loading page

Research on Spot Market Price Forecasting Method Considering the Electricity Purchase-Gain for Demand-side
  • +3
  • Ning Wang,
  • Yuan Du,
  • Haohao Wang,
  • Tao Zhu,
  • Mingxing Wu,
  • Saite Yang
Ning Wang
Guangdong Power Exchange Center Co.,Ltd

Corresponding Author:[email protected]

Author Profile
Yuan Du
Beijing Tsintergy Technology Co.,Ltd
Author Profile
Haohao Wang
Guangdong Power Exchange Center Co.,Ltd
Author Profile
Tao Zhu
Guangdong Power Exchange Center Co.,Ltd
Author Profile
Mingxing Wu
Guangdong Power Exchange Center Co.,Ltd
Author Profile
Saite Yang
Beijing Tsintergy Technology Co.,Ltd
Author Profile

Abstract

The clearing price in electricity spot market is an important reference that guides marker participants in making energy purchase. Current electricity price forecasting methods consider the numerical accuracy of the forecast result only, ignoring the need to optimize economic benefits, while higher numerical precision sometimes leads to lower electricity-purchase gain. This paper proposes a price forecasting method that considers both economic benefits and numerical accuracy. A function representing the relationship between the predicted electricity prices and the cost reference for making energy purchase decisions is calculated, and then introduced to the loss function of the prosumers' forecasting model as a revenue-optimizing term. A sequence comparison neural network structure is designed and added to consumers' forecasting model, so that the results of numerical prediction and comparison both contribute to predicting better prices. By co-optimizing numerical precision and electricity-purchase gain, the prediction is more conducive to reducing the cost of purchasing power. Actual electricity market price data are used to verify the feasibility of the proposed forecasting method in improving economic benefits.
18 Jun 2022Submitted to The Journal of Engineering
20 Jun 2022Submission Checks Completed
20 Jun 2022Assigned to Editor
09 Aug 2022Reviewer(s) Assigned
01 Mar 2023Review(s) Completed, Editorial Evaluation Pending
09 Mar 2023Editorial Decision: Revise Major
24 Mar 20231st Revision Received
28 Mar 2023Submission Checks Completed
28 Mar 2023Assigned to Editor
06 Apr 2023Reviewer(s) Assigned
14 Apr 2023Review(s) Completed, Editorial Evaluation Pending
17 Apr 2023Editorial Decision: Revise Minor
18 Apr 20232nd Revision Received
18 Apr 2023Submission Checks Completed
18 Apr 2023Assigned to Editor
22 Apr 2023Reviewer(s) Assigned
22 Apr 2023Review(s) Completed, Editorial Evaluation Pending
27 Apr 2023Editorial Decision: Revise Minor
04 May 20233rd Revision Received
05 May 2023Submission Checks Completed
05 May 2023Assigned to Editor
10 May 2023Reviewer(s) Assigned
13 May 2023Review(s) Completed, Editorial Evaluation Pending
28 Jul 2023Editorial Decision: Accept