Electricity Grid Prediction System Using Artificial Neural Networks And Machine Learning Methods

The aim of this study is to enable network energy demand forecasting through efficient methods such as machine learning (ML) and artificial neural networks (ANN), which have achieved significant success in prediction tasks in recent years, by leveraging electric vehicles (EVs) and vehicle-to-grid (V2G) systems. With the rapid increase in the adoption of electric vehicles and their integration into grid systems, this study aims to help electric vehicle users generate additional income by using the vehicle-to-grid (V2G) system, which is dependent on the grid's energy demand. At the same time, it seeks to assist energy supply companies in making more efficient and sustainable energy procurement plans by accurately forecasting these demand fluctuations. The integration of electric vehicles with network energy demands presents new opportunities for grid management, and managing this integration effectively is critical to balancing energy supply and demand. The accuracy of energy demand forecasting not only improves energy management but also offers significant opportunities for sustainable energy production and consumption. In this thesis, the impact of electric vehicles on network energy demands will be analyzed comprehensively using ANN and ML methods, and how electric vehicle users can benefit from demand fluctuations through V2G will be explored in detail. Furthermore, the strategic advantages this system can offer to energy supply companies and the potential optimizations that can be achieved in energy management will be discussed. Ultimately, this study aims to develop a model that contributes to grid management through electric vehicles, thereby enhancing both efficiency and sustainability in the energy sector.