Edge computing task allocation method based on deep Monte Carlo tree search

Abstract

The invention discloses an edge computing task allocation method based on deep Monte Carlo tree search, and aims to support optimization of resource allocation by an edge server. And the edge server takes the state of a mobile edge computing system as input, the edge server resource scheduling module outputs an optimal resource allocation scheme through a deep reinforcement learning algorithm, andthe mobile equipment terminal unloads the task according to the optimal resource allocation scheme and executes the task together with the edge server. The deep reinforcement learning algorithm is completed by mutual cooperation of DNN, MCTS and LSTM, and compared with greedy search and DQN algorithms, the algorithm provided by the invention is greatly improved in the aspects of optimizing service time delay and optimizing service energy consumption of the mobile terminal.

Description

technical field [0001] The invention relates to the field of intelligent communication, in particular to an edge computing task allocation method based on deep Monte Carlo tree search. Background technique [0002] At present, some algorithms have been applied to the optimal allocation of mobile edge computing resources. The first method uses a linear programming algorithm to optimize computing resources and bandwidth resources to increase the maximum throughput of the system and reduce the service response delay to improve the performance of the mobile edge system, but this method cannot adjust the offload rate of tasks. The second is an optimization method based on Lyapunov, which is an algorithm that dynamically adjusts the unloading rate of computing tasks, which can reduce the time for completing computing tasks. Task. Moreover, the linear programming algorithm and Lyapunov algorithm used in these two resource allocation optimization methods are all heuristic learning...

AI Technical Summary

Problems solved by technology

The first method uses a linear programming algorithm to optimize computing resources and bandwidth resources to increase the maximum throughput of the system and reduce the service response delay to improve the performance of the mobile edge system, but this method cannot adjust the unloading rate of tasks

The second is an optimization method based on Lyapunov, which is an algorithm that dynamically adjusts the unloading rate of computing tasks, which can reduce the time for completing computing tasks. Task

In addition, the number of mobile devices in the 5G Internet of Things scenario has increased significantly, and the computing tasks of mobile user terminals are diverse, and the optimization problem has become complicated. Existing methods are difficult to deal with high-complexity optimization problems.

Images