Design and implementation of an AI-based & IoT-enabled Home Energy Management System: A case study in Benguerir — Morocco
Home Energy Management Systems (HEMS) are of great importance today and have attracted a great deal of interest from both, academic researchers, and industrial engineers. These systems are considered as the intersection point between the smart grid and the smart home. Indeed, they can communicate wi...
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Elsevier
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/853488f79e684dd1937628da5e11bba1 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| Sumario: | Home Energy Management Systems (HEMS) are of great importance today and have attracted a great deal of interest from both, academic researchers, and industrial engineers. These systems are considered as the intersection point between the smart grid and the smart home. Indeed, they can communicate with the user, home appliances, on-site generation sources, storage devices, and the grid operator to make dynamic decisions enabling intelligent and efficient energy management.This work aims to design and implement a smart HEMS that ensures renewable energy integration and energy efficiency improvement in residential buildings. The system designed in this work has been implemented as part of a pilot project in a testbed house of the Smart Campus — Green & Smart Building Park, Benguerir, Morocco.The proposed HEMS framework is based on two control strategies that work jointly: the first concerns the scheduling and control of power dispatch among generation, consumption, and storage agents (Supply-Side Management), while the second concerns the scheduling and control of flexible appliances for optimal load profile modulation (Demand-Side Management). The management of energy flows is based on grid electricity price, forecasting data (PV generation and weather conditions) and user preferences. The two designed control strategies are combined into an AI-based multi-objective optimization algorithm that minimizes costs and maximizes comfort level simultaneously.The obtained results validate the effectiveness of the proposed algorithm and indicate that it would significantly increase the penetration of PV energy for self-consumption and reduce electricity costs, while ensuring a proper compromise between monetary spending and comfort level. The large-scale implementation of such systems would help decarbonize residential energy sector through higher renewable energy integration and energy efficiency improvement in buildings. |
|---|