The residential energy sector contributes substantially to global energy-related emissions. Effective energy management requires an understanding occupant behavior through activity detection and habit identification. Recent advances in artificial intelligence (AI) and machine learning (ML) enable the automatic detection of user activities and prediction of energy needs based on historical consumption data. Non-intrusive load monitoring (NILM) facilitates device-level disaggregation without additional sensors, supporting demand forecasting and behavior-aware control in Home Energy Management Systems (HEMSs). This review synthesizes various AI and ML approaches for detecting user activities and energy habits in HEMSs from 2020 to 2025. The analyses revealed that deep learning (DL) models, with their ability to capture complex temporal and nonlinear patterns in multisensor data, achieve superior accuracy in activity detection and load forecasting, with occupancy detection reaching 95–99% accuracy. Hybrid systems combining neural networks and optimization algorithms demonstrate enhanced robustness, but challenges remain in limited cross-building generalization, insufficient interpretability of deep models, and the absence of dataset standardized. Future work should prioritize lightweight, explainable edge-ready models, federated learning, and integration with digital twins and control systems. It should also extend energy optimization toward occupant wellbeing and grid flexibility, using standardized protocols and open datasets for ensuring trustworthy and sustainability.

The increasing complexity of residential energy systems, driven by rising electricity demand, renewable energy integration, and dynamic pricing mechanisms, has intensified the need for intelligent load scheduling within Home Energy Management Systems (HEMSs). This paper presents a comprehensive literature review of optimization algorithms applied to residential load scheduling, based on an analysis of 78 peer-reviewed studies published between 2020 and 2025. The analysis reveals a clear shift from conventional deterministic optimization toward adaptive and data-driven approaches capable of operating in uncertain and dynamic environments. Metaheuristic methods are widely used for solving complex scheduling problems, while Machine Learning and Deep Learning (DL) techniques primarily support forecasting tasks related to energy demand and renewable generation. Reinforcement Learning (RL) and Deep Reinforcement Learning (DRL) approaches enable autonomous real-time decision-making, although challenges related to scalability, computational cost, and practical deployment remain unresolved. The review identifies hybrid architectures that combine forecasting, optimization, and control mechanisms as the most promising direction for future HEMS development. Finally, the paper highlights key research gaps, including limited real-world validation, insufficient consideration of physical infrastructure constraints, and the need for scalable distributed control frameworks for future smart grids and energy communities.

The paper describes the concept of Human Centric Lighting (HCL, or Human Centric Lighting), and the application of modular lighting according to this concept as part of a building automation system. The process of designing and prototyping luminaires was discussed, taking into account advanced features that adapt the lighting to the ambient conditions in the room and the current needs of the users. The work demonstrated the potential of moving light sources to precisely illuminate specific areas and the importance of control algorithms to fully realize this potential. A three-layer system architecture (object, local control and supervisory) was presented, allowing parameters to be adjusted according to user preferences and optimizing operation according to criteria such as energy efficiency. The theoretical foundations based on the analysis of scientific articles and the actual technical process of building the lighting module, as well as the results of photometric tests of module prototypes are presented in the paper.