AI-based Fog and Edge Computing: A Systematic Review, Taxonomy and Future Directions (2212.04645v1)

Abstract: Resource management in computing is a very challenging problem that involves making sequential decisions. Resource limitations, resource heterogeneity, dynamic and diverse nature of workload, and the unpredictability of fog/edge computing environments have made resource management even more challenging to be considered in the fog landscape. Recently AI and Machine Learning (ML) based solutions are adopted to solve this problem. AI/ML methods with the capability to make sequential decisions like reinforcement learning seem most promising for these type of problems. But these algorithms come with their own challenges such as high variance, explainability, and online training. The continuously changing fog/edge environment dynamics require solutions that learn online, adopting changing computing environment. In this paper, we used standard review methodology to conduct this Systematic Literature Review (SLR) to analyze the role of AI/ML algorithms and the challenges in the applicability of these algorithms for resource management in fog/edge computing environments. Further, various machine learning, deep learning and reinforcement learning techniques for edge AI management have been discussed. Furthermore, we have presented the background and current status of AI/ML-based Fog/Edge Computing. Moreover, a taxonomy of AI/ML-based resource management techniques for fog/edge computing has been proposed and compared the existing techniques based on the proposed taxonomy. Finally, open challenges and promising future research directions have been identified and discussed in the area of AI/ML-based fog/edge computing.

AI-Based Fog and Edge Computing: A Systematic Review, Taxonomy, and Future Directions

The paper "AI-based Fog and Edge Computing: A Systematic Review, Taxonomy and Future Directions" by Sundas Iftikhar et al. provides a comprehensive examination of the integration of AI and Machine Learning (ML) within the fog and edge computing paradigms. With the rise in IoT applications and the limitations of traditional cloud computing due to latency and bandwidth issues, fog and edge computing have emerged as vital alternatives. These computing models bring computational resources closer to end-users, thereby offering significant advantages for real-time and latency-sensitive applications.

The authors address the complex issue of resource management in these environments, a field made more challenging by heterogeneous resources and dynamic workloads. The unpredictability and scalability of fog/edge systems necessitate advanced resource management strategies, including provisioning, scheduling, and task offloading. The paper focuses on AI and ML techniques, particularly those capable of making sequential decisions, such as reinforcement learning, to handle these resource management tasks effectively.

The systematic review conducted by the authors is grounded in a rigorous methodology as per "Centre for Reviews and Dissemination (CRD) guidelines." It presents a taxonomy of existing AI/ML techniques applied to fog/edge computing and assesses their efficacy in resource management. The taxonomy classifies methods into categories like supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning. Special emphasis is given to the practical applications of these methods and their implications on resource efficiency, load balancing, energy consumption, and SLA assurance.

In terms of resource management, the paper highlights key processes such as task offloading, application placement, and load balancing. Each process is evaluated based on its ability to optimize the use of limited computational resources while ensuring QoS requirements are met. The review also touches on the open challenges and potential research directions in integrating AI/ML with fog/edge computing, such as handling resource heterogeneity and ensuring security amidst distributed AI-driven resource management solutions.

A significant contribution of the paper is its identification of open challenges and future research directions. These include the need for adaptable and resilient resource management strategies, enhanced security protocols specific to fog and edge environments, and the integration of AI models tailored for real-time decision-making processes. The paper calls for continued exploration into the intersection of AI technologies and edge infrastructure, emphasizing the need for novel solutions that capitalize on the strengths of both domains.

In conclusion, this paper provides a valuable resource for researchers and practitioners in the field, summarizing existing work and identifying future avenues for innovation in AI-driven fog and edge computing. By outlining a clear taxonomy and reviewing cutting-edge approaches to resource management, the authors equip others with the knowledge to advance the efficacy and adoption of intelligent systems in distributed computing environments.