Co-Optimization of Revenue and Communication for Virtual Power Plants via Renewable Energy Forecasting and Time-Segmented Access

Abstract

Integrating distributed energy resources (DERs) via Virtual Power Plants (VPPs) faces challenges like renewable intermittency, communication scheduling uncertainties, and high data collection costs. While existing studies often overlook practical implementation efficiency, this paper proposes a VPP scheduling framework integrated with communication optimization. First, a communication-scheduling model is established to quantify the impact of network uncertainties on revenue. Second, an equipment pre-allocation strategy based on historical data clustering is presented to lower trial-and-error costs and algorithm complexity. Finally, a global optimization algorithm achieves time-segmented collaborative optimization of equipment access, reducing network switching frequency while balancing packet loss, transmission delay, and operational revenue. Simulation results demonstrate that the proposed strategy reduces VPP scheduling revenue loss by approximately 23.6% compared with the traditional greedy algorithm. Furthermore, when evaluated against classic metaheuristic baseline algorithms such as PSO under identical forecasting conditions, Network-Aware FA (NAFA) effectively escapes local optima and achieves the lowest revenue loss, strongly validating the economic efficiency, algorithmic superiority and scheduling reliability of the proposed framework.