Pricing strategy is crucial for improving the revenue of mobility on-demand (MoD) systems by achieving supply-demand equilibrium across different city zones. Modern MoD systems commonly utilize order ridesharing and vehicle repositioning to improve the order completion rate while supporting this equilibrium, thereby improving the revenue. However, most existing pricing strategies overlook the effects of ridesharing and repositioning, resulting in supply-demand mismatch and revenue decline. To fill this gap, we propose a multi-agent reinforcement learning (MARL) based pricing strategy via a mutual attention mechanism, named R2Pricing, where the impact of ridesharing and repositioning is considered. First, we formulate the pricing with ridesharing and repositioning as an optimization problem toward maximum overall revenue. Then, we transform it into a MARL model, where the agent makes coupled decisions about order fare with ridesharing and vehicle income with repositioning for each zone. Next, the agents are clustered based on supply-demand observation and reward to train more efficiently. The pricing messages between agents are generated based on mutual information theory, which is then aggregated with an attention mechanism to estimate the impact of price differences among zones. Finally, simulations based on real-world data are conducted to demonstrate the superiority of R2Pricing over the benchmarks.

Vehicle repositioning is widely used in Mobility on-Demand (MoD) systems to address supply-demand imbalances and improve order completion rates. Existing methods typically offer repositioning recommendations focused on enhancing vehicle coordination toward supply-demand re-balance. However, these methods often overlook the possibility that drivers may not follow these recommendations due to their personal preferences, leading to recommendation-decision inconsistency and further disrupting the supply-demand balance. To address this issue, we propose a preference-aware vehicle repositioning recommendation strategy for MoD systems, named FREE, which is based on a Coulomb Force directed approach. The core idea is to strike a balance between vehicle coordination and consistency between recommendations and driver decisions. First, we introduce a Coulomb force-based representation (CFR) to model coordination among vehicles. In this model, the interactions between vehicles and orders are represented as forces that drive the repositioning of vehicles. Next, we develop a driver preference learning model that accurately captures drivers’ preferences using triplet and consistency loss. We then integrate these preferences with the CFR into a multi-agent deep reinforcement learning (MADRL) based repositioning algorithm to generate optimal recommendations. Finally, we validate the effectiveness of FREE through simulations using real-world data, demonstrating its superiority over existing benchmarks.

The ever-increasing quality of experience (QoE) demand for video streaming has prompted the integration of video super-resolution and multi-access edge computing networks (MEC). With super-resolution, the low-resolution frames can be reconstructed into high-resolution ones by edge node and end device collaboratively, which is beneficial in improving QoE. However, the existing works focus on designing video streaming strategies in single-user scenarios, which cannot be applied to multi-user scenarios due to the resource contention among users, as well as the huge solution space of coupled bitrate selection and workload share between edge-end. To fill this gap, we propose a collaborative video streaming strategy with super-resolution in multi-user MEC networks, named Co-Video, to maximize the average QoE by making optimal bitrate selection and workload share. We first formulate the problem as an optimization problem towards maximum average QoE, where the QoE incorporates playback delay, video quality, and smoothness. Then, we transform the optimization problem into a partially observable Markov decision process (POMDP) and exploit the Co-Video strategy based on the multi-agent soft actor-critic (MASAC) algorithm. Specifically, Co-Video utilizes the branching actor network to converge to good policy stably. Finally, trace-driven simulations on real-world bandwidth traces demonstrate that Co-Video outperforms the state-of-the-art baselines.

In multiaccess edge computing (MEC) systems, service migration has been extensively applied to ensure service quality by migrating services to follow mobile users. The existing migration methods mainly focus on optimizing service response latency and migration costs by predicting user’s movements. However, some malicious adversaries can learn auxiliary knowledge, i.e., users’ mobility model and service migration trajectory, and launch location inference attacks to infer user locations. This leads to serious personal security threats, like malvertising, fraud and kidnapping. In this article, we propose a location privacy-aware service migration method to against adversaries’ location inference attacks in multiuser MEC systems. First, we adopt an entropy-based location privacy metric to accurately measure user’s location privacy leakage risk. Then, we formulate the service migration progress as a joint optimization problem that minimizes service response latency and location privacy leakage risk. To cope with interuser interference, we developed a multiagent soft actor–critic (MASAC) algorithm to help users collaboratively make service migration decisions. Finally, simulations based on real-world user movement trajectories were conducted to demonstrate the superiority of the proposed method. Evaluation and analysis results showed that our proposed method can effectively protect user location privacy while maintaining a low service response latency.

Mobility on demand (MoD) systems utilize ridesharing, i.e., multiple orders with high associating utility share a single vehicle, to reduce carbon footprint and alleviate traffic pressure. Existing methods mainly promote ridesharing by flocking multiple orders to the minimum required vehicles. However, supply-demand variations may aggregate undersupply in the long run and affect the order completion rate. Meanwhile, it is difficult to accurately estimate associating utility among ridesharing orders with lane-level features, such as traffic flow. To fill this gap, we propose ERShare, an elastic order dispatching algorithm to maximize the order completion rate in the MoD system. First, the ridesharing order dispatching problem is formulated as an offline optimization problem, and then it is proved that the order completion rate is maximized when the MoD system achieves long-term supply-demand equilibrium. Next, a dummy order/vehicle generation method is proposed to generate dummies as a spinner to achieve supply-demand equilibrium elastically. Also, a lane-level ridesharing rule is designed to accurately estimate the associating utility based on an order association graph. Subsequently, a dummy-based order dispatching algorithm is proposed to find the optimal dispatching decisions. Finally, the simulations on real-world data validate the superiority of ERShare over state-of-the-art solutions regarding order completion rate.

Multi-access edge computing (MEC)-enabled Internet of Things (IoT) has become a powerful solution to run computation-intensive applications on end devices. These applications are composed of multiple dependent tasks, which can be abstracted as directed acyclic graphs (DAGs). Moreover, applications can share partial intermediate data with each other based on dynamic network conditions to boost its performance, so-called soft cooperation. However, it is quite challenging to make optimal offloading decisions with external dependency between tasks of different DAGs introduced by soft cooperation, as well as the subsequent huge continuous solution space caused. In this paper, we propose a DAG-based dependent tasks offloading method with soft cooperation in MEC-enabled IoT. First, we formulate the problem as a Markov decision process (MDP), aiming to minimize the application latency and energy consumption, and to maximize the cooperation gain simultaneously. Then, we propose a branch soft actor-critic (BSAC) algorithm to make optimal decisions under dynamic network conditions, including the offloaded tasks, the CPU frequency of end devices, and the sharing ratio of intermediate data. Specifically, BSAC uses multiple branch networks to reduce the solution space. Finally, a series of simulations are conducted to establish the superiority of the BASC algorithm over state-of-the-art solutions.

Mobility on-demand (MoD) systems widely use machine learning to estimate matching utilities of order-vehicle pairs to dispatch orders by bipartite matching. However, existing methods suffer from overestimation problems due to the complex interactions among order-vehicle pairs in the global bipartite graph, leading to low overall revenue and order completion rate. To fill this gap, we propose a multi-agent deep reinforcement learning (MADRL) based order dispatching method with bipartite splitting, named SplitMatch. The key idea is to split the global bipartite graph into multiple sub-bipartite graphs to overcome the overestimation problem. First, we propose a bipartite splitting theorem and prove that the optimal solution of global bipartite matching can be achieved by solving multiple sub-bipartite matching problems when certain conditions are met. Second, we design a spatial-temporal padding prediction algorithm to generate sub-bipartite graphs that satisfy this theorem, where the spatial-temporal feature of orders and vehicles is captured. Next, we propose a MADRL framework to learn the matching utility, where multi-objective, e.g., immediate revenue and quality of service (QoS), are taken into account to deal with varying action space. Finally, a series of simulations are conducted to verify the superiority of SplitMatch in terms of overall revenue and order completion rate.

Teacher-student learning has emerged as a promising framework for real-time video inference on mobile devices in multi-access edge computing (MEC) networks, where heavyweight teacher models are deployed on edge servers, and lightweight student models distilled from teacher models are deployed on mobile devices. To deal with data drift and maintain the inference accuracy, the student model has to be updated periodically with the help of the teacher model through a training process. Different training configurations, such as training epochs and frozen layers, lead to different accuracy improvements with different resource requirements. However, in multi-user heterogeneous MEC networks, due to resource heterogeneity and limited computing resources of edge servers, it is quite challenging to update all the student models simultaneously to achieve high inference accuracy. To address this problem, in this paper, we propose an adaptive teacher-student framework in multi-user heterogeneous MEC networks. The key idea is to adaptively make optimal updating decisions (i.e., offloading decision and configuration selection decision) for each user, where the available resources of edge servers and network conditions are taken into account. First, we model the teacher-student collaborative video inference problem as an optimization problem with the aim of maximizing the average inference accuracy. Then, we propose an evolutionary deep reinforcement learning algorithm, CEM-MASAC, to solve this problem. Finally, trace-driven simulations employing real-world bandwidth traces demonstrate the superiority of our algorithm compared to the baseline methods.

The mobility on demand (MoD) system relieves traffic pressure by simultaneously dispatching multiple orders to a vehicle via ridesharing. However, since the supply-demand distribution varies over time, existing dispatching methods for minimum fleet failed to achieve long-term supply-demand equilibrium, and thus greatly reduces the order completion rate. In this paper, ElasticShare, a ride-sharing order dispatch method, is proposed to maximize the order completion rate under dynamic supply-demand distribution. First, we formalize the ridesharing order dispatching problem as an offline optimization problem and then prove it can be solved in an online manner by adding dummy orders and vehicles satisfying long-term supply-demand equilibrium conditions when dispatching. Second, based on the proof, we generate a certain number of dummies according to the supply-demand relation to promote or restrain ridesharing in an elastic manner. The characteristics of the dummies are determined by statistics and a specific selection method to ensure that the solution approximates the long-term supply-demand equilibrium. Next, we decouple the online problem into two sub-problems (order associating and order association dispatching), which are solved by a greedy algorithm and correctional order association dispatching algorithm, respectively. Finally, simulations with real-world data are used to validate the superiority of ElasticShare over state-of-the-art solutions in terms of the order completion rate.

Mobile edge computing (MEC) is a key enabler for ultra-low latency in heterogeneous dense cellular networks in the 5G era and beyond, by deploying services at the network edge. Due to high user mobility, the services are usually migrated to follow the users by predicting the user trajectory to achieve a balance between energy consumption and service latency. However, service migration for multi-user heterogeneous dense cellular networks is challenging because (1) the user trajectory prediction, which is crucial for service migration, becomes intractable with a large number of users, and (2) making service migration decisions for each user independently is subjected to interference among the users. Therefore, in this study, we formulated the service migration of all the users in MEC-enabled heterogeneous dense cellular networks as an optimization problem, with the objective of minimizing the average energy consumption while satisfying the service latency requirements, taking into account the interference among different users. Next, we developed an efficient energy-efficient online algorithm based on the Lyapunov and particle swarm optimizations, called EGO, to resolve the original problem without predicting the trajectories of the users. Finally, a series of simulations based on real-world mobility traces of vehicles in Bologna were conducted to establish the superiority of the EGO algorithm over state-of-the-art solutions.

Millimeter-wave (mmWave) communication is a promising technology for future vehicular networks, where plenty of self-driving vehicles transmit a great amount of sensing data to the edge-cloud platform for real-time processing to ensure driving safety. While beam selection has been widely investigated in single mmWave base station (mmBS) scenario to maximize the throughput between the vehicle and the mmBS, it is still quite challenging to perform optimal beam selection in mmWave vehicular networks with multiple mmBSs. On the one hand, performing beam selection at a central controller with global information of the networks is infeasible due to the exponentially increased complexity. On the other hand, a distributed solution may suffer from the interference between overlapping beams among mmBSs which leads to severe throughput degradation. To fill this gap, in this paper, we propose a Multi-Agent Reinforcement Learning based cooperative Beam Selection (MARL-BS) algorithm for mmWave vehicular networks. Specifically, we model the beam selection problem as a multi-agent multi-armed bandit problem and then adopt Q-learning to learn how to coordinate the beam selection decisions. In the proposed approach, each mmBS acts as an agent and learns the Q-values of its own actions in conjunction with those of the other mmBSs. We further propose a modified combinatorial upper confidence bound (CUCB) algorithm to take advantage of exploring and exploiting all the candidate beams to avoid falling into local optimum. Finally, our simulations validate the proposed MARL-BS algorithm and confirm its higher performance compared with the other benchmark algorithms.

To cope with user mobility and resource constraints of the edge servers, various service migration policies have been proposed in mobile edge computing (MEC) to achieve a trade-off between user-perceived delay and the service migration cost by moving the service to the user as close as possible. However, there is a risk of user location privacy leakage if a malicious eavesdropper tracks the service migration trajectory. In this paper, we investigate service migration in MEC by taking the risk of location privacy leakage into account. More specifically, we define the total cost of the system as the combination of the migration cost, user-perceived delay and the risk of location privacy leakage. We formulate the service migration problem as a Markov decision process, and propose an efficient algorithm to find the optimal solution that minimize the long-term total cost. Finally, the simulations based on real-world taxi traces in San Francisco show that the proposed method can make service migration decisions effectively protect the location privacy of users, as well as achieves a lower total cost than other baseline methods.

In this paper, we investigate the physical layer security performance of untrusted decode-and-forward (DF) relay networks allowing intra-link errors with cooperative jamming. Different from traditional DF relaying protocol, the decoded message at the relay will always be forwarded to the destination node in decode-and-forward relaying allowing intra-link errors (DF-IE), which can be leveraged to enhance the security of relay networks with untrusted relays. To further improve the security performance of DF-IE, we allow the destination node to send jamming signals to impair the signal reception at the relay node, which is referred to as DF-IE with cooperative jamming (DF-IE-CJ). Reliable-and-secure probability (RSP) is used to evaluate the performance of the untrusted relay networks, which represents the probability that the destination node can successfully decode the original message sent from the source node while the relay node can not decode the original message. First, the RSP of DF-IE-CJ is derived from a fading scenario where all the channels between the nodes suffer from block Rayleigh fading. Next, we propose a power allocation scheme to maximize the RSP with different signal-to-noise ratios (SNRs). To verify the effectiveness of DF-IE-CJ, we compare the RSP performance of DF-IE-CJ with that of a widely used schemes, cooperative jamming (CJ). A series of numerical simulations verified the accuracy of the theoretical analysis, and the superiority of DF-IE-CJ over CJ about 5% in RSP.