Featured

Research publications

Deep learning for intelligent demand response and smart grids: A comprehensive survey

Electricity transmission faces challenges addressed by smart grids and demand response, generating vast data from various sources. This paper surveys the application of deep learning (DL) in smart grids, covering electric load forecasting, state estimation, energy theft detection, and more, while highlighting future research directions

Federated Learning for the Healthcare Metaverse: Concepts, Applications, Challenges, and Future Directions

Technological advancements and the Metaverse are transforming healthcare by integrating AI, IoT, and other emerging technologies to create intelligent systems. This survey explores the potential of Federated Learning (FL) in the healthcare Metaverse, addressing privacy, interoperability, and data management challenges, and highlighting applications like medical diagnosis and patient monitoring.

BENIGREEN: Blockchain-Based Energy-Efficient Privacy-Preserving Scheme for Green IoT

Green IoT enhances energy efficiency in connecting people, processes, and things, but current research limits decentralized management like blockchain. This article introduces BENIGREEN, a blockchain-based, privacy-preserving framework for smart cities, improving energy-efficient cluster head selection and secure data transmission.

Smart window technology and its potential for net-zero buildings: A review

Building energy consumption, particularly from HVAC systems, surpasses that of transportation and industry combined, driving interest in smart window technology to reduce this usage. This review explores the potential of multifunctional smart windows incorporating electrochromic, thermochromic, photochromic, and supercapacitor technologies to enhance energy efficiency and meet consumer demands in green buildings.

ASXC2 Approach: A Service-X Cost Optimization Strategy Based on Edge Orchestration for IoT

Edge computing faces challenges in service reliability due to limited resources. To address this, we propose a 2-step adaptive service-X cost consolidation (ASXC2) approach using the node-centric Lyapunov method and distributed Markov mechanism, significantly enhancing service offloading efficiency and reliability in computation-intensive applications.