AI-driven smart home appliance optimization: A systematic review
APPLIED ENERGY, cilt.426, 2026 (SCI-Expanded, Scopus)
- Yayın Türü: Makale / Derleme
- Cilt numarası: 426
- Basım Tarihi: 2026
- Doi Numarası: 10.1016/j.apenergy.2026.128665
- Dergi Adı: APPLIED ENERGY
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Compendex, Environment Index, Geobase, INSPEC, Public Affairs Index, Academic Search Ultimate (EBSCO), Engineering Source (EBSCO)
- Orta Doğu Teknik Üniversitesi Kuzey Kıbrıs Kampüsü Adresli: Evet
Özet
Smart homes are widely recognized as a vital component of sustainable energy systems due to their potential to reduce energy consumption and peak demand. Artificial intelligence plays a crucial role in this process by optimizing smart appliances in homes using data obtained from smart meters and IoT devices. Unlike existing surveys that primarily focus on broad smart grid optimization frameworks or standalone prediction approaches, this work specifically concentrates on AI-based smart home appliance optimization and provides a unified perspective by integrating prediction, control, and user-centric energy management across multiple application domains. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines, this study presents a systematic review of state-of-the-art AI-driven optimization techniques for smart appliances in smart homes. The survey highlights how AI-based approaches can effectively manage dynamic pricing schemes, renewable energy integration, and evolving consumer behavior while maintaining user comfort and energy efficiency. The review covers various important application domains of smart homes such as heating, ventilation, air conditioning and lighting control, smart appliance scheduling, load forecasting, non-intrusive load monitoring, and demand response. Additionally, this paper covers AI/ML/DL models used in smart homes, data used in AI models, publicly available datasets, data preprocessing methodologies and performance metrics. Moreover, the study identifies important challenges associated with smart homes and AI-based optimization models such as scalability issues, data diversity and future research directions.