8 January 2021 in IEEE Transactions on Mobile Computing
Mobile crowdsensing has emerged as a promising paradigm where location-based sensing tasks are outsourced to mobile participants carrying sensor-equipped devices. A critical issue of crowdsensing is to guarantee the sensing coverage by appropriately recruiting participants, which requires participants’ precise locations and thus raises privacy concerns. In this paper, we are motivated to develop a privacy preserving participant recruitment scheme for mobile crowdsensing, which maximizes the spatial coverage of the sensing range while protecting participants’ location privacy against an untrusted crowdsensing platform. Briefly, we propose a utility-assured location obfuscation mechanism operated in a hexagonal grid system, which the participants can follow to locally perturb their locations with personalized privacy demands. Given the obfuscated locations, we efficiently solve a coverage-maximized participant recruitment problem with the budget constraint by using a deterministic rounding algorithm. Considering the existence of biased sensing data incurred by location obfuscation, we further develop a fault-aware crowdsensing framework to improve the robustness of the recruitment strategy, where a constant-approximation algorithm is applied to select participants against any number of unqualified sensing results. Extensive simulations on real-world location datasets and Uber’s geospatial indexing system validate the efficacy of our location obfuscation mechanism and participant recruitment schemes in mobile crowdsensing systems.
6 February 2023 in IEEE Journal on Selected Areas in Communications
Federated learning (FL) over mobile devices has fostered numerous intriguing applications/services, many of which are delay-sensitive. In this paper, we propose a service delay efficient FL (SDEFL) scheme over mobile devices. Unlike traditional communication efficient FL, which regards wireless communications as the bottleneck, we find that under many situations, the local computing delay is comparable to the communication delay during the FL training process, given the development of high-speed wireless transmission techniques. Thus, the service delay in FL should be computing delay + communication delay over training rounds. To minimize the service delay of FL, simply reducing local computing/communication delay independently is not enough. The delay trade-off between local computing and wireless communications must be considered. Besides, we empirically study the impacts of local computing control and compression strategies (i.e., the number of local updates, weight quantization, and gradient quantization) on computing, communication and service delays. Based on those trade-off observation and empirical studies, we develop an optimization scheme to minimize the service delay of FL over heterogeneous devices. We establish testbeds and conduct extensive emulations/experiments to verify our theoretical analysis. The results show that SDEFL reduces notable service delay with a small accuracy drop compared to peer designs.
1 June 2021 in IEEE Transactions on Mobile Computing
Device-to-Device (D2D) communication enabling direct data transmission between two mobile users has emerged as a vital component for 5G cellular networks to improve spectrum utilization and enhance system capacity. A critical issue for realizing these benefits in D2D-enabled networks is to properly allocate radio resources while coordinating the co-channel interference in a time-varying communication environment. In this paper, we propose a Stackelberg game (SG) guided multi-agent deep reinforcement learning (MADRL) approach, which allows D2D users to make smart power control and channel allocation decisions in a distributed manner. In particular, we define a crucial Stackelberg Q-value (ST-Q) to guide the learning direction, which can be calculated based on the equilibrium achieved in the Stackelberg game. With the guidance of the Stackelberg equilibrium, our approach converges faster with fewer iterations than the general MADRL method and thereby exhibits better performance in handling the network dynamics. After the initial training, each agent can infer timely D2D resource allocation strategies with distributed execution. Extensive simulations are conducted to validate the efficacy of our proposed scheme in developing timely resource allocation strategies. The results also show that our method outperforms the general MADRL based approach in terms of the average utility, channel capacity, and training time.
16 March 2020 in IEEE Internet of Things Journal
4 March 2019 in IEEE Internet of Things Journal
The transportation network company (TNC) services efficiently pair the passengers with the vehicles/drivers through mobile applications such as Uber, Lyft, Didi, etc. TNC services definitely facilitate the traveling of passengers, while it is equally important to effectively and intelligently schedule the routes of cruising TNC vehicles to improve TNC drivers’ revenues. From the TNC drivers’ side, the most critical question to address is how to reduce the cruising time, and improve the efficiency/earnings by using their own vehicles to provide TNC services. In this paper, we propose a deep reinforcement learning based TNC route scheduling approach, which allows the TNC service center to learn about the dynamic TNC service environment and schedule the routes for the vacant TNC vehicles. In particular, we jointly consider multiple factors in the complex TNC environment such as locations of the TNC vehicles, different time periods during the day, the competition among TNC vehicles, etc., and develop a deep Q-network (DQN) based route scheduling algorithm for vacant TNC vehicles based on distributed framework, which makes the server closer to the terminal users and accelerates the training speed. Furthermore, we apply the geo-indistinguishability scheme based on differential privacy to preserve the sensitive location information uploaded by the passengers. We evaluate the proposed algorithm’s performance via simulations using open data sets from Didi Chuxing. Through extensive simulations, we show that the proposed scheme is effective in reducing the cruising time of vacant TNC vehicles and improving the earnings of TNC drivers.
27 March 2020 in IEEE Internet of Things Journal
Cooperative Multi-Access Edge Computing (MEC) is a promising paradigm for the next generation mobile networks. However, when the number of users explodes, the computational complexity of existing optimization or learning based task placement approaches in the cooperative MEC can increase significantly, which leads to intolerable MEC decision making delay. In this paper, we propose a mean field game (MFG) guided deep reinforcement learning (DRL) approach for the task placement in the cooperative MEC, which can help servers make timely task placement decisions, and significantly reduce average service delay. Instead of applying MFG or DRL separately, we jointly leverage MFG and DRL for task placement, and let the equilibrium of MFG guide the learning directions of DRL. We also ensure that the MFG and DRL approaches are consistent with the same goal. Specifically, we novelly define a mean field guided Q-value (MFG-Q), which is an estimation of Q-value with the Nash equilibrium gained by MFG. We evaluate the proposed method’s performance using real-world user distribution. Through extensive simulations, we show that the proposed scheme is effective in making timely decisions and reducing the average service delay. Besides, the convergence rates of our proposed method outperform the pure DRL based approaches.