Intelligent Electric Power Management System for Economic Maximization in a Residential Prosumer Unit

Abstract

The electricity demand has grown continuously in recent years, raising the necessity to expand generation sources, distribution networks, and equipment efficiency. In addition, it is necessary to attend sustainable development in a conciliated manner. Applications involving the intelligent management of the distributed networks have increased to achieve a balance between growth and sustainability. In this context, this article presents the development of an Intelligent Electric Power Management System (IEPMS) for the economic maximisation of a photovoltaic system applied to a prosumer residential unit without storage in Brazil. Using historical meteorological data and a heuristic to simulate energy use habits, the IEPMS forecasts both generation and demand in 24 hours. From the projections, an optimisation problem was built and solved using the genetic algorithm technique to find the most economical moments for driving loads. This model aims to reach the lowest daily cost of electricity, considering the return (sale) of unused energy to the power distribution company. The validation of the IEPMS considered four usage patterns, integrating 26 scenarios, those composed by the (i) flexibility; (ii) type of tariff; and (iii) hit rates provided by the climate forecasting method proposed for the system. As a result, the IEPMS savings considering the white tariff were 34.72% for one year, assuming full-time external work usage. Additionally, it was possible to identify in all scenarios that the proposed method's performance was not less than 97%, measured through the relative error among distinct hit rates of the evaluated climatic forecast.

Optimal Energy Management System for Grid-Tied Microgrid: An Improved Adaptive Genetic Algorithm

“…A model focuses on achieving the lowest daily electricity cost while considering the return of unused energy to the distribution company. It is validated using various usage patterns and climate forecasting methods [35]. Proposing a machine learning-based feature selection approach, this study enhances short-term electricity demand forecasting accuracy in distributed energy systems [37].…”