Artificial Intelligence (AI) is crucial to numerous functions required for driving automation systems, including the computer vision techniques used to detect the roadway environment and make real-time decisions. However, the images used as inputs to the AI system may be maliciously perturbed, or manipulated, causing the AI system to make an incorrect classification. In this study, we examined humans’ perception of the AI’s computer vision capability of classifying various road sign images, including the original images, images with two different types of malicious attacks, and images that are scrambled randomly at the pixel level. Our results showed that participants rated the AI agent to be less capable than themselves of classifying the road signs. However, they overestimated the AI’s computer vision capability for correctly classifying images with malicious attacks that should cause the AI system to misclassify the image. These findings suggest that people lack an accurate understanding of the vulnerabilities of AI computer vision technologies and tend to overtrust AI in driving automation systems.

Federated learning relies on distributed training on mobile device. The previous research mainly focuses on addressing the heterogeneity from computation and data distributions. As battery life remains to be the performance bottleneck on mobile devices, energy consumption from the persistent training tasks poses great challenges. In this paper, we propose an online scheduler to optimize energy usage by leveraging application co-execution and asynchronous gradient updates. Motivated by a series of preliminary experiments, we find that placing the training process in the background while co-running a foreground application gives the system a large energy discount. Based on these findings, we first study an offline baseline assuming all the application occurrences are known in advance, and propose a dynamic programming solution. Then we propose an online scheduler using the Lyapunov framework to exploit the energy-staleness/slowdown trade-offs and prove the convergence at the rate of$1/\sqrt{K}$. We conduct extensive experiments on a mobile testbed with devices from different vendors. The results indicate 10-30% energy saving and much faster convergence compared to FedAvg and FedProx with 3-4% higher testing accuracy under the non-IID data setting. The design is also validated in terms of resource utilization, memory bandwidth and Frame-Per-Second rates.

Mobile authentication using behavioral biometrics has been an active area of research. Existing research relies on building machine learning classifiers to recognize an individual’s unique patterns. However, these classifiers are not powerful enough to learn the discriminative features. When implemented on the mobile devices, they face new challenges from the behavioral dynamics, data privacy and side-channel leaks. To address these challenges, we present a new framework to incorporate training on battery-powered mobile devices, so private data never leaves the device and training can be flexibly scheduled to adapt the behavioral patterns at runtime. We re-formulate the classification problem into deep metric learning to improve the discriminative power and design an effective countermeasure to thwart side-channel leaks by embedding a noise signature in the sensing signals without sacrificing too much usability. The experiments demonstrate authentication accuracy over 95 percent on three public datasets, a sheer 15 percent gain from multi-class classification with less data and robustness against brute-force and side-channel attacks with 99 and 90 percent success, respectively. We show the feasibility of training with mobile CPUs, where training 100 epochs takes less than 10 mins and can be boosted 3-5 times with feature transfer. Finally, we profile memory, energy and computational overhead. Our results indicate that training consumes lower energy than watching videos and slightly higher energy than playing games.

Smart transportation shall address utility waste, traffic congestion, and air pollution problems with least human intervention in future smart cities. To realize the sustainable operation of smart transportation, we leverage solar-harvesting charging stations and rooftops to power electric autonomous vehicles(AVs) solely via design. With a fixed budget, our framework first optimizes the locations of charging stations based on historical spatial-temporal solar energy distribution and usage patterns, achieving $(2+\epsilon)$ factor to the optimal. Then a stochastic algorithm is proposed to update the locations online to adapt to any shift in the distribution. Based on the deployment, a strategy is developed to assign energy requests in order to minimize their traveling distance to stations while not depleting their energy storage. Equipped with extra harvesting capability, we also optimize route planning to achieve a reasonable balance between energy consumed and harvested en-route. As a promising application, utility optimization of shared electric AVs is discussed, and $(2k\!+\!1)$ -approx algorithm is proposed to manage $k$ vehicles simultaneously. Our extensive simulations demonstrate the algorithm can approach the optimal solution within 10-15% approximation error, improve the operating range of vehicles by up to 2-3 times, and improve the utility by more than 50% compared to other competitive strategies.

Internet of Things (IoT) is progressively becoming an essential aspect of daily life that can be sensed anywhere and anytime, transforming the traditional lifestyle into a high-tech one. Numerous applications in the edge are brought to life based on IoT infrastructures. Especially, edge computing has witnessed the proliferation and impact of IoT-enabled devices benefiting from the data collection and computation capabilities of IoT. However, establishing an IoT from scratch can be monetarily expensive, and leasing the existing sub-networks confronts the potentially dishonest behavior of service providers. To address these issues, we propose a novel framework of leasing edge IoT networks and analyze the influence of sub-network owners’ dishonest behavior on the network. We model the interaction between the edge user and the owners of sub-networks by a Stackelberg game with a unique equilibrium, jointly analyzing the pricing and data collection mechanisms. The Primal-dual Decomposition algorithm and its theoretical analyses are provided for the corresponding strategies of the edge user and sub-network owners. Evaluations demonstrate that the proposed algorithm in the leasing model can save data collection cost up to 53% compared with existing data collection strategies, and illustrate the difference in network performance compared with the game without dishonest owners.

Energy is an essential, but often forgotten aspect in large-scale federated systems. As most of the research focuses on tackling computational and statistical heterogeneity from the machine learning algorithms, the impact on the mobile system still remains unclear. In this paper, we design and implement an online optimization framework by connecting asynchronous execution of federated training with application co-running to minimize energy consumption on battery-powered mobile devices. From a series of experiments, we find that co-running the training process in the background with foreground applications gives the system a deep energy discount with negligible performance slowdown. Based on these results, we first study an offline problem assuming all the future occurrences of applications are available, and propose a dynamic programming-based algorithm. Then we propose an online algorithm using the Lyapunov framework to explore the solution space via the energy-staleness trade-off. The extensive experiments demonstrate that the online optimization framework can save over 60% energy with 3 times faster convergence speed compared to the previous schemes.

Multi-armed bandits problem has been widely utilized in economy-related areas. Incentives are explored in the sharing economy to inspire users for better resource allocation. Previous works build a budget-feasible incentive mechanism to learn users’ cost distribution. However, they only consider a special case that all tasks are considered as the same. The general problem asks for finding a solution when the cost for different tasks varies. In this paper, we investigate this problem by considering a system with$k$levels of difficulty. We present two incentivizing strategies for offline and online implementation, and formally derive the ratio of utility between them in different scenarios. We propose a regret-minimizing mechanism to decide incentives by dynamically adjusting budget assignment and learning from users’ cost distributions. We further extend the problem to a more generalized k-MAB problem by removing the contextual information of difficulties. CUE-UCB algorithm is proposed to address the online advertisement problem for multi-platforms. Our experiment demonstrates utility improvement about 7 times and time saving of 54% to meet a utility objective compared to the previous works in sharing economy, and up to 175% increment of utility for online advertising.

With the large multimedia content online, deep hashing has become a popular method for efficient image retrieval and storage. However, by inheriting the algorithmic back-end from softmax classification, these techniques are vulnerable to the well-known adversarial examples as well. The massive collection of online images into the database also opens up new attack vectors. Attackers can embed adversarial images into the database and target specific categories to be retrieved by user queries. In this paper, we start from an adversarial standpoint to explore and enhance the capacity of targeted black-box transferability attack for deep hashing. We motivate this work by a series of empirical studies to see the unique challenges in image retrieval. We study the relations between adversarial subspace and black-box transferability via utilizing random noise as a proxy. Then we develop a new attack that is simultaneously adversarial and robust to noise to enhance transferability. Our experimental results demonstrate about 1.2-3× improvements of black-box transferability compared with the state-of-the-art mechanisms. The code is available at: https://github.com/SugarRuy/CVPR21_Transferred_Hash.

Energy provisioning plays a key role in the sustainable operations of Wireless Sensor Networks (WSNs). Recent efforts deploy multi-source energy harvesting sensors to utilize ambient energy. Meanwhile, wireless charging is a reliable energy source not affected by spatial-temporal ambient dynamics. This article integrates multiple energy provisioning strategies and adaptive adjustment to accomplish self-sustainability under complex weather conditions. We design and optimize a three-tier framework with the first two tiers focusing on the planning problems of sensors with various types and distributed energy storage powered by environmental energy. Then we schedule the Mobile Chargers (MC) between different charging activities and propose an efficient, 4-factor approximation algorithm. Finally, we adaptively adjust the algorithms to capture real-time energy profiles and jointly optimize those correlated modules. Our extensive simulations demonstrate significant improvement of network lifetime ( ), increase of harvested energy (15%), reduction of network cost (30%), and the charging capability of MC by 100%.

Originated from distributed learning, federated learning enables privacy-preserved collaboration on a new abstracted level by sharing the model parameters only. While the current research mainly focuses on optimizing learning algorithms and minimizing communication overhead left by distributed learning, there is still a considerable gap when it comes to the real implementation on mobile devices. In this article, we start with an empirical experiment to demonstrate computation heterogeneity is a more pronounced bottleneck than communication on the current generation of battery-powered mobile devices, and the existing methods are haunted by mobile stragglers. Further, non-identically distributed data across the mobile users makes the selection of participants critical to the accuracy and convergence. To tackle the computational and statistical heterogeneity, we utilize data as a tuning knob and propose two efficient polynomial-time algorithms to schedule different workloads on various mobile devices, when data is identically or non-identically distributed. For identically distributed data, we combine partitioning and linear bottleneck assignment to achieve near-optimal training time without accuracy loss. For non-identically distributed data, we convert it into an average cost minimization problem and propose a greedy algorithm to find a reasonable balance between computation time and accuracy. We also establish an offline profiler to quantify the runtime behavior of different devices, which serves as the input to the scheduling algorithms. We conduct extensive experiments on a mobile testbed with two datasets and up to 20 devices. Compared with the common benchmarks, the proposed algorithms achieve 2-100× speedup epoch-wise, 2–7 percent accuracy gain and boost the convergence rate by more than 100 percent on CIFAR10.

With the rapid growth of visual content, deep learning to hash is gaining popularity in the image retrieval community recently. Although it greatly facilitates search efficiency, privacy is also at risks when images on the web are retrieved at a large scale and exploited as a rich mine of personal information. An adversary can extract private images by querying similar images from the targeted category for any usable model. Existing methods based on image processing preserve privacy at a sacrifice of perceptual quality. In this paper, we propose a new mechanism based on adversarial examples to "stash'' private images in the deep hash space while maintaining perceptual similarity. We first find that a simple approach of hamming distance maximization is not robust against brute-force adversaries. Then we develop a new loss function by maximizing the hamming distance to not only the original category, but also the centers from all the classes, partitioned into clusters of various sizes. The extensive experiment shows that the proposed defense can harden the attacker's efforts by 2-7 orders of magnitude, without significant increase of computational overhead and perceptual degradation. We also demonstrate 30-60% transferability in hash space with a black-box setting. The code is available at: https://github.com/sugarruy/hashstash

The rise of dockless electric bike sharing becomes a new urban lifestyle recently. More than just the first-and-last mile, it offers a new modality of green transportation. However, in addition to the traditional re-balance and overcrowding problems, it also brings new challenges to urban management and maintenance. Due to the safety risks of batteries, customers are regulated to park at designated locations, which potentially causes dissatisfaction and customer loss. Meanwhile, service providers should charge those scattering low-energy batteries in time. To address these issues, we propose E-sharing, a two-tier optimization framework that leverages data-driven online algorithms to plan parking locations and maintenance. First, we balance the user dissatisfaction and the number of parking locations by minimizing their sum. To account for real-time dynamics while not losing track of the historical optimality, we propose an online algorithm based on its near-optimal offline solution. Second, we develop an incentive mechanism to motivate users to aggregate low-battery bikes together, saving the cost of bike charging. Our experiment based on the public dataset demonstrates that the online algorithm can minimize the cost from the conflicting objectives and incentive mechanism further reduces the maintenance cost by 47%.

Electric autonomous vehicles provide a promising solution to the traffic congestion and air pollution problems in future smart cities. Considering intensive energy consumption, charging becomes of paramount importance to sustain the operation of these systems. Motivated by the innovations in renewable energy harvesting, we leverage solar energy to power autonomous vehicles via charging stations and solar-harvesting rooftops, and design a framework that optimizes the operation of these systems from end to end. With a fixed budget, our framework first optimizes the locations of charging stations based on historical spatial-temporal solar energy distribution and usage patterns, achieving (2 + ε) factor to the optimal. Then a stochastic algorithm is proposed to update the locations online to adapt to any shift in the distribution. Based on the deployment, a strategy is developed to assign energy requests in order to minimize their traveling distance to stations while not depleting their energy storage. Equipped with extra harvesting capability, we also optimize route planning to achieve a reasonable balance between energy consumed and harvested en-route. Our extensive simulations demonstrate the algorithm can approach the optimal solution within 10-15% approximation error, and improve the operating range of vehicles by up to 2-3 times compared to other competitive strategies.

Federated learning learns a collaborative model by aggregating locally-computed updates from mobile devices for privacy preservation. While current research typically prioritizing the minimization of communication overhead, we demonstrate from an empirical study, that computation heterogeneity is a more pronounced bottleneck on battery-powered mobile devices. Moreover, if class is unbalanced among the mobile devices, inappropriate selection of participants may adversely cause gradient divergence and accuracy loss. In this paper, we utilize data as a tunable knob to schedule training and achieve near-optimal solutions of computation time and accuracy loss. Based on the offline profiling, we formulate optimization problems and propose polynomial-time algorithms when data is class-balanced or unbalanced. We evaluate the optimization framework extensively on a mobile testbed with two datasets. Compared with common benchmarks of federated learning, our algorithms achieve 210× speedups with negligible accuracy loss. They also mitigate the impact from mobile stragglers and improve parallelism for federated learning.

This work proposes GangSweep, a new backdoor detection framework that leverages the super reconstructive power of Generative Adversarial Networks (GAN) to detect and ''sweep out'' neural backdoors. It is motivated by a series of intriguing empirical investigations, revealing that the perturbation masks generated by GAN are persistent and exhibit interesting statistical properties with low shifting variance and large shifting distance in feature space. Compared with the previous solutions, the proposed approach eliminates the reliance on the access to training data, and shows a high degree of robustness and efficiency for detecting and mitigating a wide range of backdoored models with various settings. Moreover, this is the first work that successfully leverages generative networks to defend against advanced neural backdoors with multiple triggers and their polymorphic forms.

Linux Control Groups, i.e., cgroups, are the key building blocks to enable operating-system-level containerization. The cgroups mechanism partitions processes into hierarchical groups and applies different controllers to manage system resources, including CPU, memory, block I/O, etc. Newly spawned child processes automatically copy cgroups attributes from their parents to enforce resource control. Unfortunately, inherited cgroups confinement via process creation does not always guarantee consistent and fair resource accounting. In this paper, we devise a set of exploiting strategies to generate out-of-band</>workloads via de-associating processes from their original process groups. The system resources consumed by such workloads will not be charged to the appropriate cgroups. To further demonstrate the feasibility, we present five case studies within Docker containers to demonstrate how to break the resource rein of cgroups in realistic scenarios. Even worse, by exploiting those cgroups' insufficiencies in a multi-tenant container environment, an adversarial container is able to greatly amplify the amount of consumed resources, significantly slow-down other containers on the same host, and gain extra unfair advantages on the system resources. We conduct extensive experiments on both a local testbed and an Amazon EC2 cloud dedicated server. The experimental results demonstrate that a container can consume system resources (e.g., CPU) as much as $200\times$ of its limit, and reduce both computing and I/O performance of particular workloads in other co-resident containers by 95%.

Incentives are explored in the sharing economy to inspire users for better resource allocation. Previous works build a budget-feasible incentive mechanism to learn users' cost distribution. However, they only consider a special case that all tasks are considered as the same. The general problem asks for finding a solution when the cost for different tasks varies. In this paper, we investigate this general problem by considering a system with k levels of difficulty. We present two incentivizing strategies for offline and online implementation, and formally derive the ratio of utility between them in different scenarios. We propose a regret-minimizing mechanism to decide incentives by dynamically adjusting budget assignment and learning from users' cost distributions. Our experiment demonstrates utility improvement about 7 times and time saving of 54% to meet a utility objective compared to the previous works.

This work proposes an innovative approach, named CapJack, to detect in-browser malicious cryptocurrency mining activities by using the latest CapsNet technology. To the best of our knowledge, this is the first work to introduce CapsNet to the field of malware detection through system behavioral analysis. It is particularly effective to detect malicious miners under multitasking environments where multiple applications run simultaneously. Experimental data show appealing performance of CapJack, with a detection rate of as high as 87% instantly and 99% within a window of 11 seconds.

Energy supply remains to be a major bottleneck in Wireless Sensor Networks (WSNs). A self-sustainable network operates without battery replacement. Recent efforts employ multi-source energy harvesting to power sensors with ambient energy. Meanwhile, wireless charging is considered in WSNs as a reliable energy source. It motivates us to integrate both fields of research to build a self-sustainable network and guarantee operation under any weather condition. We propose a three-step solution to optimize this new framework. We first solve the Sensor Composition Problem (SCP) to derive the percentage of different types of sensors. Then we enable self-sustainability by bringing energy harvesting storage to the field for charging the Mobile Charger (MC). Next, we propose a 3-factor approximation algorithm to schedule sensor charging and energy replenishment of MC. Our extensive simulation results demonstrate significant improvement of network lifetime and reduction of network cost. The network lifetime can be extended at least three times compared with traditional approaches and the charging capability of MC increases at least 100%.

Pre-trained deep learning models can be deployed on mobile devices to conduct inference. However, they are usually not updated thereafter. In this paper, we take a step further to incorporate training deep neural networks on battery-powered mobile devices and overcome the difficulties from the lack of labeled data. We design and implement a new framework to enlarge sample space via data paring and learn a deep metric under the privacy, memory and computational constraints. A case study of deep behavioral authentication is conducted. Our experiments demonstrate accuracy over 95% on three public datasets, a sheer 15% gain from traditional multi-class classification with less data and robustness against brute-force attacks with 99% success. We demonstrate the training performance on various smartphone models, where training 100 epochs takes less than 10 mins and can be boosted 3-5 times with feature transfer. We also profile memory, energy and computational overhead. Our results indicate that training consumes lower energy than watching videos so can be scheduled intermittently on mobile devices.

Energy remains a major hurdle in running computation-intensive tasks on wireless sensors. Recent efforts have been made to employ a Mobile Charger (MC) to deliver wireless power to sensors, which provides a promising solution to the energy problem. Most of previous works in this area aim at maintaining perpetual network operation at the expense of high operating cost of MC. In the meanwhile, it is observed that due to the low cost of wireless sensors, they are usually deployed at high density so there is abundant redundancy in their coverage in the network. For such networks, it is possible to take advantage of the redundancy to reduce the energy cost. In this paper, we relax the strictness of perpetual operation by allowing some sensors to temporarily run out of energy while still maintaining target $k$k-coverage in the network at lower cost of MC. We first establish a theoretical model to analyze the performance improvements under this new strategy. Then, we organize sensors into load-balanced clusters for target monitoring by a distributed algorithm. Next, we propose a charging algorithm named $\lambda$λ-GTSP Charging Algorithm to determine the optimal number of sensors to be charged in each cluster to maintain $k$k-coverage in the network and derive the route for MC to charge them. We further generalize the algorithm to encompass mobile targets as well. Our extensive simulation results demonstrate significant improvements of network scalability and cost saving that MC can extend charging capability over 2-3 times with a reduction of 40 percent of moving cost without sacrificing the network performance.

Identity-based attacks such as MAC spoofing are common in wireless networks. The recently developed virtualization technologies bring a new type of MAC spoofing attack, virtual MAC spoofing. This makes it even more challenging to detect such attacks, especially in a tight environment with spatial similarities. In this paper, we design, implement and evaluate a system to effectively detect virtual MAC spoofing attacks via deep learning. A deep convolutional neural network is constructed to extract physical features from CSI obtained from packet transmissions, to detect virtual MAC spoofing attacks. An important merit of the proposed detection system is that this system can distinguish two devices even at the same location, which was not well addressed by previous approaches. Our extensive experimental results demonstrate the effectiveness of the system with an average detection accuracy of 95%, even when devices are co-located.

Privacy is a fundamental challenge for a variety of smart applications that depend on data aggregation and collaborative learning across different entities. In this paper, we propose a novel privacy-preserved architecture where clients can collaboratively train a deep model while preserving the privacy of each client’s data. Our main strategy is to carefully partition a deep neural network to two non-colluding parties. One party performs linear computations on encrypted data utilizing a less complex homomorphic cryptosystem, while the other executes non-polynomial computations in plaintext but in a privacy-preserved manner. We analyze security and compare the communication and computation complexity with the existing approaches. Our extensive experiments on different datasets demonstrate not only stable training without accuracy loss, but also 14 to 35 times speedup compared to the state-of-the-art system.

In this paper, we report a newfound vulnerability on smartphones due to the malicious use of unsupervised sensor data. We demonstrate that an attacker can train deep Convolutional Neural Networks (CNN) by using magnetometer or orientation data to effectively infer the Apps and their usage information on a smartphone with an accuracy of over 80%. Furthermore, we show that such attacks can become even worse if sophisticated attackers exploit motion sensors to cluster the magnetometer or orientation data, improving the accuracy to as high as 98%. To mitigate such attacks, we propose a noise injection scheme that can effectively reduce the App sniffing accuracy to only 15% and at the same time has negligible effect on benign Apps.

The application of wireless charging technology in traditional battery-powered wireless sensor networks (WSNs) grows rapidly recently. Although previous studies indicate that the technology can deliver energy reliably, it still faces regulatory mandate to provide high power density without incurring health risks. In particular, in clustered WSNs there exists a mismatch between the high energy demands from cluster heads and the relatively low energy supplies from wireless chargers. Fortunately, solar energy harvesting can provide high power density without health risks. However, its reliability is subject to weather dynamics. In this paper, we propose a hybrid framework that combines the two technologies - cluster heads are equipped with solar panels to scavenge solar energy and the rest of nodes are powered by wireless charging. We divide the network into three hierarchical levels. On the first level, we study a discrete placement problem of how to deploy solar-powered cluster heads that can minimize overall cost and propose a distributed 1:61(1+ϵ)2-approximation algorithm for the placement. Then, we extend the discrete problem into continuous space and develop an iterative algorithm based on the Weiszfeld algorithm. On the second level, we establish an energy balance in the network and explore how to maintain such balance for wireless-powered nodes when sunlight is unavailable. We also propose a distributed cluster head re-selection algorithm. On the third level, we first consider the tour planning problem by combining wireless charging with mobile data gathering in a joint tour. We then propose a polynomial-time scheduling algorithm to find appropriate hitting points on sensors' transmission boundaries for data gathering. For wireless charging, we give the mobile chargers more flexibility by allowing partial recharge when energy demands are high. The problem turns out to be a Linear Program. By exploiting its particular structure, we propose an efficient algorithm that can achieve near-optimal solutions. Our extensive simulation results demonstrate that the hybrid framework can reduce battery depletion by 20 percent and save vehicles' moving cost by 25 percent compared to previous works. By allowing partial recharge, battery depletion can be further reduced at a slightly increased cost. The results also suggest that we can reduce the number of high-cost mobile chargers by deploying more low-cost solar-powered sensors.

In recent years, mobile data gathering in wireless sensor networks has attracted much interests in the research community. However, despite extensive efforts, many of previous work in this area lies only in theory and evaluates network performance with computer simulations, which leaves a large gap from reality. In this paper, we present the design and implementation of a general purpose, flexible platform for mobile data gathering in wireless sensor networks to evaluate network performance and algorithms in a practical setting. Instead of relying on hand-crafted theoretical models, our platform integrates both mobile data collector and sensor nodes to provide realistic performance evaluations. In addition, the platform adopts a modular design in mobile data collector and sensor nodes, and equips the mobile data collector with advanced computing capability, which makes it versatile for evaluating the performance of a wide-range of applications. Finally, as a case study, weimplement a wildlife monitoring system on our platform. Our experimental results demonstrate that real implementations can evaluate many practical performance factors which would have a great impact on the sensing results and are very difficult to fully capture by theoretical models and simulations. We expect that this platform can become a very powerful general tool for more accurate network simulations and facilitate performance optimization in wireless sensor networks.

Energy remains a major hurdle in running computation-intensive tasks on wireless sensors. Recent efforts have been made to employ a Mobile Charger (MC) to deliver wireless power to sensors, which provides a promising solution to the energy problem. Most of previous works in this area aim at maintaining perpetual network operation at the expense of high operating cost of MC. In the meanwhile, it is observed that due to low cost of wireless sensors, they are usually deployed at high density so there is abundant redundancy in their coverage in the network. For such networks, it is possible to take advantage of the redundancy to reduce the energy cost. In this paper, we relax the strictness of perpetual operation by allowing some sensors to temporarily run out of energy while still maintaining target k-coverage in the network at lower cost of MC. We first establish a theoretical model to analyze the performance improvements under this new strategy. Then we organize sensors into load-balanced clusters for target monitoring by a distributed algorithm. Next, we propose a charging algorithm named λ-GTSP Charging Algorithm to determine the optimal number of sensors to be charged in each cluster to maintain k-coverage in the network and derive the route for MC to charge them. We further generalize the algorithm to encompass mobile targets as well. Our extensive simulation results demonstrate significant improvements of network scalability and cost saving that MC can extend charging capability over 2-3 times with a reduction of 40% of moving cost without sacrificing the network performance.

Wireless charging has provided a convenient alternative to renew nodes' energy in wireless sensor networks. Due to physical limitations, previous works have only considered recharging a single node at a time, which has limited efficiency and scalability. Recent advances on multi-hop wireless charging is gaining momentum and provides fundamental support to address this problem. However, existing single-node charging designs do not consider and cannot take advantage of such opportunities. In this paper, we propose a new framework to enable multi-hop wireless charging using resonant repeaters. First, we present a realistic model that accounts for detailed physical factors to calculate charging efficiencies. Second, to achieve balance between energy efficiency and data latency, we propose a hybrid data gathering strategy that combines static and mobile data gathering to overcome their respective drawbacks and provide theoretical analysis. Then, we formulate multi-hop recharge schedule into a bi-objective NP-hard optimization problem. We propose a two-step approximation algorithm that first finds the minimum charging cost and then calculates the charging vehicles' moving costs with bounded approximation ratios. Finally, upon discovering more room to reduce the total system cost, we develop a post-optimization algorithm that iteratively adds more stopping locations for charging vehicles to further improve the results while ensuring none of the nodes will deplete battery energy. Our extensive simulations show that the proposed algorithms can handle dynamic energy demands effectively, and can cover at least three times of nodes and reduce service interruption time by an order of magnitude compared to the single-node charging scheme.

Recently, there have been a growing number of applications that power wireless sensor networks (WSNs) by wireless charging technology. Although previous studies indicate that wireless charging can deliver energy reliably, it still faces regulatory challenges to provide high power density without incurring health risks. In particular, in clustered WSNs there exists a mismatch between the high energy demands from cluster heads and the relatively low energy supplies that wireless charging can provide. Fortunately, solar energy harvesting can provide high power density which is also risk-free. However, it is subject to weather dynamics. Therefore, in this paper, we propose a hybrid framework that combines the two technologies - cluster heads are equipped with solar panels to scavenge solar energy and the rest of nodes are powered by wireless charging. First, we study a placement problem on how to deploy solar-powered cluster heads that can minimize overall cost and propose a distributed 1.61(1 + ϵ)2-approximation algorithm for the placement. Second, we establish an energy balance in the network and explore how to maintain such balance when sunlight is unavailable. Third, we consider combining wireless charging and mobile data gathering in a joint tour in such networks, and propose a polynomial-time scheduling algorithm. Our extensive simulation demonstrates that the hybrid framework can reduce battery depletion by 20% and save system cost by 25% compared to previous results.

Several recent works have studied mobile vehicle scheduling to recharge sensor nodes via wireless energy transfer technologies. Unfortunately, most of them overlooked important factors of the vehicles' moving energy consumption and limited recharging capacity, which may lead to problematic schedules or even stranded vehicles. In this paper, we consider the recharge scheduling problem under such important constraints. To balance energy consumption and latency, we employ one dedicated data gathering vehicle and multiple charging vehicles. We first organize sensors into clusters for easy data collection, and obtain theoretical bounds on latency. Then we establish a mathematical model for the relationship between energy consumption and replenishment, and obtain the minimum number of charging vehicles needed. We formulate the scheduling into a Profitable Traveling Salesmen Problem that maximizes profit - the amount of replenished energy less the cost of vehicle movements, and prove it is NP-hard. We devise and compare two algorithms: a greedy one that maximizes the profit at each step; an adaptive one that partitions the network and forms Capacitated Minimum Spanning Trees per partition. Through extensive evaluations, we find that the adaptive algorithm can keep the number of nonfunctional nodes at zero. It also reduces transient energy depletion by 30-50 percent and saves 10-20 percent energy. Comparisons with other common data gathering methods show that we can save 30 percent energy and reduce latency by two orders of magnitude.

Data uploading time constitutes a large portion of mobile data gathering time in wireless sensor networks. By equipping multiple antennas on the mobile collector, data uploading time can be greatly shortened. However, previous works only treated wireless link capacity as a constant and ignored power control on sensors, which would significantly deviate from the real wireless environments. To overcome this problem, in this paper we propose a new data gathering cost minimization framework for mobile data gathering in wireless sensor networks by considering dynamic wireless link capacity and power control jointly. Our new framework not only allows concurrent data uploading from sensors to the mobile collector, but also determines transmission power under elastic link capacities. We study the problem under constraints of flow conservation, energy consumption, elastic link capacity, transmission compatibility, and Sojourn time. We employ the subgradient iteration algorithm to solve the minimization problem. We first relax the problem with Lagrangian dualization, then decompose the original problem into several subproblems, and present distributed algorithms to derive data rate, link flow and routing, power control, and transmission compatibility. For the mobile collector, we also propose a sub-algorithm to determine sojourn time at different stopping locations. Finally, we provide extensive simulation results to demonstrate the convergence and robustness of proposed algorithms. The results reveal 20 percent shorter data collection latency on average with lower energy consumptions compared to previous works as well as lower data gathering cost and robustness in case of node failures.

Recent advances in environmental energy harvesting technologies have provided great potentials for traditional battery powered sensor networks to achieve perpetual operations. Due to dynamics from the temporal profiles of ambient energy sources, most of the studies so far have focused on designing and optimizing energy management schemes on single sensor node, but overlooked the impact of spatial variations of energy distribution when sensors work together at different locations. To design a robust sensor network, in this paper, we use mobility to circumvent communication bottlenecks caused by spatial energy variations. We employ a mobile collector, called SenCar, to collect data from designated sensors and balance energy consumptions in the network. To show spatial-temporal energy variations, we first conduct a case study in a solar-powered network and analyze possible impact on network performance. Next, we present a two-step approach for mobile data collection. First, we adaptively select a subset of sensor locations where the SenCar stops to collect data packets in a multi-hop fashion. We develop an adaptive algorithm to search for nodes based on their energy and guarantee data collection tour length is bounded. Second, we focus on designing distributed algorithms to achieve maximum network utility by adjusting data rates, link scheduling, and flow routing that adapts to the spatial-temporal environmental energy fluctuations. Finally, our numerical results indicate the distributed algorithms can converge to optimality very fast and validate its convergence in case of node failure. We also show advantages of our framework such as it can adapt to spatial-temporal energy variations and demonstrate its superiority compared to the network with static data sink.

Wireless charging is a game-changing technology to provide reliable energy source for wireless sensor networks. Combining wireless charging with mobile data collection on a single mobile vehicle can mitigate the nonuniform energy distribution problem. However, data latency may be too long for some applications because vehicles have to spend significant time in charging before uploading data to the base station. In this paper, we propose a new framework that employs a dedicated vehicle for data collection and theoretically study the trade-offs between data latency and the number of recharging vehicles needed. We first study how to minimize data latency while ensuring all sensory data are collected and derive a latency bound. Then we establish a mathematical model to calculate the minimum number of recharging vehicles needed. Finally, we conduct simulations to validate the theoretical results and evaluate the efficiency of the framework. The results show that our scheme can reduce the number of nonfunctional nodes by 30-60%, and cut down data collection latency more than an order of magnitude compared to the previous work.

Wireless charging has provided a convenient alternative to renew sensors' energy in wireless sensor networks. Due to physical limitations, previous works have only considered recharging a single node at a time, which has limited efficiency and scalability. Recent advance on multi-hop wireless charging is gaining momentum to provide fundamental support to address this problem. However, existing single-node charging designs do not consider and cannot take advantage of such opportunities. In this paper, we propose a new framework to enable multi-hop wireless charging using resonant repeaters. First, we present a realistic model that accounts for detailed physical factors to calculate charging efficiencies. Second, to achieve balance between energy efficiency and data latency, we propose a hybrid data gathering strategy that combines static and mobile data gathering to overcome their respective drawbacks and provide theoretical analysis. Then we formulate multi-hop recharge schedule into a bi-objective NP-hard optimization problem. We propose a two-step approximation algorithm that first finds the minimum charging cost and then calculates the charging vehicles' moving costs with bounded approximation ratios. Finally, upon discovering more room to reduce the total system cost, we develop a post-optimization algorithm that iteratively adds more stopping locations for charging vehicles to further improve the results. Our extensive simulations show that the proposed algorithms can handle dynamic energy demands effectively, and can cover at least three times of nodes and reduce service interruption time by an order of magnitude compared to the single-node charging scheme.

Recent studies show that the novel wireless charging technology can extend the lifetime of Wireless Sensor Networks (WSNs) towards perpetual operations. Recharging Vehicles (RVs) can be applied in WSNs to recharge sensors conveniently via wireless charging devices. Most of existing work focused only on energy replenishment whereas ignored sensor activity management. In this paper, we propose a new framework that can jointly schedule sensor activity and recharging to save the traveling energy of RVs. First, we propose two schemes to manage sensor activity: balanced clustering and distributed sensor activation schemes. We further introduce a new metric so that the energy demand in each cluster can be managed. Then we formulate the recharging problem into a Traveling Salesman Problem with Profits, which is NP-hard. For the recharging route schedule, we first study the case of a single RV by coordinating sensor activity and energy replenishment, and then extend it to multiple RVs using two different schemes. The first scheme focuses on reducing traveling distance of RVs by confining their moving scopes and the second one improves the overall system performance by giving RVs a global view over the entire network. Finally, we validate the correctness and evaluate the performance of the sensor activity management schemes along with the recharging algorithms by extensive simulations. Our results indicate that significant reduction on system cost can be achieved. The sensor activity management schemes can save traveling energy of RVs by 16% while maintaining a reliable detection on targets. Compared with a simple greedy algorithm, the first and the second recharging schemes can save 41% and 13% traveling distance of RVs, and reduce nonfunctional nodes by 23% and 52%, respectively.

In this paper, a three-layer framework is proposed for mobile data collection in wireless sensor networks, which includes the sensor layer, cluster head layer, and mobile collector (called SenCar) layer. The framework employs distributed load balanced clustering and dual data uploading, which is referred to as LBC-DDU. The objective is to achieve good scalability, long network lifetime and low data collection latency. At the sensor layer, a distributed load balanced clustering (LBC) algorithm is proposed for sensors to self-organize themselves into clusters. In contrast to existing clustering methods, our scheme generates multiple cluster heads in each cluster to balance the work load and facilitate dual data uploading. At the cluster head layer, the inter-cluster transmission range is carefully chosen to guarantee the connectivity among the clusters. Multiple cluster heads within a cluster cooperate with each other to perform energy-saving inter-cluster communications. Through inter-cluster transmissions, cluster head information is forwarded to SenCar for its moving trajectory planning. At the mobile collector layer, SenCar is equipped with two antennas, which enables two cluster heads to simultaneously upload data to SenCar in each time by utilizing multi-user multiple-input and multiple-output (MU-MIMO) technique. The trajectory planning for SenCar is optimized to fully utilize dual data uploading capability by properly selecting polling points in each cluster. By visiting each selected polling point, SenCar can efficiently gather data from cluster heads and transport the data to the static data sink. Extensive simulations are conducted to evaluate the effectiveness of the proposed LBC-DDU scheme. The results show that when each cluster has at most two cluster heads, LBC-DDU achieves over 50 percent energy saving per node and 60 percent energy saving on cluster heads comparing with data collection through multi-hop relay to the static data sink, and 20 percent shorter data collection time compared to traditional mobile data gathering.

Wireless sensor networks adopting static data gathering may suffer from unbalanced energy consumption due to non-uniform packet relay in such networks, especially in large scale networks. On the other hand, although mobile data gathering provides a reasonable approach to solving this problem, it inevitably introduces longer data collection latency due to the use of mobile data collectors. In the meanwhile, energy harvesting has been considered as a promising solution to relieve energy limitation in wireless sensor networks. In this paper, we consider a joint design of these two schemes and propose a novel two layer heterogeneous architecture for wireless sensor networks, which consists of two types of nodes: sensor nodes which are static and powered by solar panels, and cluster heads that have limited mobility and can be wirelessly recharged by power transporters. Based on this network architecture, we present a data gathering scheme, called Mobility Assisted Data Gathering (MADG), where sensor nodes are clustered around cluster heads that change their positions in each data gathering cycle, and the sensing data are forwarded to the data sink by these cluster heads working as data aggregation points. We evaluate the performance of the proposed scheme by extensive simulations and the results show that MADG provides significant improvement in terms of balancing energy consumption and the amount data gathered compared to previous work.

Environmental energy harvesting technologies have provided potential for battery-powered wireless sensor networks to have perpetual network operations. To design a robust network that can adapt to not only temporal but also spatial variations of ambient energy sources, in this paper, we utilize mobility to circumvent communication bottlenecks, by employing a mobile data collector, called SenCar. We propose a two-stage approach for mobile data collection. In the first stage, SenCar makes stops at a subset of selected sensor locations to collect data packets in a multi-hop fashion. We provide a selection algorithm to search for sensor locations with most residual energy while guaranteeing a bounded tour length. Then we design a distributed data gathering algorithm to achieve maximum network utility by adjusting data rates, link scheduling and flow routing that adapts to spatial temporal environmental energy variations. The effectiveness and efficiency of the proposed algorithms are validated by extensive numerical results.

Several recent works have studied the schedule for mobile vehicles to recharge sensor nodes via wireless energy transfer technologies. Unfortunately, most of them overlooked the important factors of the vehicles' moving energy consumption and limited recharging capacity. These oversights may lead to problematic schedules or even stranded vehicles. In this paper, we study the recharging schedule that maximizes the recharging profit - the amount of replenished energy less the cost of vehicle movements - under these important constraints. We first derive the minimum number of vehicles needed for energy neutral condition and discover a set of desired network properties. Then we formulate the recharge schedule optimization into a Profitable Traveling Salesmen Problem with capacity and battery deadline constraints, which we prove to be NP-hard. We propose two algorithms to solve the problem. The first one is a greedy algorithm that maximizes the recharge profit at each step; the second one first adaptively partitions the network based on recharge requests, then forms Capacitated Minimum Spanning Tree in each partition followed by route improvements. Finally, we evaluate and compare the performance of proposed algorithms and validate the correctness of theoretical results through extensive simulations. Given a sufficient number of vehicles, the adaptive algorithm can keep the number of nonfunctional nodes at zero. Compared to the greedy algorithm, it reduces the percentage of transient energy depletion by 30-50% with 10-20% energy saving on vehicles.

The emerging wireless energy transfer technology enables charging sensor batteries in a wireless sensor network (WSN) and maintaining perpetual operation of the network. Recent breakthrough in this area has opened up a new dimension to the design of sensor network protocols. In the meanwhile, mobile data gathering has been considered as an efficient alternative to data relaying in WSNs. However, time variation of recharging rates in wireless rechargeable sensor networks imposes a great challenge in obtaining an optimal data gathering strategy. In this paper, we propose a framework of joint wireless energy replenishment and anchor-point based mobile data gathering (WerMDG) in WSNs by considering various sources of energy consumption and time-varying nature of energy replenishment. To that end, we first determine the anchor point selection strategy and the sequence to visit the anchor points. We then formulate the WerMDG problem into a network utility maximization problem which is constrained by flow, energy balance, link and battery capacity and the bounded sojourn time of the mobile collector. Furthermore, we present a distributed algorithm composed of cross-layer data control, scheduling and routing subalgorithms for each sensor node, and sojourn time allocation subalgorithm for the mobile collector at different anchor points. We also provide the convergence analysis of these subalgorithms. Finally, we implement the WerMDG algorithm in a distributed manner in the NS-2 simulator and give extensive numerical results to verify the convergence of the proposed algorithm and the impact of utility weight, link capacity and recharging rate on network performance.

Using vehicles equipped with wireless energy transmission technology to recharge sensor nodes over the air is a game-changer for traditional wireless sensor networks. The recharging policy regarding when to recharge which sensor nodes critically impacts the network performance. So far only a few works have studied such recharging policy for the case of using a single vehicle. In this paper, we propose NETWRAP, an NDN based Real Time Wireless Recharging Protocol for dynamic wireless recharging in sensor networks. The real-time recharging framework supports single or multiple mobile vehicles. Employing multiple mobile vehicles provides more scalability and robustness. To efficiently deliver sensor energy status information to vehicles in real-time, we leverage concepts and mechanisms from named data networking (NDN) and design energy monitoring and reporting protocols. We derive theoretical results on the energy neutral condition and the minimum number of mobile vehicles required for perpetual network operations. Then we study how to minimize the total traveling cost of vehicles while guaranteeing all the sensor nodes can be recharged before their batteries deplete. We formulate the recharge optimization problem into a Multiple Traveling Salesman Problem with Deadlines (m-TSP with Deadlines), which is NP-hard. To accommodate the dynamic nature of node energy conditions with low overhead, we present an algorithm that selects the node with the minimum weighted sum of traveling time and residual lifetime. Our scheme not only improves network scalability but also ensures the perpetual operation of networks. Extensive simulation results demonstrate the effectiveness and efficiency of the proposed design. The results also validate the correctness of the theoretical analysis and show significant improvements that cut the number of nonfunctional nodes by half compared to the static scheme while maintaining the network overhead at the same level.

The emerging wireless energy transfer technology enables charging sensor batteries in a wireless sensor network (WSN) and maintaining perpetual operation of the network. Recent breakthrough in this area has opened up a new dimension to the design of sensor network protocols. In the meanwhile, mobile data gathering has been considered as an efficient alternative to data relaying in WSNs. However, time variation of recharging rates in wireless rechargeable sensor networks imposes a great challenge in obtaining an optimal data gathering strategy. In this paper, we propose a framework of joint Wireless Energy Replenishment and anchor-point based Mobile Data Gathering (WerMDG) in WSNs by considering various sources of energy consumption and time-varying nature of energy replenishment. To that end, we first determine the anchor point selection and the sequence to visit the anchor points. We then formulate the WerMDG problem into a network utility maximization problem which is constrained by flow conversation, energy balance, link and battery capacity and the bounded sojourn time of the mobile collector. Furthermore, we present a distributed algorithm composed of cross-layer data control, scheduling and routing subalgorithms for each sensor node, and sojourn time allocation subalgorithm for the mobile collector at different anchor points. Finally, we give extensive numerical results to verify the convergence of the proposed algorithm and the impact of utility weight on network performance.

Mobile vehicles equipped with wireless energy transmission technology can recharge sensor nodes over the air. When to recharge which nodes, and in what order, critically impact the network performance. So far only a few works have studied the recharging policy for a single mobile vehicle. In this paper, we study how to coordinate the recharging activities of multiple mobile vehicles, which provide more scalability and robustness than a single vehicle. We leverage concepts and mechanisms from NDN (Named Data Networking) to design energy monitoring protocols that deliver energy status information to mobile vehicles in an efficient manner. Then we study how to minimize the total traveling cost of multiple vehicles while ensuring no node failure. We derive theoretical results on the energy neutral condition and the minimum number of mobile vehicles required for perpetual network operations. We formulate the optimization problem into a Multiple Traveling Salesman Problem with Deadlines (m-TSP with Deadlines), which is NP-hard. To accommodate the dynamic nature of node energy conditions and reduce computational overhead, we present a heuristic algorithm that selects the node with the minimum weighted sum of traveling time and residual lifetime. Our scheme not only improves network scalability but also guarantees the perpetual operation of networks. Finally, we conduct extensive simulations to demonstrate the effectiveness and efficiency of our proposed design, and validate the correctness of theoretical analysis.

A mobile vehicle equipped with wireless energy transmission technology can move around a wireless sensor network and recharge nodes over the air, leading to potentially perpetual operation if nodes can always be recharged before energy depletion. When to recharge which nodes, and in what order, critically impact the outcome. So far only a few works have studied this problem and relatively static recharging policies were proposed. However, dynamic changes such as unpredictable energy consumption variations in nodes, and practical issues like scalable and efficient gathering of energy information, are not yet addressed. In this paper, we propose NETWRAP, an NDN based Real Time Wireless Recharging Protocol for dynamic recharging in wireless sensor networks. We leverage concepts and mechanisms from NDN (Named Data Networking) to design a set of protocols that continuously gather and deliver energy information to the mobile vehicle, including unpredictable emergencies, in a scalable and efficient manner. We derive analytic results on energy neutral conditions that give rise to perpetual operation. We also discover that optimal recharging of multiple emergencies is an Orienteering problem with Knapsack approximation. Our extensive simulations demonstrate the effectiveness and efficiency of the proposed framework and validate the theoretical analysis.

Recent studies have shown that environmental energy harvesting technologies have the potential to provide perpetual operation to wireless sensor networks. However, due to the large variations of the ambient energy source, such networks could only support low-rate data services and the performance is affected by many unpredictable environmental factors. To deliver energy to sensor nodes reliably, in this paper, we apply the novel wireless power transmission technology to rechargeable sensor networks by introducing a mobile actuator to replenish sensor energy wirelessly. We first establish an analytical model based on stochastic wireless energy replenishment to obtain a variety of performance metrics. Then based on the theoretical results, we further propose battery-aware mobile energy replenishment scheme and present two heuristic algorithms: (1) linear adaptation sensor activation with prioritized recharge; and (2) battery-aware activation with selective recharge. We validate the theoretical results and evaluate the performance of the proposed algorithms through extensive simulations. The results demonstrate that a good design of sensor activation with effective control of mobile energy replenishment can provide substantial performance improvement.