Machine learning based renewable energy solutions for smart grid technologies

Abstract

Smart grid engineering is the key for an optimized use of extensive energy resources which allows the hybrid renewable energy sources microgrid to be integrated and therefore dispatch their power generation to the grid over long distance DC transmission lines using the HDVC transmission technologies. However, the required number of generating units of wind-turbine generators and photovoltaic arrays, and the associated storage capacity for standalone and/or grid connected hybrid microgrid is determined using a sizing algorithm based on the observation that the state of charge of battery should be periodically invariant which results in a microgrid optimum cost. However the intermittency of wind speed and solar irradiance are very challenging to power production from wind turbines and photovoltaic arrays. In this context, the Convolution Neural Network (CNN) can symbolize a practical and reliable tool to precisely monitor and predict the wind speed and solar irradiance outputs and accordingly manage the power transfer switching between areas that have surplus renewable energies to areas that have shortage in energies by initiating the Energy Management System (EMS) to dispatch power according to schedule. The efficiency of the proposed model CNN was tested using meteorological data related to Lebanon, Beirut city. The experimental results indicate that the Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) values related to wind speed and solar irradiance are small, demonstrating very high forecasting accuracy.