Electrical markets and MLP neural networks with MATLAB and MATPOWER

• Grant number: 14/05426-9
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: August 01, 2014
• End date: July 31, 2015
• Field of knowledge: Engineering - Electrical Engineering - Power Systems
• Principal Investigator: Anna Diva Plasencia Lotufo
• Grantee: Gilian Sayuri Saccai Matsuda
• Host Institution: Faculdade de Engenharia (FEIS). Universidade Estadual Paulista (UNESP). Campus de Ilha Solteira. Ilha Solteira , SP, Brazil

Abstract

Price forecasting is one of the tasks executed in the planning and operation of electricity markets. According to the literature, Artificial Neural Networks are the most used techniques to forecast as well as associated with other classical methods or other artificial intelligence forming the hybrid methods. This work has two parts: use the IEEE 24 RTS to run a DC OPF and compute the LMP randomly varying the load to obtain different scenarios and after realizing the price prediction with Neural Networks (MLP). The DC OPF will be done by MATPOWER and the predictions by the Neural Network Toolbox of MATLAB. (AU)