that formally develops the closed-form expression of average AoI in the Stationary Randomized Sampling (SRS) policy space and proposes approximation schemes with constant ratios in multi-source systems under a stochastic energy harvesting model. More specifically, under the perfect wireless channel, the closed-form expression of AoI under the SRS policy space with arbitrary finite battery size is developed. Based on the result, we propose the Max Energy-Aware Weight (MEAW) policy, which is proven to achieve 2-approximation in the full policy space. Under the uncertain wireless channel, we develop the closed-form expression of Whittle’s index to address the target problem. Based on the result, we propose the Energy-aware Whittle’s index policy (EWIP) and prove its approximate performance by using the Lyapunov optimization techniques. Experimental results show that MEAW under the perfect channel setting and EWIP under the uncertain channel setting both perform close to the theoretical lower bound and outperform the state-of-the-art schemes.

Traffic signal control (TSC) has been one of the most useful ways for reducing urban road congestion. The challenge of TSC includes 1) real-time signal decision, 2) the complexity in traffic dynamics, and 3) the network-level coordination. Reinforcement learning (RL) methods can query policies by mapping the traffic state to the signal decision in real-time, however, are inadequate for different traffic flow environment. By observing real traffic information, online planning methods can compute the signal decisions in a responsive manner. Unfortunately, existing online planning methods either require high computation complexity or get stuck in local coordination. Against this background, we propose an explicit multiagent coordination (EMC)-based online planning methods that can satisfy adaptive, real-time and network-level TSC. By multiagent, we model each intersection as an autonomous agent, and the coordination efficiency is modeled by a cost function between neighbor intersections. By network-level coordination, each agent exchanges messages of cost function with its neighbors in a fully decentralized manner. By real-time, the message-passing procedure can interrupt at any time when the real time limit is reached and agents select the optimal signal decisions according to current message. Finally, we test our EMC method in both synthetic and real road network datasets. Experimental results are encouraging: compared to RL and conventional transportation baselines, our EMC method performs reasonably well in terms of adapting to real-time traffic dynamics, minimizing vehicle travel time and scalability to city-scale road networks.

Mobile devices have been increasingly deployed in large-scale cyber-physical systems (CPS) to traverse the field and retrieve various data measurements from designated physical entities with stringent performance requirements. This work studies the Availability-constrained real-time Fresh Data Retrieval problem in CPS with a Speed Adjustable mobile device (AFDR-SA). The goal is to maintain the temporal validity of the real-time data with different priorities to be retrieved in the system while meeting the data availability constraints imposed by the communication range between the mobile device and the physical entities. The general case of the AFDR-SA problem is proved to be NP-hard. A dynamic programming (DP)-based optimal algorithm is proposed for a special scenario where the retrieval times of individual data items with the same priority are of the same length. For the general case where data items can have arbitrary retrieval times and different priorities, another different DP-based scheme is proposed, which is proved to be optimal given the retrieval order. A fast heuristic with low complexity is also proposed for the general problem to improve the computational efficiency. The experimental results show that the proposed schemes for the general case outperform the state-of-the-art methods and have close performance compared to the optimal solution while incurring much less computational overhead.

In many IoT applications, information needs to be gathered from multiple heterogeneous sources to the base station for real-time processing and follow-up actions. Undoubtedly, information freshness, measured by age of information (AoI), is critical in taking responsive actions. Recent studies have taken AoI into the consideration of transmission scheduling over wireless channels. However, existing studies on guaranteeing AoI either assume error-free wireless channels or priorly known link reliability, which is unrealistic. In this paper, we tackle the AoI-guaranteed transmission scheduling problem over an unreliable channel with the aim of throughput maximization, which is modelled as an AoI-Guaranteed Multi-Armed Bandit (AG-MAB) problem. Since the problem has not been studied in the literature even for the oracle case with given link reliability, we first propose an optimal stationary randomized sampling (SRS) policy for the oracle case. For the AG-MAB problem with unknown link reliability, we propose learning algorithms that meet the AoI requirements with probability 1 and incur sublinear regret compared to Oracle SRS, which can also detect the unsatisfiability of the AoI constraint and switch to the fallback policy promptly with guaranteed accuracy. Numerical results show that our algorithm outperforms the AoI-constraint-aware baselines on throughput with per-source AoI requirement guaranteed.

This work investigates the truthful auction for dependent task offloading in vehicular edge computing by considering the selfishness and rationality of participating nodes. Specifically, we first illustrate a truthfulness-guaranteed dependent task offloading architecture. Then, we formulate the Truthfulness-Guaranteed Dependent Task Offloading problem, aiming at maximizing the system utility (SU) while ensuring truthfulness and individual rationality in dynamic environments. Further, we design both centralized and distributed auction mechanisms to derive the optimal and approximate solutions, respectively. For centralized auction mechanism, we adopt the branch-and-price algorithm to determine the offloaded nodes, which yields maximum SU. Then, we adopt VCG mechanism to determine the payment of buyers. For distributed auction mechanism, each seller independently chooses the winning bid, and the buyer greedily chooses the offloaded node with maximum utility. Then, a novel payment mechanism regarding the cost of failed buyers is designed to guarantee the truthfulness and individual rationality. Finally, we build the simulation model and conduct the performance evaluation based on realistic vehicular trajectories. The results demonstrate that the proposed distributed auction mechanism achieves performance within approximately 4% of the optimal method, while significantly reducing computational complexity. Additionally, it significantly outperforms other methods in terms of system utility across various task requirements.

Unmanned Aerial Vehicle (UAV) swarm offers extended coverage and is a vital solution for many applications. A key issue in UAV swarm control is to cover all targets while maintaining connectivity among UAVs, referred to as a multi-target coverage problem. With existing dynamic routing protocols, the flying ad hoc network suffers outdated and incorrect route information due to frequent topology changes. This might lead to failures of time-critical tasks. One mitigation solution is to keep the physical topology unchanged, thus maintaining a fixed communication topology and enabling static routing. However, keeping physical topology unchanged may sacrifice the coverage. In this article, we propose to maintain a fixed communication topology among UAVs, which allows certain changes in physical topology, so that to maximize the coverage. We develop a distributed motion planning algorithm for the online multi-target coverage problem with the constraint of keeping communication topology intact. As the communication topology needs to be timely updated when UAVs leave or arrive at the swarm, we further design a topology-management protocol. Experimental results from the ns-3 simulator show that under our algorithms, UAV swarms of different sizes achieve significantly improved delay and loss ratio, efficient coverage, and rapid topology update.

This work studies the non-uniform multi-source data update problem for real-time monitoring systems, where a set of heterogeneous data sources transmit their updates to a Base Station (BS) through wire or wireless channel(s). The performance metric called Age of Information (AoI) - which measures the time elapsed since the last data update of each source received by the BS - is commonly used to quantify the freshness of the data updates. However, most existing work on minimizing AoI of multi-source data updates assume that all sources have a uniform size of data updates which unnecessarily reduces their applicability. This work explores a more general model where individual sources can have non-uniform sizes of data updates, and provides thorough analysis to optimize both peak and average AoI of the target system. Based on these analysis, an optimal scheme to minimize the peak AoI is first developed by guaranteeing the delivery frequency of each source proportional to the function determined by its data size. A$(2+\delta)$-approximation algorithm based on random sampling (RS) and a heuristic called Ratio-driven Maximum Age First (RMAF) are further proposed to minimize the average AoI. Our extensive experiments validate the bound of RS, and show that RMAF can achieve close performance to the lower bound of the minimum time-average AoI and outperforms the state-of-the-art schemes.

Accurately predicting Origin-Destination (OD) passenger flow can help metro service quality and efficiency. Existing works have focused on predicting incoming and outgoing flows for individual stations, while little attention was paid to OD prediction in metro systems. The challenges are that OD flows 1) have high temporal dynamics and complex spatial correlations, 2) are affected by external factors, and 3) have sparse and incomplete data slices. In this paper, we propose an Adaptive Feature Fusion Network (AFFN) to a) adaptively fuse spatial dependencies from multiple knowledge-based graphs and even hidden correlations between stations and b) accurately capture the periodic patterns of passenger flows based on the auto-learned impact from external factors. To deal with the incompleteness and sparsity of OD matrices, we extend AFFN to multi-task AFFN to predict the inflow and outflow of each station as a side-task to further improve OD prediction accuracy. We conducted extensive experiments on two real-world metro trip datasets collected in Nanjing and Xi’an, China. Evaluation results show that our AFFN and multi-task AFFN outperform the state-of-the-art baseline techniques and AFFN variants in various accuracy metrics, demonstrating the effectiveness of AFFN and each of its key components in OD prediction.

In energy harvesting communication systems, it is possible for a transmitter to schedule the transmission by jointly scaling the rate and turning the transmitter ON/OFF adaptively. Such a joint rate and sleep schedule can greatly increase the throughput achieved by the transmitter with battery constraints. However, most existing works on joint rate and sleep scheduling assume the transition between different states does not have any cost, i.e., energy or time consumption. This is not realistic while the energy and time needed for booting a transmitter, i.e., turning a transmitter from OFF to ON, are not small enough to be ignored in most cases. In this paper, we investigate the joint rate and sleep scheduling on system throughput with more general booting consumption considered in energy harvesting communication systems. We first identify the structural properties of the optimal solution for the model with booting consumption considered. Inspired by these observations, we develop an optimal offline algorithm and an online heuristic algorithm to solve the problem. Experimental results from simulations and real tests show that the proposed algorithms can achieve much higher throughput on average in a realistic energy harvesting communication system, compared to those algorithms that only consider rate scheduling or ignore the booting consumption.

In a crowdsensing platform, users are invited to provide data services, and multiple requesters compete for desired services. Due to users' costs of providing services, it is critical to design incentive mechanisms to incentivize users with (monetary) rewards. Meanwhile, requesters may have individual budgets and compete for services with different procurement abilities. Such a setting falls into the budget-feasible mechanism design. However, most of the existing budget-feasible mechanisms focus on one-sided markets with a single requester rather than the two-sided markets with multiple requesters having different procurement abilities. Moreover, requesters and users can be selfish and strategic with their private information, which requires preventing information manipulation on both requesters' and users' sides. In this paper, we investigate budget-feasible mechanisms in two-sided crowdsensing markets where multiple strategic requesters come with private budgets to obtain services from the strategic users. We also consider the fairness on the requesters' side,i.e., a requester with more budget should obtain more service. We propose budget-feasible mechanisms for two models by distinguishing the types of services,i.e., the homogeneous or heterogeneous services. All proposed mechanisms satisfy fairness, budget feasibility, truthfulness on both users' and requesters' sides, and the constant approximation ratio. Numerical experiment results further demonstrate the efficiency of our proposed mechanisms.

Mobile crowdsensing (MCS) has recently received considerable attention due to its capability of providing a promising paradigm to complete complex sensing tasks. Existing works on MCS mainly focus on designing incentive mechanisms to attract mobile users to participate in crowdsensing, while ignoring the freshness of information, i.e.,Age of Information(AoI). Although multiple source nodes with common observation can indeed improve the data quality of MCS, it complicates the calculation of the AoI. To address this issue, this article proposes a freshness-aware incentive mechanism in MCS, which not only captures the conflict interests/competitions among users, but also considers the age of information (AoI). Specifically, we define two data sampling models, namedsampling-at-willmodel andsampling-predeterminedmodel. For both models, we design efficient auction mechanisms, which recruit appropriate mobile users, determine the payments, and schedule the data sampling, so as to optimize the average AoI and data quality under budget constraint. It is proved that the proposed auction achieves several desirable properties, including individual rationality, budget balance, truthfulness and computational efficiency. We also theoretically derive the upper bound of the average AoI obtained by the proposed scheme. Finally, we conduct simulations to evaluate the efficiency of the proposed mechanism in optimizing the data quality and AoI.

The edge-cloud collaboration architecture can support Deep Neural Network-based (DNN) video analytics with low inference delays and high accuracy. However, the video analytics pipelines with edge-cloud collaboration are complex, involving the decision-making for many coupled control knobs. We propose a deep reinforcement learning-based approach, named ModelIO, for dynamic DNN Model selection and Inference Offloading for video analytics with edge-cloud collaboration. We jointly consider the decision-making for video pre-processing, DNN model selection, local inference, and offloading in a video analytics system to maximize performances. Our method can learn the optimal control policy for video analytics with the edge-cloud collaboration without complex system modeling. We implement a real-world testbed to conduct the experiments to evaluate the performances of our method. The results show that our method can significantly improve the system processing capacity, reduce average inference delays, and maximize overall rewards.

Age of Information (AoI) has become a new performance metric that quantifies the freshness of information in the Internet of Things (IoT). To optimize the AoI, the latest information should be frequently sampled and timely updated by source nodes (SNs), which, however, contradicts with the fact that the resources of both the SNs and destination node are limited. To consider this issue, this article formulates a more general multisource information update problem, taking into account both the budget constraint of destination node and the limited sampling/updating capabilities of the SNs. Besides that, two different sampling models, namedsampling-predeterminedandsampling-at-willmodels, have been studied, respectively. Particularly, for the information update problem under the sampling-predetermined model, we prove that it is an NP-hard problem. Then, we propose a greedy algorithm to select the appropriate SNs, and theoretically analyze the bound of the AoI achieved by the proposed algorithm. For the sampling-at-will model, we theoretically derive the minimum AoI that can be achieved under given number of updates, based on which, we design an optimal SNs selection and updating time determination mechanism, to achieve the minimum AoI. Finally, we conduct simulations to evaluate the effectiveness of the proposed algorithms.

Energy harvesting techniques have been increasingly employed in both consumer and industrial applications to provide clean energy supply. Among the many available energy harvesting techniques, ambient energy harvesting (AEH) is a promising one as it harvests free energy from the environment and, thus, is economically efficient. AEH techniques, however, heavily depend on the dynamic environment and are thus uncontrollable and unstable. More recently, the wireless power transfer (WPT) technique has attracted significant attentions due to its highly controllable feature when powering low-cost devices. Unfortunately, WPT faces strict regulatory limitations to provide high power density and requires charging infrastructures installed to perform effective wireless energy transfer. The pros and cons of the two techniques motivate this work to design a hybrid energy harvesting method by charging a device using a combination of AEH and WPT to maximize the throughput of a wireless system. Specifically, this work first proposes an optimal offline charging scheme to maximize the point-to-point data throughput of a wireless system by fully utilizing the ambient energy and providing extra power supply through WPT to determine the transmission rates. An online heuristic algorithm is further proposed to improve the computational efficiency for practical scenarios when the system has the estimation of future AEH patterns. Our experimental results show that the proposed approaches are effective in maximizing the data throughput when compared to the state of the art.

Ride-hailing systems (RHSs) provide passengers with convenient and flexible mobility services, have played an important role in modern urban transportation. With the limited vehicles, RHSs wish to optimize the dispatch of vehicles to requests with the objective of serving as many requests as possible. To address such a city-scale vehicle dispatch problem with thousands of vehicles and requests in each epoch, existing algorithms always take a tradeoff between effectiveness (i.e., real-time) and efficiency (i.e., service rate), such as ignoring future demands to guarantee real-time or solving a complex combinatorial optimization to improve service rate. To guarantee the service rate in a real-time fashion, this paper proposes two novel network flow-based vehicle dispatch algorithms. A network flow-based algorithm (NFBA) is provided to deal with offline scenarios. By constructing the vehicle-shareability network, a min-cost flow is built to find the optimal dispatch of vehicles to requests. To improve the request service rate in real-time, an efficient multi-sample multi-network flow-based algorithm (MNFBA) is proposed for the online scenarios. Each min-cost flow is utilized for a sample of future requests, and online vehicle dispatch policy is averaged over these flows. Extensive simulations based on real-world trip datasets in New York City are conducted. The experimental results show that compared to the benchmarks, our proposed algorithm can generate the dispatch of vehicles to requests within seconds, but can greatly increase the daily request service rate.

Nowadays, not only wearable and portable devices but also aerial and ground robots can be made smaller, lighter, cheaper, and thus as large as hundreds of them may form a swarm to participate in a complicated cooperative application, such as searching, rescuing, mapping, and war-battling. Devices and robots in such a swarm have three important features, namely, large number, high mobility and short distance, hence they form a dynamic and dense wireless network. Successful swarm cooperative applications require low latency communications and real-time localization. This paper proposes to use ultra-wideband (UWB) radio technology to implement both functionalities, because UWB is very time-sensitive that an accurate distance can be calculated using the transmission and reception timestamps of data messages. A UWB swarm ranging protocol is designed to achieve simultaneously wireless data communication and swarm ranging that allows a device/robot to compute the distances to all the peer neighbors at the same time. This protocol is designed for dynamic and dense networks, meanwhile it can also be used in various wireless networks and implemented on various types of devices/robots including low-end ones. In our experiment, this protocol is implemented on Crazyflies, STM32 microcontroller powered micro drones, with onboard UWB wireless transceiver chips DW1000. Extensive real-world experiments are conducted to verify the proposed protocol on various performance aspects, with a total of 9 Crazyflie drones in a compact area. The implemented swarm ranging protocol is open-sourced athttps://github.com/SEU-NetSI/crazyflie-firmware

This paper studies the budget-feasible mechanism design over graphs, where a buyer wishes to procure items from sellers, and all participants (the buyer and sellers) can only directly interact with their neighbors during the auction campaign. The problem for the buyer is to use the limited budget to incentivize sellers to propagate auction information to their neighbors, thereby more sellers will be informed of the auction and more item value will be procured. An impossibility result shows that the large-market assumption is necessary. We propose efficient budget-feasible diffusion mechanisms for large markets that simultaneously guarantee individual rationality, budget-feasibility, strong budget-balance, incentive-compatibility to report private costs and diffuse auction information. Moreover, the proposed mechanisms achieve logarithmic approximation that the total procured value is within a logarithmic factor of the optimal solution. Compared to most related budget-feasible mechanisms, which do not take the individual interactions among sellers into account, our mechanisms can incentivize sellers to further propagate auction information to other potential sellers. Meanwhile, existing related diffusion mechanisms only focus on seller-centric auctions and fail to satisfy the budget-feasibility of the buyer.

Supervised link prediction aims at finding missing links in a network by learning directly from the data suitable criteria for classifying link types into existent or non-existent. Recently, along this line, subgraph-based methods learning a function that maps subgraph patterns to link existence have witnessed great successes. However, these approaches still have drawbacks. First, the construction of the subgraph relies on an arbitrary nodes selection, often ineffective. Second, the inability of such approaches to evaluate adaptively nodes importance reduces flexibility in nodes features aggregation, an important step in subgraph classification. To address these issues, a novel graph-classification based link-prediction model is proposed: Attention and Re-weighting based subgraph Classification for Link prediction (ARCLink). ARCLink first extracts a subgraph around the two nodes whose link should be predicted, by network reweighting, i.e. attributing a weight in the range 0-1 to all links of the original network, and then learns a function to map the subgraph to a continuous vector for classification, thus revealing the nature (non-existence/existence) of the unknown link. For leaning the mapping function, ARCLink generates a vector representation of the extracted subgraph by hierarchically aggregating nodes features according to nodes importance. In contrast to previous studies that either fully ignore or use fixed schemes to compute nodes importance, ARCLink instead learns nodes importance adaptively by employing attention mechanism. Through extensive experiments, ARCLink was validated on a series of real-world networks against state-of-the-art link prediction methods, consistently demonstrating its superior performances

Efficient optimization is a key enabler for emerging intelligent applications in Internet of Vehicles (IoV). However, existing studies in IoV only focus on solving a single domain-specific optimization problem at a time, which undermines their efficiency on tackling various cross-domain optimization tasks in IoV. In this paper, we make the first effort on investigating a novel optimization framework in IoV for cross-domain tasks via vehicular edge computing. Specifically, two typical cross-domain tasks in IoV are presented, namely, the data dissemination (DD) task and the computing offloading (CO) task. Then, a cross-domain problem called DD-CO is formulated to facilitate the sharing of task features and knowledge during the solution searching. On this basis, we propose an evolutionary multitasking approach named EMA, which consists of an integer based unified representation scheme for encoding both the DD and CO tasks in a single solution, a corresponding decoding operator for task-specific solution evaluation, and a new population evolution mechanism for better adaptation to the cross-domain problem optimization. Finally, we build the simulation model and give a comprehensive performance evaluation, which demonstrate the advancement of the new optimization framework via vehicular edge computing and the effectiveness of the proposed EMA method.

In this paper, we consider the problem of designing budget-feasible mechanisms for selecting agents with private costs from various groups to ensure proportional representation, where the minimum proportion of the selected agents from each group is maximized. Depending on agents' membership in the groups, we consider two main models: single group setting where each agent belongs to only one group, and multiple group setting where each agent may belong to multiple groups. We propose novel budget-feasible proportion-representative mechanisms for these models, which can select representative agents from different groups. The proposed mechanisms guarantee theoretical properties of individual rationality, budget-feasibility, truthfulness, and approximation performance on proportional representation.

Nowadays, aerial and ground robots, wearable and portable devices are becoming smaller, lighter, cheaper, and thus popular. It is now possible to utilize tens and thousands of them to form a swarm to complete complicated cooperative tasks, such as searching, rescuing, mapping, and battling. A swarm usually contains a large number of robots or devices, which are in short distance to each other and may move dynamically. So this paper studies the dynamic and dense swarms. The ultra-wideband (UWB) technology is proposed to serve as the fundamental technique for both networking and localization, because UWB is so time sensitive that an accurate distance can be calculated using timestamps of the transmit and receive data packets. A UWB swarm ranging protocol is designed in this paper, with key features: simple yet efficient, adaptive and robust, scalable and supportive. This swarm ranging protocol is introduced part by part to uncover its support for each of these features. It is implemented on Crazyflie 2.1 drones, STM32 microcontrollers powered aerial robots, with onboard UWB wireless transceiver chips DW1000. Extensive real world experiments are conducted to verify the proposed protocol with a total of 9 Crazyflie drones in a compact area.

Mobile devices have been increasingly deployed in large-scale cyber-physical systems (CPS) to traverse the field and retrieve data measurements from designated physical entities with stringent performance requirements. This work studies the availability-constrained real-time data retrieval problem in CPS with a speed adjustable mobile device (AFDR-SA). The goal is to maintain the temporal validity of the real-time data to be retrieved in the system while meeting the data availability constraints imposed by the communication range between the mobile device and the physical entities. A dynamic programming (DP)-based optimal algorithm is proposed for a special but commonly presented scenario where the retrieval times of individual data items are of the same length. Based on this optimal algorithm, an effective heuristic method is further developed for the general case where data items can have arbitrary retrieval times. The effectiveness of the proposed methods are validated through extensive experiments. Our results demonstrate the optimality of the DP-based algorithm, and show that the heuristic method outperforms the state-of-the-art schemes and performs close to the optimal solution obtained by the exhaustive search with much less computational overhead.

In mobile cloud computing, offloading resource-demanded applications from mobile devices to remote cloud servers can alleviate the resource scarcity of mobile devices, whereas long distance communication may incur high communication latency and energy consumption. As an alternative, fortunately, recent studies show that exploiting the unused resources of the nearby mobile devices for task execution can reduce the energy consumption and communication latency. Nevertheless, it is non-trivial to encourage mobile devices to share their resources or execute tasks for others. To address this issue, we construct an auction model to facilitate the resource trading between the owner of the tasks and the mobile devices participating in task execution. Specifically, the owners of the tasks act as bidders by submitting bids to compete for the resources available at mobile devices. We design a distributed auction mechanism to fairly allocate the tasks, and determine the trading prices of the resources. Moreover, an efficient payment evaluation process is proposed to prevent against the possible dishonest activity of the seller on the payment decision, through the collaboration of the buyers. We prove that the proposed auction mechanism can achieve certain desirable properties, such as computational efficiency, individual rationality, truthfulness guarantee of the bidders, and budget balance. Simulation results validate the performance of the proposed auction mechanism.

Despite the salient feature of cloud computing, the cloud provider still suffers from electricity bill, which in part comes from 1) the power consumption of running physical machines (PMs) to guarantee the resource/time requirements of virtual machines (VMs), and 2) the dynamically varying electricity price offered by smart grids. In the literature, there exist viable solutions adaptive to electricity price variation to reduce the electricity bill. However, they are not applicable to serving time-sensitive VM requests. In serving time-sensitive VM requests, it is potential for the cloud provider to apply proper consolidation strategies to further reduce the electricity bill. Few prior works have provided theoretical solutions of VM consolidation strategies that are adaptive to electricity price variations in serving time-sensitive VM requests. In this work, to address this challenge, we develop electricity-price-aware consolidation algorithms for both the offline and online scenarios. For the offline scenario, we first develop a consolidation algorithm with constant approximation, which always approaches the optimal solution within a constant factor of 5. For the online scenario, we propose an$O(\log (\frac{L_{max}}{L_{min}}))$-competitive algorithm that is able to approach the optimal offline solution within a logarithmic factor, where$\frac{L_{max}}{L_{min}}$is the ratio of the longest length of the processing time requirement of VMs to the shortest one. Our trace-driven simulation results further demonstrate that the average performance of the proposed algorithms produce near-optimal electricity bill.

The identification of wood is an important problem both in industrial manufacturing and in people's daily life. Traditional methods based on experts are laborious. New technologies based on computer visions rely on high-quality cross section images. In this paper, we take the first attempt to identify the wood type based on commodity RFID devices. A system named RF-WTI is proposed. The main idea of RF-WTI is that different wood types result in different signal changes when RF signals pass through the wood. Specifically, after collecting the changes of Received Signal Strength (RSS) and phase when RFID signals pass through the wood, a feature that is unique for the wood is derived. Then RF-WTI applies a Bayesian neural network to identify wood types. Experimental results show that RF-WTI achieves 92.33% average accuracy for identifying 12 different types of wood.

Most existing models of energy efficiency retrofit are able to evaluate energy saving and retrofit cost for a certain stakeholder, but unable to guide how to allocate retrofit task and incentive among multiple stakeholders. The multistakeholder situation is firstly modeled in the proposed crowdsourcing model (CM), which contributes to quantify the utility of each competitive stakeholder with respect to participation decision. To solve the CM, a Stackelberg game approach is newly developed in this article to find rational and efficient strategies of task/incentive allocation. For the building energy efficiency retrofit, the challenge of CM is to handle mixed-integer decisions of energy service companies. We prove the existence of Stackelberg equilibrium (SE), which introduces the optimal budget, and the Nash equilibrium of task allocation. To compute the SE of CM, effective search algorithms are designed based on best response and optimization techniques. Simulation results have verified the CM and game theoretical approach. The resulted SE has provided stable and efficient strategies of incentive/task allocation.

Deep learning is a popular direction in computer vision and digital image processing. It is widely utilized in many fields, such as robot navigation, intelligent video surveillance, industrial inspection, and aerospace. With the extensive use of deep learning techniques, classification and object detection algorithms have been rapidly developed. In recent years, with the introduction of the concept of “unmanned retail,” object detection, and image classification play a central role in unmanned retail applications. However, open-source datasets of traditional classification and object detection have not yet been optimized for application scenarios of unmanned retail. Currently, classification and object detection datasets do not exist that focus on unmanned retail solely. Therefore, in order to promote unmanned retail applications by using deep learning-based classification and object detection, in this article we collected more than 30 000 images of unmanned retail containers using a refrigerator affixed with different cameras under both static and dynamic recognition environments. These images were categorized into ten kinds of beverages. After manual labeling, images in our constructed dataset contained 155 153 instances, each of which was annotated with a bounding box. We performed extensive experiments on this dataset using ten state-of-the-art deep learning-based models. Experimental results indicate great potential of using these deep learning-based models for real-world smart unmanned vending machines.

In the past decade, unmanned aircraft systems (UASs) have been widely used in various civilian applications, most of which involve only a single unmanned aerial vehicle (UAV). In the near future, more and more UAS applications will be facilitated by the cooperation of multiple UAVs. In such applications, it is desirable to utilize a general control platform for cooperative UAVs. However, existing open-source control platforms cannot fulfill such a demand because (1) they only support the leader-follower mode, which limits the design options for fleet control, (2) existing platforms can support only certain type of UAVs and thus lack compatibility, and (3) these platforms cannot accurately simulate a flight mission, which may cause a big gap between simulation and real-world flight. To address these issues, we propose a general control and monitoring platform for cooperative UAS, namely, CoUAS , which provides a set of core cooperation services of UAVs, including synchronization, connectivity management, path planning, energy simulation, and so on. To verify the applicability of CoUAS, we design and develop a prototype in which an embedded path planning service is provided to complete any task with the minimum flying time while considering the network connectivity and coverage. Experimental results by both simulation and field test demonstrate that the proposed system is viable.

In cloud computing, it is crucial to maintain service continuity, while power outage is one of the most common and serious threats. To improve the resilience of cloud against power outage, a service provider usually deploys emergency energy supply (e.g., UPSs and generators) in a data center. When a power outage at a data center happens, the cloud service provider needs to make the operation decision on which subset of VMs to keep running and which servers to host such VMs to minimize its loss (or maximize its profit) using the emergency energy supply while the selected VMs are running in the affected data center until they are finished, migrated to other data centers, or normal power supply of the affected data center has been restored. No prior research has theoretically studied such a cloud service continuity problem under power outage. In this paper, we tackle this challenge and investigate the cloud service continuity problem. Specifically, we consider that a profit is associated with maintaining the continuity of a service, denoted as service continuity profit. Based on that we first formulate an optimization problem that aims to maximize the total profit subject to energy constrains. After showing the hardness of the problem, we focus on the design of approximation algorithms for solving the problem, where we consider two practical cases. In the first one with sufficient number of servers for re-provisioning, we develop a constant approximation algorithm of which the worst-case performance approaches the optimal solution within a constant factor (≈4.5-6.4). In the second one, we consider the general case with limited number of servers, and we develop an approximation algorithm with an approximation ratio of around 5.7-8. By combining these two algorithms together, we can achieve both good worst-case performance and average performance. Simulation results demonstrate the efficiency in terms of maximizing the service continuity profit of the proposed algorithms.

With rapid development of Internet of Things (IoT) and pervasive computing, indoor localization and tracking has attracted considerable attentions. This work aims at designing an effective and scalable indoor tracking system based on smart phones embedded with Wi-Fi interfaces and inertial sensors. Specifically, we first propose a zero site-survey overhead algorithm (ZSSO), which includes a step detection mechanism, a map constraint construction method and a customized particle filter. The step detection mechanism is used to count user steps based on raw data extracted from inertial sensors. The map constraint construction method is adopted to generate obstacle constraints of the indoor environment based on a two-step conversion method designed for indoor map. Finally, a customized particle filter is proposed to track user's positions continuously. Further, we propose an enhanced version of ZSSO (i.e., E-ZSSO) to improve tracking performance by incorporating with Wi-Fi fingerprint based localization technique. First, an automatic Wi-Fi fingerprint collection mechanism is developed for building the fingerprint database without extra site-survey overhead. Then, the Wi-Fi fingerprint based localization results are further adopted to speed up the convergence of the particle filter as well as to better calibrate the localization results. We have implemented the indoor tracking system in real-world environments and conducted comprehensive performance evaluation. The field testing results conclusively demonstrate the scalability and effectiveness of our proposed algorithms.

In recent years, deep learning techniques have been commonly used in the fields of image processing and computer vision. With the popularity of deep learning models, researchers have developed many effective object detection methods. Unmanned retail applications start to utilizing object detection algorithms for changing traditional retail modes. Until now, there is no public datasets for object detection in unmanned retail application environments. Moreover, state-of-the-art deep learning-based object detection models have not yet been examined in this application scenario. In this paper, we compiled a large-scale dataset which contains over 30,000 images captured in a refrigerator equipped with different cameras. 10 kinds of beverages were utilized for targeted objects. An empirical study on this dataset is performed by using several recent developed deep learning models. Results demonstrate the effectiveness of using deep learning techniques real-life unmanned retail environments.

Billions of lightweight Internet of Things (IoT) devices have been deployed for various applications nowadays. Most of them first collect interested data and then process them in some degree according to application requirements. Transparent computing (TC) is a promising technique that makes such lightweight devices suitable to process even large-size applications. The advantage of TC is to separate code storage from its execution, allowing IoT devices to load code blocks from nearby TC storage server on demand. Distinct from existing work, this paper allows the TC IoT devices to offload some tasks to servers, since wireless IoT devices are usually powered by batteries, having limited energy resources. If a task is offloaded, a challenging problem is that its input data collected by the IoT device must be transferred as well, which incurs additional transmission time and energy. This paper proposes a two-step approach aiming at minimizing the energy consumption of the IoT device while satisfies the delay constraint. This approach first studies the offloading decision problem that determines for each task whether to offload task data or load task code blocks, while loading code indicates code receiving and executing energy cost. Second, the transmission power scheduling problem is investigated to further reduce offloading energy for a given delay constrained offloading task set. Heuristic decision making algorithms and optimal power scheduling algorithm are proposed, respectively. Such two-step approach is shown by extensive simulation to be near optimal for the original problem thanks to the optimal design of the power scheduling algorithm.

Radiative wireless power transfer (WPT) is a promising technique to power wireless devices' transmission. In a resource-limited device, receiving energy and transmitting data cannot operate at the same time because they share the same spectrum or hardware. This paper studies the problem for a wireless device to decide when to harvest energy, when to deliver data, and what transmission rate to use. Distinct from the most existing works, we focus on delay minimization in transmitting a sequence of data packets over a point-to-point channel, which is critical for time-sensitive applications. Since the battery is capacitated, the device must repeatedly switch between harvesting energy and transmitting data. For the offline case where packet information is known before scheduling, a surprising result is discovered that for all (energy receiving and data transmitting) cycles, except the last one, the optimal transmission rate should be a constant which is called the wOPT rate. Based on this discovery, the offline delay minimization problem is optimally solved. For the online case where packets arrive dynamically without prior information, we propose a simple online algorithm: using the wOPT rate to transmit whenever both energy and data are ready. It is proved to be 1.16-competitive if the battery is initially empty, namely, its delay is less than 1.16 times the offline optimal delay for any given packet set. When the battery is with arbitrary initial energy, simulation results show that the performance is near optimal. The discovery of the wOPT rate reveals an essential property of WPT and is expected to be significant in solving other related problems.

Transmission is crucial for big data analysis and learning in industrial Internet of Things (IoT) systems. To transmit data with limited energy is a challenge. This paper studies the problem of data transmission in energy harvesting systems with capacitor to supply energy where the energy receiving rate varies over time. The energy receiving rate is slower when the capacitor receives more energy. Based on this characteristic, we study the problem of how to transmit more data when the energy receiving time is not continuous. Given many packets that arrive at different time instances, there is a tradeoff between transmitting the packet right now or saving the energy to transmit the future arriving packets. We formalize two types of problems. The first one is how to minimize the total completion time when there is enough energy to transmit all the packets. The second one is how to transmit as many packets as possible when the energy is not enough to transmit all the packets. For the first problem, we give a 1 + α approximation off line algorithm when all the information of the packets and the energy receiving periods is known in advance, and a max{2, β} competitive ratio online algorithm where the information is not known in advance. For the second problem, we study three cases and give a 6 + [h/(b/R)] approximation off line algorithm for the general situation. We also prove that there does not exit a constant competitive ratio online algorithm.

With the increasing complexity of tasks that are crowdsourced, requesters need to form teams of professional workers that can satisfy complex task skill requirements. Team crowdsourcing in social networks (SNs) provides a promising solution for complex task crowdsourcing, where the requester hires a team of professional workers that are also socially connected can work together collaboratively. Previous social team formation approaches have mainly focused on the algorithmic aspect for social welfare maximization; however, within the traditional objective of maximizing social welfare alone, selfish workers can manipulate the crowdsourcing market by behaving untruthfully. This dishonest behavior discourages other workers from participating and is unprofitable for the requester. To address this strategic social team crowdsourcing problem, truthful mechanisms are developed to guarantee that a worker's utility is optimized when he behaves honestly. This problem is proved to NP-hard, and two efficient mechanisms are proposed to optimize social welfare while reducing time complexity for different scale applications. For small-scale applications where the task requires a small number of skills, a binary tree network is first extracted from the social network, and a dynamic programming-based optimal team is formed in the binary tree. For large-scale applications where the task requires a large number of skills, a team is formed greedily based on the workers' social structure, skill, and working cost. For both mechanisms, the threshold payment rule, which pays each worker his marginal value for task completion, is proposed to elicit truthfulness. Finally, the experimental results of a real-world dataset show that compared to the benchmark exponential VCG truthful mechanism, the proposed small-scale-oriented mechanism can reduce computation time while producing nearly the same social welfare results. Furthermore, compared to other state-of-the-art polynomial heuristics, the proposed large-scale-oriented mechanism can achieve truthfulness while generating better social welfare outcomes.

This paper considers the mechanism design problem in two-sided markets where multiple strategic buyers come with budgets to procure as much value of items as possible from the strategic sellers. Each seller holds an item with public value and is allowed to bid its private cost. Buyers could claim their budgets, not necessarily the true ones. The goal is to seek budget-feasible mechanisms that ensure sellers are rewarded enough payment and buyers' budgets are not exceeded. Our main contribution is a random mechanism that guarantees various desired theoretical guarantees like the budget feasibility, the truthfulness on the sellers' side and the buyers' side simultaneously, and constant approximation to the optimal total procured value of buyers.

In the “network-as-a-service” paradigm, network operators have a strong need to know the metrics of critical paths running services to their users/tenants. However, it is usually prohibitive to directly measure the metrics of all such paths due to the measuring overhead. A practical solution is to use network tomography to infer the metrics of such paths based on observations from a small number of monitoring nodes. This problem is termed as path identifiability problem, a new problem that largely differs from existing link identifiability problems. we show that the new problem is harder than link identifiability problems, in the sense that fewer monitors are required for identifying the metrics of given paths than for identifying the metrics of links along the paths. To solve the problem, we develop sufficient and necessary conditions for the identifiability of a given set of interested paths, and design an efficient algorithm that deploys the minimum number of monitors. Experiments show a saving of up to 40% fewer monitors that guarantee the identifiability of a given set of paths.

This work aims to design and implement a scalable and easy-deployed indoor localization system based on particle filter and Wi-Fi fingerprint techniques. Specifically, our system leverages particle filter to estimate user's location and automatically scans Wi-Fi fingerprints. Then, we utilize the collected fingerprints to speed up the convergence of particles. Finally, the system iteratively refines the collected fingerprints by evaluating their performance duration the on-line localization phase, which is able to further enhance the positioning accuracy. We implement the system on Android platform and give a comprehensive performance evaluation by setting up the system in our lab area and comparing the algorithm with conventional fingerprint-based solutions. Experimental results demonstrate the scalability and effectiveness of the proposed solution.

Wireless power transfer (WPT) is a recently developed technique to perfectly address the energy problem for smart city sensors that do not have a readily wired power supply. In a radio-frequency-powered wireless communication system, sensors first harvest energy via the radio-frequency WPT, and then, transmit sensed data to the receiver. The “harvest-then-transmit” protocol is used to coordinate the two operations, in which we wish to optimally decide when to harvest energy, when to transmit data, and what transmission rate should be used such that the data are maximally transmitted. Unlike existing works, we assumed that the wireless transferred power is dynamically changing, instead of being constant, which is more realistic in green smart city applications, e.g., Industry 4.0 workshop, smart transportation, and smart buildings, where environments are continuously changing, so the wireless transferred power is affected dynamically. In this paper, we present an optimal scheduling algorithm for the offline case where the varying WPT is known in advance. Based on the optimal principles learned from the offline case, we have designed an efficient online algorithm. Finally, we report our simulation results that demonstrate that our online scheduling algorithm can adaptively and efficiently achieve high data throughput.

Efficient data dissemination is critical for enabling emerging applications in vehicular ad hoc networks. As a typical traffic scenario, the bidirectional road scenario of highways bring unique challenges on well exploiting the benefit of vehicle-to-vehicle (V2V) communication for data sharing among vehicles driving in opposite directions. This paper is dedicated to investigating the characteristics of data services in such a scenario and exploring new opportunities for enhancing overall system performance. Specifically, we present a system architecture to enable the road-side unit assisted data scheduling via vehicle-to-infrastructure communication. Then, we give a theoretical analysis on the opportunity of successful data sharing among vehicles driving in opposite directions based on the analysis of signal-to-interference-noise-ratio of V2V communication. On this basis, we propose a clustering mechanism based on the design of a time division policy and the derivation of the optimal cluster length. In addition, a cluster association strategy is designed to enable vehicles to dynamically join or leave a cluster based on their real-time velocities. Furthermore, a two-phase backoff mechanism is designed for distributed data sharing based on V2V communication, and a cooperative scheduling algorithm is proposed for selecting sender vehicles as well as the corresponding data items for broadcasting. Finally, we build the simulation model and give a comprehensive simulation study, which demonstrates that the proposed solutions can effectively improve the overall system performance.

With recent advances in wireless communications, vehicular networks are envisioned as a promising paradigm on achieving breakthroughs in transportation safety, efficiency, and sustainability. This work investigates data broadcast via Infrastructure-to-Vehicle (I2V) communication by exploiting the vehicular caching and network coding for enhancing bandwidth efficiency of the road-side unit (RSU). Specifically, we present an architecture for providing real-time data services via I2V communication in the service range of a RSU. Then, we investigate the problem of cache-aided data dissemination with network coding and prove that it is NP-hard. Further, we propose a memetic algorithm, which consists of a binary vector representation for encoding solutions, a fitness function for solution evaluation, a set of operators for offspring generation, a local search method for solution enhancement and a repair operator for fixing infeasible solutions. Finally, we build the simulation model and give a comprehensive performance evaluation to demonstrate the superiority of the proposed solution.

Despite the increased capabilities of mobile devices, resource-demanded mobile applications still transcend what can be accomplished on a single device. As such, mobile device cloud (MDC), an environment that enables computation-intensive tasks to be performed among a set of nearby mobile devices, offers a promising architecture to support real-time mobile applications. To stimulate mobile devices to execute tasks for others, it is essential to design an incentive mechanism that appropriately charges the owners of the tasks, acted as the buyers, and rewards the mobile devices, acted as the sellers. In this paper, we propose two truthful auction mechanisms for two different task models, heterogeneous and homogeneous task models, which assume the different and the same resource requirements of the tasks, respectively. Specifically, for heterogeneous task model, we propose an efficient heuristic winning bids determination algorithm to allocate the tasks, and decide the payment of each seller for its winning bids. For homogeneous task model, we design an optimal winning bid determination algorithm, and propose a Vickrey-Clarke-Groves (VCG) based auction mechanism to determine the payment of each bid. Both theoretical analysis and simulations show that the proposed auction mechanisms achieve several desirable properties such as individual rationality, truthfulness and computational efficiency.

In crowdsourcing markets, a requester announces a task and calls for contribution from potential participants. With strategic participants, the requester needs to reward the participants to introduce the incentives of participation. However, it is natural to ask whether it is worth introducing incentives if the total payment for eliciting incentives is too high. This paper addresses such a fundamental concern by designing a frugal mechanism with minimum payment used to procure the total amount of service contributions demanded. We design two mechanisms to provide the incentives of participation while minimizing the payment used by the requester. We first propose a frugal auction-based mechanism, which stimulates participants to truthfully report their information. We theoretically prove that the payment used is not more than the optimal cost (with no incentive considered) plus a bounded additive. We then design a Stackelberg-game-based mechanism, in which the requester fixes a certain total payment at the very beginning so as to encourage the participants to compete for it and participate in the task. We verify the existence of a unique Nash equilibrium (NE) and develop a novel algorithm to find the NE, as well as the optimal payment to extract the NE. Our simulation results show that the payment used in these mechanisms is close to the optimal solution with no incentive considered, while the extra payment caused by introducing truthfulness in auction-based mechanism is about twice that of the NE in Stakelberg-game-based mechanism.

Due to the low pollution and sustainable properties, using electric buses for public transportation systems has attracted considerable attention, whereas how to recharge the electric buses with long continuous service hours remains an open problem. In this paper, we consider the problem of placing electric vehicle (EV) charging stations at selected bus stops, to minimize the total installation cost of charging stations. Specifically, we study two EV charging station placement cases, with and without considering the limited battery size, which are called ECSP_LB and ECSP problems, respectively. The solution of the ECSP problem achieves the lower bound compared with the solution of the ECSP_LB problem, and the larger the battery size of the EV, the lower the overall cost of the charging station installation. For both cases, we prove that the placement problems under consideration are NP-hard and formulate them into integer linear programming. Specifically, for the ECSP problem we design a linear programming relaxation algorithm to get a suboptimal solution and derive an approximation ratio of the algorithm. Moreover, we derive the condition of the battery size when the ECSP problem can be applied. For the ECSP_LB problem, we show that, for a single bus route, the problem can be optimally solved with a backtracking algorithm, whereas for multiple bus routes we propose two heuristic algorithms, namely, multiple backtracking and greedy algorithms. Finally, simulation results show the effectiveness of the proposed schemes.

Energy harvesting communication system enables energy to be dynamically harvested from natural resources and stored in capacitated batteries to be used for future data transmission. In such a system, the amount of future energy to harvest is uncertain and the battery capacity is limited. As a consequence, battery overflow and energy dropping may happen, causing energy underutilization. To maximize the data throughput by using the energy efficiently, a rate-adaptive transmission schedule must address the trade-off between a high-rate transmission which avoids energy overflow and a low-rate transmission which avoids energy shortage. In this paper, we study an online throughput maximization problem without knowing future information. To the best of our knowledge, this is the first work studying the fully-online transmission rate scheduling problem for battery-capacitated energy harvesting communication systems. We consider the problem under two models of the communication channel, a static channel model that assumes the channel status is stable, and a fading channel model that assumes the channel status varies. For the former, we develop an online algorithm that approximates the offline optimal solution within a constant factor for all possible inputs. For the latter, that the channel gains vary in range [hmin; hmax], we propose an online algorithm with a proven ⊖(log(hmax/ hmin))-competitive ratio. Our simulation results further validate the efficiency of the proposed online algorithms.

Cloud computing has emerged as a very flexible service paradigm by allowing users to require virtual machine (VM) resources on-demand and allowing cloud service providers (CSPs) to provide VM resources via a pay-as-you-go model. This paper addresses the CSP's problem of efficiently allocating VM resources to physical machines (PMs) with the aim of minimizing the energy consumption. Traditional energy-aware VM allocations either allocate VMs to PMs in a centralized manner or implement VM migrations for energy reduction without considering the migration cost in cloud computing systems. We address these two issues by introducing a decentralized multiagent (MA)-based VM allocation approach. The proposed MA works by first dispatching a cooperative agent to each PM to assist the PM in managing VM resources. Then, an auction-based VM allocation mechanism is designed for these agents to decide the allocations of VMs to PMs. Moreover, to tackle system dynamics and avoid incurring prohibitive VM migration overhead, a local negotiation-based VM consolidation mechanism is devised for the agents to exchange their assigned VMs for energy cost saving. We evaluate the efficiency of the MA approach by using both static and dynamic simulations. The static experimental results demonstrate that the MA can incur acceptable computation time to reduce system energy cost compared with traditional bin packing and genetic algorithm-based centralized approaches. In the dynamic setting, the energy cost of the MA is similar to that of benchmark global-based VM consolidation approaches, but the MA largely reduces the migration cost.

Wireless power transfer (WPT) technique enables wireless charging/recharging, thus is a promising way to power wireless devices' transmissions. Because current WPT technique requires a wireless device to stop transmitting data when receiving power, and also because the received power in this way is limited, careful scheduling is needed to decide when the device should receive power and when it should transmit such that data can be efficiently transmitted. This paper assumes the most fundamental point-to-point White Gaussian Noise channel is used for data transmission and attempts to obtain an optimal scheduling such that a sequence of data packets can be transmitted with the minimum delay. It is discovered that, for all (energy receiving, data transmitting) cycles, except the last one, the optimal transmission rate should be a constant which is called the wOPT rate. Based on this discovery, this paper optimally solves the offline delay minimization problem. Then, an online heuristic scheduling algorithm is proposed, which either receives energy or transmits at the wOPT rate. Simulations have demonstrated its efficiency. The discovery of the wOPT rate reveals an essential property of WPT, thus is expected to make significant impact in the field of WPT.

In a participatory sensing system, data sensed from smartphone users are shared with the general public who requests data through submitting tasks. When multiple tasks request the data from a mobile user, the mobile user can make a transmission schedule to achieve the balance between the amount of data transmitted and energy consumption. Intuitively, reducing the amount of data transmitted by making use of data sharing between the tasks can save the energy consumption. However, due to the convexity of rate-power function for rate-adaptive transmitting devices, a schedule purely minimizing the amount of data transmitted may not always be the optimal one minimizing the energy consumption. Thus, there exists a tradeoff between the amount of data transmitted and energy consumption. This paper formulates the problem as a bi-objective optimization problem to simultaneously minimize the amount of data transmitted and the energy consumption. Two task models are studied, first-in-first-out (FIFO) task model and arbitrary deadline (AD) task model, respectively. We first provide optimal algorithms for the off-line case. We then study the online case where requests arrive dynamically without prior information. For FIFO tasks, we develop an online algorithm that is O(ln L)-competitive with respect to both the amount of data transmitted and energy consumption, where L is the longest length of the time duration of the tasks. For AD tasks, we devise an online algorithm that is O(ln2L)-competitive with respect to both the amount of data transmitted and energy consumption. Our simulation results validate the efficiency of our online algorithms.

Vehicle-to-vehicle/vehicle-to-infrastructure (referred to as V2X) communications have potential to revolutionize current road transportation systems with respect to vehicle safety, transportation efficiency, and travel experience. This paper puts the first effort on applying network coding in cooperative V2X communication environments to improve bandwidth efficiency and enhance data service performance. Specifically, we investigate new arising challenges on network-coding-assisted data dissemination by considering both communication constraints and application requirements in vehicular networks. We present the system model and give an insight into the characteristics of cooperative data dissemination with network coding. On this basis, we formulate the problem and propose a network-coding-assisted scheduling algorithm to enable the hybrid of vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communications and exploit their joint effects on providing efficient data services. We design a cache strategy that allows vehicles to retrieve their unrequested data items. This strategy not only increases the opportunity of data sharing among vehicles but also gives higher probability of packet decoding, which in turn enhances the data service performance. We give an intensive analysis on the scheduling overhead, which shows the scalability of the algorithm. Finally, we build the simulation model and conduct a comprehensive performance evaluation to demonstrate the superiority of the proposed solution.

In a wireless system, when multiple applications can share data transmitted by rate-adaptive wireless devices, there exists a trade-off between transmission redundancy and energy efficiency. This paper conducts the first theoretical analysis on such a trade-off. We formulate the problem as a bi-objective optimization problem to simultaneously minimize the transmission redundancy and the energy consumption. In the offline setting that the full information is known in advance, we provide optimal algorithms for the bi-objective optimization problem. In the online setting, we provide an online algorithm with proven performance bound to approximate the optimal solution without relying on any assumed distribution or future information. The proposed online algorithm is proved O(ln T)-competitive with respect to transmission redundancy and also O(ln T)-competitive with respect to energy consumption, where T is the number of time slots. That is, the output of the algorithm always approximates the optimal solution within a logarithmic factor over all possible inputs. Our simulation results further validate the efficiency of our online algorithm.

Myopia becomes a more and more serious worldwide problem as the number of myopic people (especially young people) grows rapidly. Efficient methods are required to monitoring the deterioration of nearsightness so as to take further treatment. This demo realizes a noval nearsightness monitoring system, called iSee, which utilizes the widely used smartphones to detect the deterioration of nearsightness by monitoring and analysing the the distance between the eyes and the smartphone screen. A prototype of iSee has been developed to evaluated the effectiveness under different environmental conditions.

This paper presents an optimal rate scheduling algorithm called Truncation for an energy-harvesting enabled wireless transmitter to transmit a set of dynamically arrived packets with minimum transmission energy. Distinct from existing works, we allow packets to have individual delay constraints, which is the most general model ever assumed but is very much desired to guarantee per-application quality-of-service (QoS). Moreover, we restrict the allowable rates to a set of discrete values, which is more practical and required in many real applications. As the first achievement, we obtain an optimal offline algorithm, which assumes the rate is continuously adjustable. Then, we propose a general framework that transforms any algorithm using the continuous-rate model into an algorithm using only discrete-rates, while preserving the optimality as long as the optimality holds for convex rate-power functions. It is possible that the harvested energy is insufficient to guarantee all packets to meet their deadlines. Should this occur, maximizing throughput with the limited available energy becomes the goal to achieve. Our Truncation algorithm is able to identify this case and produces a schedule that guarantees maximum throughput, if packets share a common deadline. Furthermore, based on the optimal offline algorithms, an efficient online algorithm is designed which has been shown by simulations to produce near optimal results.

To upgrade the systems or fix the security issues, some physical machines (PMs) in data centers are required to undergo a maintenance process, which might disable the continuous services of the virtual machines (VMs) run on them for a few time slots. To reduce the waiting delay, one may migrate the VMs to other active PMs. However, it will incur extra migration cost, e.g., bandwidth or memory used to move data. To balance the tradeoff between delay and migration cost, we formulate a two-objective optimization problem, which minimizes both delay and migration cost according to a certain weightage, so as to decide whether the VMs should be migrated to other active PMs or should wait their own maintained PMs to be back. We first prove that the proposed problem is NP-hard. For a special case, where each VM requires the same size of resource, we show that the defined problem can be converted to minimum weighted bipartite matching problem in an auxiliary bipartite graph. A lower bound of the delay is derived for a specific setting. For the general case of the problem, we also design an efficient heuristic algorithm. Finally, simulation results demonstrate the effectiveness of the proposed scheme.

Recent advances in infrastructure-to-vehicle (I2V) and vehicle-to-vehicle (V2V) communications are envisioned to enable a variety of emerging applications in vehicular networks, where it is imperative to provide efficient data services via cooperative vehicular communications. In this work, we present the data dissemination system via cooperative I2V and V2V communications. We formulate the problem by investigating both the communication constraint and the application requirement on data dissemination. The goal is to maximize the system performance by exploiting the joint effects of I2V and V2V communications. On this basis, we propose an on-line scheduling algorithm to enable scalable, fair and robust data dissemination. The algorithm makes scheduling decisions by transforming the data dissemination problem to the maximum weighted independent set (MWIS) problem and approximately solving MWIS using a greedy method. We build the simulation model based on realistic traffic and communication characteristics. A comprehensive simulation study demonstrates that the proposed solution is able to effectively strike a balance between I2V and V2V data services and maximize system performance in terms of scalability, fairness and robustness.