当前位置: X-MOL 学术Electr. Power Syst. Res. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A deep learning method for forecasting residual market curves
Electric Power Systems Research ( IF 3.3 ) Pub Date : 2021-01-01 , DOI: 10.1016/j.epsr.2020.106756
Alex Coronati , José R. Andrade , Ricardo J. Bessa

Abstract Forecasts of residual demand curves (RDCs) are valuable information for price-maker market agents since it enables an assessment of their bidding strategy in the market-clearing price. This paper describes the application of deep learning techniques, namely long short-term memory (LSTM) network that combines past RDCs and exogenous variables (e.g., renewable energy forecasts). The main contribution is to build up on the idea of transforming the temporal sequence of RDCs into a sequence of images, avoiding any feature reduction and exploiting the capability of LSTM in handling image data. The proposed method was tested with data from the Iberian day-ahead electricity market and outperformed machine learning models with an improvement of above 35% in both root mean square error and Frechet distance.

中文翻译:

一种预测剩余市场曲线的深度学习方法

摘要 剩余需求曲线 (RDC) 的预测对于价格制定者市场代理来说是有价值的信息,因为它可以评估他们在市场出清价格中的投标策略。本文描述了深度学习技术的应用,即结合过去 RDC 和外生变量(例如,可再生能源预测)的长短期记忆 (LSTM) 网络。主要贡献是建立了将 RDC 的时间序列转换为图像序列的想法,避免任何特征减少并利用 LSTM 处理图像数据的能力。所提出的方法用来自伊比利亚日前电力市场的数据进行了测试,其性能优于机器学习模型,均方根误差和 Frechet 距离均提高了 35% 以上。
更新日期:2021-01-01
down
wechat
bug