Evolutionary algorithms (EAs) are important optimization and search techniques that have been developed in recent years. EAs are a subset of evolutionary computations (EC) and belong to a set of modern heuristics-based search methods. Due to the resilient nature and robust behavior inherent in evolutionary computation, EAs are efficient problem-solving methods for widely used global optimization problems. Evolutionary computation has enjoyed tremendous growth in recent years, with much research into both its theoretical foundations and industrial applications. The scope of EAs has gone far beyond binary string optimization using simple genetic algorithms, and EAs are being increasingly applied to obtain optimal or near-optimal solutions to many complex real-world optimization problems. One prime example of this is in fifth-generation mobile communication networks (5G), where standardization activities and deployment of 5G networks are growing rapidly.

Federated learning (FL) is a distributed platform of artificial intelligence (AI)-based approaches that enhances a smart system's connectivity with increased network capacity, quality of service, network availability, and user experience. Advanced mathematical tools in the field of federated learning applied to wireless communications have many potential applications in telecommunications, bioinformatics, healthcare, the Internet of Things (IoT), social networks, and manufacturing. This emerging FL-based wireless communication improves automation and optimized transmission for next-generation data networks. With the low latency, high transmission rate, and high reliability provided by fifth-generation mobile communication networks, many applications requiring ultra-low latency and high reliability (uRLLC) have become subjects of increasing attention. Among these issues, the critical application is the Internet of Vehicles (IoV). To maintain the safety of vehicle drivers and road conditions, the IoV can transmit through sensors or infrastructure to maintain communication quality and transmission. However, because 5G uses millimeter waves for transmission, a large number of base stations (BS) or lightweight infrastructure will need to be built in 5G, which will make the overall environment more complex than 4G. The lightweight infrastructure also has to be considered together.

This Special Issue solicits high-quality original research papers that use the application of federated learning to optimize next-generation networks with evolutionary algorithms. We hope to identify and discuss new techniques and concepts, innovations, standards, potential use cases, open research problems, technical challenges, and promising solution methods. We welcome both original research and review articles.

Potential topics include but are not limited to the following:

• Blockchain and IoT applications in mobile networks using FL
• Heuristic algorithms for millimeter-wave technologies using FL
• Heuristic algorithms for ultra-dense cell communication using FL
• Heuristic algorithms for physical layer heterogeneous networks using FL
• Heuristic algorithms for unmanned aerial vehicles (UAVs) using FL
• Applications of evolutionary algorithm-based FL for wireless communication technologies
• Edge/IoT-based mobile networks using FL
• Multi-objective optimization in wireless communication networks using FL
• Handover management mechanism heuristic algorithms using FL
• Location prediction combined with heuristic algorithms using FL
• Delay time formulation in wireless communication networks with heuristic algorithms
• Energy-efficient wireless communication networks with heuristic algorithms using FL