Resource Allocation Strategies for Edge and Fog Computing in the Cloud Continuum

The advent of edge and fog computing has revolutionized the traditional cloud computing landscape by enabling data processing closer to the data source. This paradigm shift addresses limitations such as high latency and bandwidth consumption inherent in centralized cloud models. Effective resource allocation in this context is crucial for optimizing performance and ensuring efficient operation across the cloud continuum, which integrates cloud, fog, and edge computing layers. This paper provides a comprehensive review of current resource allocation strategies employed in edge and fog computing, including heuristic-based methods, machine learning approaches, game theory, auction mechanisms, and Quality of Service (QoS)-aware techniques. Each method's strengths and weaknesses are analysed, highlighting the challenges of complexity, scalability, data requirements, and adaptability. Additionally, this review identifies future research directions that promise to enhance resource allocation efficiency. Key areas of focus include the integration of advanced artificial intelligence and edge intelligence, the use of federated learning for collaborative resource optimization, the application of blockchain technology for secure and transparent resource management, and the development of energy-efficient allocation strategies. The potential of hybrid approaches that combine multiple resource allocation strategies is also explored. By addressing these challenges and leveraging emerging technologies, future research can significantly improve resource allocation in the cloud continuum, ensuring robust, scalable, and efficient computing environments capable of meeting the demands of diverse and dynamic applications. This review aims to guide researchers and practitioners in developing innovative solutions for resource allocation in edge and fog computing, driving the evolution of the cloud continuum.