Fog and edge are new alternatives for scalable and huge computing that are now used worldwide. There can be, however, various performance issues caused by increasing infrastructure in particular locations. In such distributed environments, where different vendors come together to provide services, trust and reliability are crucial issues, where trust is defined by the past performance of the system. Moreover, faults at various levels of infrastructure occurring at random points degrade performance and reliability in the cloud environment. Therefore, there is an urgent need for new research in the field of trustworthy, fault-tolerant, and reliable computing algorithms to improve the performance of fog and edge computing in applications such as smart cities.

Optimization algorithms are also changing with the introduction of machine learning (ML) and deep learning. These evolving future generation algorithms can solve the issues of fault prediction, trust models, and the locating of malicious objects. ML/artificial intelligence (AI) algorithms and hybrid algorithms are considered next-generation solutions to computation-intensive problems and fault prediction. However, existing models in edge and fog computing suffer from fault and trust issues among distributed resources where malicious objects can reduce the reliability of the system. To overcome these drawbacks, new models are required. Fortunately, artificial intelligence and machine learning technology incorporated with existing models may provide a promising way towards next-generation algorithms with predictive methodology, and the integration of AI and ML in fault prediction will result in improved and reliable models.

This Special Issue aims to highlight innovative approaches from the field of optimization in cloud, Internet of Things, and fog computing using artificial intelligence, metaheuristic optimization approaches, or nature-inspired algorithms. This Special Issue is looking for any optimization programming mathematical models related to the performance of systems in distributed environments, and the software models will be responsible for making intelligent decisions considering their past performance and for better forecasting models.

Potential topics include but are not limited to the following:

• Fault prediction models using AI/ ML
• Optimization to evaluate trust
• Trust and fault aware machine learning models
• Reliability prediction in cloud and edge computing
• Fault tolerance and reliability of big data systems
• Fault-tolerant resource optimization models
• Fault-tolerant algorithms for energy efficiency
• Trust aware resource optimization
• Machine learning and nature inspired optimization models for edge computing