Effective End-to-End Learning Framework for Economic Dispatch

TL;DR

This paper proposes an end-to-end machine learning framework for economic dispatch that directly optimizes system cost, overcoming limitations of traditional load forecasting methods by utilizing task-specific criteria and efficient optimization.

Contribution

It introduces a novel end-to-end learning approach with a task-specific criterion and an efficient optimization kernel for economic dispatch, supported by theoretical and empirical validation.

Findings

Enhanced data utilization in dispatch optimization

Improved system cost reduction compared to traditional methods

Theoretical and empirical evidence of framework effectiveness

Abstract

Conventional wisdom to improve the effectiveness of economic dispatch is to design the load forecasting method as accurately as possible. However, this approach can be problematic due to the temporal and spatial correlations between system cost and load prediction errors. This motivates us to adopt the notion of end-to-end machine learning and to propose a task-specific learning criteria to conduct economic dispatch. Specifically, to maximize the data utilization, we design an efficient optimization kernel for the learning process. We provide both theoretical analysis and empirical insights to highlight the effectiveness and efficiency of the proposed learning framework.