Resource Allocation based on Computing Modeling in Computing Power Network

Abstract

Computing Power Network as a novel network architecture, aims to integrate ubiquitous computing power with the network, enabling intelligent scheduling and efficient allocation of computational resources to meet the high-diversity demands of computational services.The resource allocation problem in the computing power network differs from the traditional cloud-edge-end structure. It necessitates adopting a macroscopic perspective to establish an effective mapping between computational resources and demands. However, this task is inherently challenging due to the heterogeneous nature of both resources and demands.In this paper, we investigate and summarize the current computing modeling scheme. Based on the unified measurement of resources and demand, we model the resource allocation problem in the computing power network as the demand response problem in the smart grid. Then we solve the above problem using game theory, and verify the effectiveness of the method through simulation experiments.