Electrical energy consumption prediction using machine learning for industry and smart buildings
Abstract : Machine learning (ML) methods has recently contributed very well in the advancement of the prediction models used for energy consumption. Such models highly improve the accuracy, robustness, and precision and the generalization ability of the conventional time series forecasting tools. This article reviews the state of the art of machine learning models used in the general application of energy consumption. Through a novel search and taxonomy the most relevant literature in the field are classified according to the ML modeling technique, energy type, perdition type, and the application area. A comprehensive review of the literature identifies the major ML methods, their application and a discussion on the evaluation of their effectiveness in energy consumption prediction. This paper further makes a conclusion on the trend and the effectiveness of the ML models. As the result, this research reports an outstanding rise in the accuracy and an ever increasing performance of the prediction technologies using the novel hybrid and ensemble prediction models.
Nowadays, reliability and sustainability of energy are the two critical factors to be considered while checking for any energy sources. Also, increasing utilization of energy has led to development of solutions to save electricity. Prediction of energy is one such scheme that help forecast future energy demand in accordance with the current usage and many others conditions. There are many techniques used for prediction of electricity consumption like statistical, machine learning, deep learning, etc, but prediction with machine learning has gained more popularity.
the electricity demand is volatile in nature, it cannot be stored and has to be consumed immediately; so efficient load forecasting of electricity an important challenge in managing supply and demand of the electricity
This study proposes a method for forecasting the energy consumption of residential buildings by using machine learning technique. Here the random forest algorithm for classification is used. Random forest classifier uses multitude of decision trees, making it robust and hence increasing the accuracy. The model include preprocessing the data that is removing unwanted and incomplete data, feature engineering phase in which variables of importance are selected, then learning a classification model includes training a prediction model using historical data, and the experimental evaluation on the dataset for individual household electric power consumption. Experimentation was performed on 5 years consumption data and results produced by the proposed system yield a better performance. The model produces electricity consumption prediction for given date and time.
? In electric power systems many different prediction techniques have been used for achieving accuracy. Because of its high performance and accuracy, forecasting of electric energy using machine learning has been of great interest.
? Main focus here was utilization of smart meter data for forecasting so that energy demands can be managed appropriately.
|