A new type power system task offloading and resource allocation based on AHP-DDPG

In the New Type Power System, a large number of terminal devices deployed in multiple scenarios are connected in parallel to the power system, resulting in a significant increase in the amount of various business data and difficulty in ensuring differentiated demands for power services. This article proposes a New Type Power System task offloading and resource allocation algorithm based on AHP-DDPG to address this issue. Firstly, the Analytic Hierarchy Process is used to determine the priority order for handling various types of power services, ensuring timely processing of critical data. Then, considering the weights of delay and energy consumption, a cost function is established with the optimization objective of minimizing system cost, and a joint optimization problem of task offloading and resource allocation is constructed. Finally, the joint optimization problem is modeled as a Markov decision process, with state space, action space, and reward function constructed, and solved using the Deep Deterministic Policy Gradient (DDPG) algorithm. The simulation experiment results show that compared with existing methods, the proposed algorithm can achieve a system cost 22% to 31% lower than random strategies, and achieve load balancing effect.