Е-Публикации
Технически университет - София

Abstract: This paper presents a comprehensive overview of machine learning techniques applied to energy consumption forecasting and cost optimization in smart homes. The study examines various predictive models, including statistical timeseries methods, ensemble approaches, and deep learning architectures, and evaluates their suitability for different forecasting horizons and system requirements. Particular attention is given to practical applications such as time-of-use pricing, contract-based energy planning, load shifting, and energy storage management. Challenges such as incomplete or irregular data, model overfitting, interpretability, and privacy concerns are discussed, alongside more recent advancements in explainable and federated learning. The review highlights how predictive analytics can support intelligent, cost-effective, and user-adaptive energy management in smart environments. These insights aim to support the design of smarter, more resilient energy systems capable of adapting to evolving consumer needs and dynamic market conditions.

References

1. T. Hong, P. Pinson, and S. Fan, “Global energy forecasting competition 2012,” Int. J. Forecast., vol. 30, no. 2, pp. 357–363, 2014.
2. Y. Himeur et al., “Recent trends of smart non-intrusive load monitoring in buildings,” Int. J. Intell. Syst., 2022.
3. H. Boxwala and A. Al-Wakeel, “A review of ARIMA and SARIMA models for energy forecasting,” Renew. Energy Rev., vol. 13, no. 2, 2020.
4. B. Völker et al., “Watt’s up at home? Smart meter data analytics from a consumer-centric perspective,” Energies, vol. 14, p. 719, 2021.
5. Y. Himeur et al., “Recent trends of smart non-intrusive load monitoring in buildings,” Int. J. Intell. Syst., 2022.
6. “Analyzing the energy consumption of smart home and price prediction,” Eng. Technol. J., vol. 9, no. 5, 2024.
7. X. Bao, “Applying machine learning for prediction, recommendation, and integration,” Ph.D. dissertation, Oregon State Univ., 2009.
8. G. Chicco and P. Mancarella, “Distributed multi-generation: A comprehensive view,” Renew. Sustain. Energy Rev., vol. 13, pp. 535–551, 2009.
9. A. Tundis et al., “A feature-based model for the identification of electrical devices in smart environments,” Sensors, vol. 19, p. 2611, 2019.
10. Z. Ahmed et al., “Machine learning at Microsoft with ML.NET,” in Proc. 25th ACM SIGKDD, 2019, pp. 2448–2458.
11. E. McKenna, I. Richardson, and M. Thomson, “Smart meter data: Balancing consumer privacy concerns with legitimate applications,” Energy Policy, vol. 41, pp. 807–814, 2012.
12. L. G. Fahad and S. F. Tahir, “Activity recognition and anomaly detection in smart homes,” Neurocomputing, vol. 423, pp. 362–372, 2021.
13. D. Mohamed et al., “Energy efficiency in cloud computing,” Int. J. Mach. Learn. Comput., vol. 9, no. 1, pp. 40–45, 2019.
14. C. Chen et al., “Reinforcement learning for energy management in buildings: A survey,” Appl. Energy, vol. 280, p. 115000, 2020.
15. S. Ruelens et al., “Reinforcement learning applied to an electric water heater: From theory to practice,” IEEE Trans. Smart Grid, vol. 9, no. 4, pp. 3792–3800, 2018.
16. N. R. Rizwan et al., “Federated learning for smart home energy systems,” IEEE Access, vol. 9, pp. 18023–18034, 2021.
17. S. K. Sharma et al., “Edge AI for smart energy management: Opportunities and challenges,” IEEE Internet Things J., vol. 9, no. 5, pp. 3600–3611, 2022.
18. M. Tjoa and C. Guan, “A survey on explainable artificial intelligence (XAI): Toward medical XAI,” IEEE Trans. Neural Netw. Learn. Syst., vol. 32, no. 11, pp. 4793–4813, 2021.
19. A. Parisio, E. Rikos, and L. Glielmo, “A model predictive control approach to microgrid operation optimization,” IEEE Trans. Control Syst. Technol., vol. 22, no. 5, pp. 1813–1827, 2014.
20. T. Weise et al., “Multi-objective optimization for smart energy systems,” Energies, vol. 13, no. 9, p. 2245, 2020.
21. F. Zantalis et al., “A review of machine learning and IoT in smart transportation,” Future Internet, vol. 11, no. 4, p. 94, 2019.

Issue