Delay-Prioritized and Reliable Task Scheduling With Long-Term Load Balancing in Computing Power Networks

Abstract

In the era driven by big data and algorithms, the efficient collaboration of pervasive computing power is crucial for rapidly meeting computing demands and enhancing resource utilization. However, current mainstream end-edge-cloud collaboration faces challenges of computing isolation, adversely affecting resource efficiency and user experience. The Computing Power Network (CPN) is a novel architecture designed to sense and collaborate ubiquitous computing resources through networks. Nevertheless, the expansion of its scope and the integration of networks complicate task scheduling. To address this, we design a collaborative scheduling system that considers the joint selection of computing nodes and network links, aiming to reduce delay, enhance reliability, and ensure long-term load balance. First, we propose a delay-prioritized reliable scheduling policy based on a dual-priority mechanism for forwarding and computing. Second, we define the scheduling problem as a Constrained Markov Decision Process (CMDP) and introduce Lyapunov optimization to transform constraints into instantaneous optimizations, achieving a long-term balanced load of computing and network resources. Lastly, we employ an enhanced Deep Reinforcement Learning (DRL) approach to solve the problem. Performance evaluation demonstrates that compared to standard DRL, the proposed algorithm effectively reduces delay and improves reliability while maintaining long-term load balance, resulting in an overall performance improvement of 54.7%.