Research Article
Bidding Feature Extraction and Bidding Strategy Optimization of Generation Companies Based on Big Data Analysis and Machine Learning
@INPROCEEDINGS{10.4108/eai.12-1-2024.2347200, author={Yang Tang and Yifeng Liu and Weiqiang Huo and Meng Chen and Junxuan Zou and Xi Chen}, title={Bidding Feature Extraction and Bidding Strategy Optimization of Generation Companies Based on Big Data Analysis and Machine Learning}, proceedings={Proceedings of the 3rd International Conference on Big Data Economy and Digital Management, BDEDM 2024, January 12--14, 2024, Ningbo, China}, publisher={EAI}, proceedings_a={BDEDM}, year={2024}, month={6}, keywords={electricity market; bidding strategy; big data analyze; canonical correlation analysis; simulated annealing algorithm}, doi={10.4108/eai.12-1-2024.2347200} }- Yang Tang
Yifeng Liu
Weiqiang Huo
Meng Chen
Junxuan Zou
Xi Chen
Year: 2024
Bidding Feature Extraction and Bidding Strategy Optimization of Generation Companies Based on Big Data Analysis and Machine Learning
BDEDM
EAI
DOI: 10.4108/eai.12-1-2024.2347200
Abstract
This paper introduces a method for optimizing bidding strategy for generation companies based on big data analysis and machine learning. This paper first proposes a bidding feature extraction model based on canonical correlation analysis, then proposes a generation company bidding prediction model, and finally solves the bi-level optimization model for generation companies bidding strategy optimization based on the simulated annealing method. A case scenario based on actual spot market data in China is provided to illustrate the relevant method. This paper optimizes the bidding strategy for a large coal-fired unit, and the profit of the unit increased by 76.6% after optimization. It is found that the key point of the bidding strategy for large coal-fired units is to keep the price of the first section low to ensure that the unit can always be turned on.
