Improving Sequential Market Coordination via Value-oriented Renewable Energy Forecasting

TL;DR

This paper introduces a value-oriented renewable energy forecasting method that optimizes RES entering quantities to minimize total operating costs in electricity markets, improving coordination between day-ahead and real-time markets.

Contribution

It proposes a novel training approach for RES forecasts that directly minimizes expected market operating costs, unlike traditional error minimization models.

Findings

Significant reduction in overall operating costs using the proposed forecasting method.

Derivation of an exact piecewise linear loss function for market-based training.

Efficient gradient computation enabling practical implementation.

Abstract

Large penetration of renewable energy sources (RESs) brings huge uncertainty into the electricity markets. The current deterministic clearing approach in the day-ahead (DA) market, where RESs participate based on expected production, has been criticized for causing a lack of coordination between the DA and real-time (RT) markets, leading to high overall operating costs. Previous works indicate that improving day-ahead RES entering quantities can significantly mitigate the drawbacks of deterministic clearing. In this work, we propose using a trained forecasting model, referred to as value-oriented forecasting, to determine RES Improved Entering Quantities (RIEQ) more efficiently during the operational phase. Unlike traditional models that minimize statistical forecasting errors, our approach trains model parameters to minimize the expected overall operating costs across both DA and RT markets. We derive the exact form of the loss function used for training, which becomes piecewise linear when market clearing is modeled by linear programs. Additionally, we provide the analytical gradient of the loss function with respect to the forecast, enabling an efficient training strategy. Numerical studies demonstrate that our forecasts significantly reduce overall operating costs for deterministic market clearing compared to conventional forecasts based on expected RES production.