Wireless Body Area Network (WBAN) as one of the primary Internet of Things (IoT) provides real time and continuous healthcare monitoring and has been widely deployed to improve the quality of peoples' life. In edge-enabled WBANs, intensive computing tasks could be offloaded to Mobile Edge Computing (MEC) servers, guaranteeing that the massive amount of health data with different user priorities could be processed in lower delay and energy consumption. Efficient computation offloading schemes are more critical to satisfy the massive data access and personalized service requirements for multiple Quality of Service (QoS) parameters constraint WBANs. In this paper, we propose a Two-Stage Potential Game based Computation Offloading Strategy (TPOS) to optimize resource allocation while taking into consideration the task priorities and user priorities of WBANs. Firstly, we construct a system utility maximization problem about the QoS of tasks. The reward, cost and penalty functions are given to model the computation offloading. Then, we propose a two-stage optimization method to solve the problem of mutual restriction strategies existing in the strategy space of the potential game model, reducing the computation complexity and improving the feasibility of the algorithm. Finally, performance evaluations on average processing delay, energy consumption and network utility are conducted to show the significance of the proposed TPOS algorithm. INDEX TERMS WBAN, edge computing, computation offloading, potential game, healthcare monitoring.

No abstract

The Internet of Medical Things (IoMT) and Artificial Intelligence (AI) have brought unprecedented opportunities to meet massive behavioral data access and personalization requirements for Internet of Behavior (IoB). They facilitate the communication and computing resource allocation to guarantee low delay and energy consumption demands in healthcare. This paper presents an improved offloading algorithm for Mobile Edge Computing (MEC) based on Deep Q Network (DQN) and Simulated Annealing (SA) for IoB. Firstly, we analyze the network model and establish a task cost function based on processing delay and energy consumption. Secondly, we define a Distributed Optimization Problem (DOP) to maximize individual utilities and system utility, which is proved be a potential countermeasure. Thirdly, we conduct Markov modeling for the current offloading strategy-making scheme and define the objectives and constraints of the optimization function. At the same time, the SA is introduced into the DQN Algorithm, which improves the capacity of the algorithm by focusing on the exploration in the early stage and following the experience value in the later stage. From the simulation results, we can see that compared with the traditional scheme, the proposed strategy can maximize the utilization of the system and reduce processing delay and energy consumption.