Forecast for Market Clearing Price with Artificial Neural Networks in Day Ahead Market

In this study, the Market Clearing Price (MCP) is forecasted with Artificial Neural Networks and modeling success examined for different preprocessing strategies. The purpose of study to obtain optimum model a significant estimation provide best price prediction. hour-based electricity generation data diverse production items are assigned as inputs resulting MCP modeled. raw first cleaned from outliers, then subjected normalization processes 70 ANNs trained. Additionally, networks trained classified in seasons effect seasonal patterns on observed. Finally, showing performance selected. It noted that type strategy hidden layer size key factors make decent estimation. Then, order test extreme cases, special days (official holidays) applied these input. evaluated by comparing predictions actual values. revealed prediction official holidays, which period year required.