Bidding Strategy with Forecast Technology Based on Support Vector Machine in Electrcity Market

TL;DR

This paper proposes two SVM-based bidding strategies for electricity markets that incorporate price forecast accuracy and bid impact, aiming to improve risk management and decision-making.

Contribution

It introduces novel SVM-based bidding strategies that consider forecast accuracy and bid impact, enhancing market participation strategies.

Findings

Strategies effectively control bidding risks through parameter tuning

Approaches demonstrate improved risk management in numerical tests

SVM-based methods outperform traditional bidding strategies

Abstract

The participants of the electricity market concern very much the market price evolution. Various technologies have been developed for price forecast. SVM (Support Vector Machine) has shown its good performance in market price forecast. Two approaches for forming the market bidding strategies based on SVM are proposed. One is based on the price forecast accuracy, with which the being rejected risk is defined. The other takes into account the impact of the producer's own bid. The risks associated with the bidding are controlled by the parameters setting. The proposed approaches have been tested on a numerical example.