Advertisement
Published in:
2017 | OriginalPaper | Chapter
Market-Clearing Price Forecasting for Indian Electricity Markets
Authors : Anamika, Niranjan Kumar
Published in: Proceeding of International Conference on Intelligent Communication, Control and Devices
Publisher: Springer Singapore
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Abstract
A robust market-clearing price (MCP) forecasting tool is needed for efficient and profitable power market execution. The work predicts MCPs for the months of April, May, and June using artificial neural networks (ANNs). A very large ANN with varying input data may lead to poor prediction in comparison with smaller ANN with similar input data due to its highly sensitive characteristic. Grouping of similar data accelerates the learning process of ANNs along with more accurate and efficient prediction result. In this paper, input data set is arranged into homogeneous groups of hours with similarity in prices, based on correlation matrix and peak, off-peak values of prices. Mean absolute percentage errors (MAPEs) are evaluated to find out the best grouping technique and forecasting model for Indian Electricity Markets. MAPE results are shown for the best two consecutive days and the whole month to demonstrate the effectiveness of grouping techniques.