Today, most innovative operators and building managers have a limited ability to analyze energy consumption and to use insights from that analysis to optimize energy. Energy service companies (ESCOs) – the commercial and non-profit entities that develop and implement energy solutions – and the customers they serve are exploring how emerging technologies can more effectively manage energy consumption to reduce costs, mitigate risk and address environmental concerns. Specifically, interest is growing in how Internet of Things (IoT) communications can be leveraged to improve energy management. IoT is a powerful technology that enables intelligent wireless communications, mobile computing, and smart applications to enhance the quality of human life. By deploying wireless communications and mobile computing, connected assets and devices that continuously collect, analyze, and share data can deliver deep insights into how large facilities, factories, utilities, and embedded and computing systems consume energy.

With the rapid development of IoT systems and intelligent wireless communications, energy-efficient mobile computing is emerging as an attractive solution for processing the data of IoT devices. In this procedure, data transmission is performed by IoT devices based on intermediate computing nodes, as well as the physical servers in cloud data centers. There are challenges in this, however, due to the energy-saving limitations, service heterogeneity, dynamic nature, and unpredictability of IoT environments, but machine learning methods offer a promising avenue to enhance the accuracy and performance of IoT infrastructure to help predict energy consumption and power generation in electronic circuits and computing systems. Due to the above-mentioned critical points, energy-aware data transmission, load balancing, routing, service selection, and composition issues can be introduced as the main challenges to be considered in IoT environments.

Despite the importance of energy-efficient electronic circuits and computing systems issues, This Special Issue invites researchers to publish intelligent trends to help solve new challenges in intelligent services and system management problems, with emphasis on the importance of energy-efficient electronic circuits and computing systems issues. We also are interested in review articles that present the state-of-the-art of this topic, showing recent major advances and discoveries, significant gaps in research, and future issues.

Potential topics include but are not limited to the following:

• New methods for artificial neural networks and multilayer perceptron (MLP) techniques and for established intelligent architectures
• Classification methods for non-established models, such as support vector machines (SVM), fuzzy models, or deep clustering techniques
• Complexity reduction and transformation of deep learning models
• Interpretability aspects for a better understanding of machine learning models
• Reasoning of input-output behavior of machine learning models (toward understanding their predictions)
• Deep learning classifiers combined with active learning
• Evolutionary-based optimization
• Hybrid learning schemes (deterministic, heuristics-based, or mimetic) and transfer learning for deep learning systems
• Incremental learning methods for self-adaptive deep learning models
• Evolving techniques for deep learning systems, such as expanding and pruning layers
• Energy-aware communication theory and network management in IoT
• Energy efficiency in microwave, radio, and terahertz circuit systems and devices
• Energy consumption in embedded and wireless communications
• Energy-aware service offloading and placement in IoT devices
• Energy efficiency in other applications of IoT, for example, healthcare technologies
• New energy harvesting approaches in cognitive radio and wireless communications
• Energy management of industrial mobile services in IoT