In-network pooling resource allocation optimization method based on contribution perception in computing power network

Abstract

The invention discloses an intra-network pooling resource allocation optimization method based on contribution awareness in a computing power network. The method comprises the following steps: constructing a computing power network resource allocation system comprising an infrastructure layer, a resource pool layer and a CPN scheduler layer; constructing the computing power queue length of each resource pool in the resource pool layer based on the dynamic nature of the task and the mobile equipment; respectively establishing a computing power model and a cache model in the CPN scheduler layer by using a deep reinforcement learning algorithm, and respectively constructing the models as Markov processes; constructing a utility function of the computing power network resource allocation system based on the computing power model and the cache model; constructing a near-end strategy optimization algorithm based on the attention mechanism by using a near-end strategy optimization algorithm and the attention mechanism; and solving the long-term utility function by using a near-end strategy optimization algorithm based on an attention mechanism by taking maximization of the long-term utility function as a target. According to the method, higher system effectiveness is realized, and the performance of integrated computing tasks and caches can be remarkably improved.

Description

technical field [0001] The invention belongs to the technical field of communication networks, and in particular relates to an optimization method for pooling resource allocation within a network based on contribution perception in a computing power network. Background technique [0002] The development of B5G / 6G technology will support various large-scale data-intensive applications in the next decade, such as virtual and augmented reality, brain communication interface, remote surgery, etc. At the same time, it will generate zettabytes (ZB) of digital information and require more computing power to support it. The development of 6G not only benefits from the technology brought by 5G, but also benefits from the need for more new technologies. Computing Power Network (CPN) provides an effective solution to enable the deep integration of computing power and network. CPN acceleration spreads computing power from a set of data centers to multiple network edges and end users, ...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problem that it is difficult to allocate resources between resource pools in the prior art, and the efficiency of resource allocation is low, the present invention proposes an optimization method for pooled resource allocation in a computing power network based on contribution perception, and designs a CPN A dynamic resource pool, and based on the attention mechanism, the limited resources are placed on the resource pool that makes a greater contribution to the system, so as to allocate resources and maximize the long-term utility of the system

Images