Machine Learning-Based Day-Ahead Market Energy Usage Bidding for Smart Microgrids
Al-Ammar, Mohd Saqib, Sanjeev Anand Sahu, Mohd Sakib, Essam A. . 2021
ABSTRACT
An expert system of the bidding process for the energy of charging infrastructure using cloud-based artificial intelligence (AI) has demonstrated in this work. Finding out an optimal energy price that is suitable for all the three entities (vehicle owners, electricity providers, and charging service providers) is a hectic job for a human being. The proposed system is competent to automating the bidding process of the day-ahead market using a cloud-based infrastructure. In this system, preregistered vehicle owners will be able to bid for their required unit of energy and the same as on the other side, electricity providers give their service quotes by filling an online form. After getting data from both sides, AI comes into the picture and provides an optimal solution to the charging service provider. This system is not only beneficial for the charging service providers but also will be beneficial for the electricity providers and vehicle owners. xEV users can check optimal estimated energy prices for any specific charging service provider, which can be predicted based on previous bidding data stored in the cloud. Same as for the electricity providers, it will suggest some suitable pairs of price and quantity of energy for their service quotes. Further, AI will improve the algorithm in a way to maximize the profit for charging service provider, as well as bidding data will increase in the cloud.
State-of-the-art research to solve the grid congestion due to EVs is focused on smart charging and using (centralized, de-centralized, vehicle-to-grid) stationery energy storage as a buffer…
Electric vehicles (EVs) are not only a viable energy efficient mode of transport, but they have considerable capacity of providing flexible and quick responding storage alternative based on…
ABSTRACT