This paper presents a Genetic Algorithm-based Home Energy Management System designed to exploit the energy flexibility of user-dependent loads by identifying and recommending optimal operating schedules that minimize electricity costs. To determine the most advantageous 15 min activation slot for the following day for each load, the algorithm uses as input the forecasted consumption profile of non-optimizable loads and photovoltaic generation, both obtained through an LSTM-based model, along with the contracted power, applicable tariffs, and the load profiles of the selected appliances. Unlike previous approaches, the proposed framework allows users to select which loads to optimize and define specific operational constraints. Additionally, a user-friendly interface was developed to facilitate seamless interaction between the user and the system. To validate the proposed framework, a case study was conducted on a residential household with four occupants located in Portugal, considering user-dependent flexible loads such as a washing machine, tumble dryer, and dishwasher. The results demonstrated that the developed system operated effectively, reducing electricity costs by approximately 9% compared to a scenario without the proposed solution.
This article proposes a solution based on a genetic algorithm to exploit the energy flexibility of certain loads, which also considers energy consumption forecasts. Considering the growing need to integrate renewable energy sources in order to reduce greenhouse gases emissions, the algorithm seeks to find the optimal operating schedule for flexible loads. By predicting consumption for each load present in a home, the algorithm suggests optimal operating schedules, minimizing costs without compromising user comfort. The results show a significant reduction in costs, indicating the effectiveness of the proposed algorithm. This study contributes to the understanding and application of energy optimization techniques at building level, promoting the transition to renewable energy communities.
Despite the growing adoption of residential battery storage, most systems rely on basic control strategies, while forecasting-enabled approaches in the literature lack validation on operational installations. To address this, the current study presents a modular system for the management of existing residential photovoltaic battery energy storage systems (PV-BESS), integrating deep learning forecasting with Internet of Things (IoT) infrastructure. The system consists of a physical layer adaptable to inverters with external interfaces, and a virtual layer that determines optimal battery scheduling based on day-ahead forecasts of electricity consumption and photovoltaic generation. To demonstrate the system's capabilities, a forecast-based control strategy was developed for the case-study's time-of-use tariff, where the optimization problem focuses on determining the optimal battery state of charge at the beginning of the peak period. The system was validated through deployment on an existing, operational PV-BESS installation in a residential setting in the historic center of Évora, Portugal, characterized by limited PV generation due to architectural constraints and partial shading. Under a Portuguese time-of-use tariff with settlement mechanism, the proposed control achieved a 3% reduction in electricity costs compared to a maximum self-consumption strategy during autumn and winter, demonstrating the system's viability even under non-ideal conditions.