As more people seek ways to improve their homes and workplaces while reducing energy consumption, smart home systems are becoming increasingly prevalent. Unfortunately, the complexity and "black-box" nature of these systems made it difficult to deploy AI-enabled decision-making simulations, raising issues with explainability, confidence, transparency, responsiveness, and fairness. Explainable Artificial Intelligence (XAI), a rapidly developing discipline, addresses these problems by offering justifications for various decisions and behaviors of the systems. This research describes a novel method for IoT-based autonomic devices to control energy that combines XAI with Deep Reinforcement Learning (DRL) to achieve significant Home Energy Management System (HEMS) for household cost reductions. The proposed approach leverages XAI's features to improve the accessibility and transparency of DRL agents, helping consumers understand and trust autonomous power management decisions. By optimizing energy usage patterns and adapting to changing environmental conditions, the proposed solution ensures effective energy use while maintaining user comfort. Use in-depth modeling and real-world applications to demonstrate the solution's efficacy, highlighting its potential to reduce energy consumption costs and promote sustainable living. This study sets a new standard for clarity and flexibility in AI-driven smart home systems, paving the way for more reliable and user-friendly IoT software. It is important to note that developing a thermal dynamics model and understanding unidentified variables are not prerequisites for the proposed technique. Results from simulations based on real-world data show the resilience and effectiveness of the recommended strategy.
Prabagaran et al. (Thu,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: