Intelligent edge computing carries out edge devices of the Internet of things(Io T) for data collection, calculation and intelligent analysis, so as to proceed data analysis nearby and make feedback timely. Because of...Intelligent edge computing carries out edge devices of the Internet of things(Io T) for data collection, calculation and intelligent analysis, so as to proceed data analysis nearby and make feedback timely. Because of the mobility of mobile equipments(MEs), if MEs move among the reach of the small cell networks(SCNs), the offloaded tasks cannot be returned to MEs successfully. As a result, migration incurs additional costs. In this paper, joint task offloading and migration schemes in mobility-aware Mobile Edge Computing(MEC) network based on Reinforcement Learning(RL) are proposed to obtain the maximum system revenue. Firstly, the joint optimization problems of maximizing the total revenue of MEs are put forward, in view of the mobility-aware MEs. Secondly, considering time-varying computation tasks and resource conditions, the mixed integer non-linear programming(MINLP) problem is described as a Markov Decision Process(MDP). Then we propose a novel reinforcement learning-based optimization framework to work out the problem, instead traditional methods. Finally, it is shown that the proposed schemes can obviously raise the total revenue of MEs by giving simulation results.展开更多
Genetic Algorithms (GAs) are efficient non-gradient stochastic search methods and Parallel GAs (PGAs) are proposed to overcome the deficiencies of the sequential GAs, such as low speed, aptness to local convergence, e...Genetic Algorithms (GAs) are efficient non-gradient stochastic search methods and Parallel GAs (PGAs) are proposed to overcome the deficiencies of the sequential GAs, such as low speed, aptness to local convergence, etc. However, the tremendous increase in the communication costs accompanied with the parallelization stunts the further improvements of PGAs. This letter takes the decrease of the communication costs as the key to this problem and advances a new Migration Scheme based on Schema Theorem (MSST). MSST distills schemata from the populations and then proportionately disseminates them to other populations, which decreases the total communication cost among the populations and arms the multiple-population model with higher speed and better scalability.展开更多
基金supported in part by the National Natural Science Foundation of China under Grant 61701038。
文摘Intelligent edge computing carries out edge devices of the Internet of things(Io T) for data collection, calculation and intelligent analysis, so as to proceed data analysis nearby and make feedback timely. Because of the mobility of mobile equipments(MEs), if MEs move among the reach of the small cell networks(SCNs), the offloaded tasks cannot be returned to MEs successfully. As a result, migration incurs additional costs. In this paper, joint task offloading and migration schemes in mobility-aware Mobile Edge Computing(MEC) network based on Reinforcement Learning(RL) are proposed to obtain the maximum system revenue. Firstly, the joint optimization problems of maximizing the total revenue of MEs are put forward, in view of the mobility-aware MEs. Secondly, considering time-varying computation tasks and resource conditions, the mixed integer non-linear programming(MINLP) problem is described as a Markov Decision Process(MDP). Then we propose a novel reinforcement learning-based optimization framework to work out the problem, instead traditional methods. Finally, it is shown that the proposed schemes can obviously raise the total revenue of MEs by giving simulation results.
基金National Natural Science Foundation of China (No.60073012)National Science Foundation of Jiangsu, China(BK2001004)Visiting Scholar Foundation of Key Lab. in the University
文摘Genetic Algorithms (GAs) are efficient non-gradient stochastic search methods and Parallel GAs (PGAs) are proposed to overcome the deficiencies of the sequential GAs, such as low speed, aptness to local convergence, etc. However, the tremendous increase in the communication costs accompanied with the parallelization stunts the further improvements of PGAs. This letter takes the decrease of the communication costs as the key to this problem and advances a new Migration Scheme based on Schema Theorem (MSST). MSST distills schemata from the populations and then proportionately disseminates them to other populations, which decreases the total communication cost among the populations and arms the multiple-population model with higher speed and better scalability.
