Self-Healing Software Architectures in the Cloud: AI-Driven Detection and Recovery Mechanisms

Аннотация

The recent evolution of cloud computing demands that systems are able to self-diagnose and self-heal as well as constantly optimize without human intervention. This paper provides an in-depth review of the self-healing software architectures in cloud computing, focusing on AI-induced detection and recovery methods. The authors talk about how self-healing systems have changed from traditional ideas to modern AI-powered systems and categorize the main types of methods used for synchronization, tracking, and fixing problems in today's cloud services. Based on a systematic review of available literature, we investigate essential issues such as fault detection accuracy, recovery time optimization, and system reliability improvement. The study finds that although much has been achieved in self-healing, the existing approaches are not yet able to efficiently deal with complex fault situations and to reduce the level of service interruption. Our results suggest that the application of large language models updated using machine learning has the potential to deliver up to an 85% increase in the accuracy of fault prediction and a 60% reduction in system downtime as compared to state-of-the-art approaches. Finally, we talk about what future research should focus on, including the necessary understanding and development of new AI models, different system structures, and standard ways to measure how well self-healing cloud systems work. Key words: Self-healing systems, cloud computing, artificial intelligence, fault detection, autonomic computing. 1. Introduction Cloud computing has revolutionized the way software systems are deployed, managed, and maintained due to rapid acceptance. With the development of cloud computing and the increasing complexity and distribution of cloud infrastructures, how to guarantee the reliability and availability of the system has become a crucial problem. Old-school systems maintenance, which is based on people doing everything manually to try and resolve a problem, does not scale and does not work when managing large-scale cloud systems. This requirement has led instead to the development of self-healing software, where the system intelligently finds, diagnoses, and recovers from a fault without human intervention. 1.1 Emergence of Autonomic Computing The notion of autonomic computing was first described by IBM in the early 2000s in reaction to the increasing complexity of IT systems. Kephart and Chess defined autonomic computing systems as those that self-manage themselves given high-level objectives from administrators. The pioneering work laid the four pillars for https://www.academicpublishers.org/journals/index.php/ijdsml 56 A MERICAN ACADEMIC PUBLISHER autonomic systems, namely, self-configuration, self-optimization, self-healing, and self-protection. This transformation from early ideas of autonomic computing to today’s AI-based self-healing systems is an important jump, thanks to advancements in ML algorithms, growing computational capabilities, and big data availability for training intelligent systems. 1.2 Cloud Computing Paradigm and Self-Healing Requirements Cloud computing environments introduce new requirements for system reliability mechanisms, which arise from specific characteristics such as high distribution, adaptive resource allocation, and multi-tenancy. The elasticity and scalability dimensions of cloud systems further complicate the failure detection and recovery procedures. Figure 1: Cloud Computing Paradigm and Self-Healing Requirements Next-generation cloud infrastructures should be able to deal with different types of failures—hardware failures, software bugs, network splits, and performance drops—while still meeting SLAs and preferably providing a high quality of service to end users. The utilization of AI in self-healing systems has become an encouraging way to overcome these problems and deal with how AI is used in predictive maintenance, intelligent fault patterns, and automatic recovery policies. 1.3 AI-based approaches on Self-Healing Systems Recent advances in the integration of artificial intelligence methods to self-repair systems have transformed the discipline, permitting more advanced detection and recovery techniques. Machine learning methods have been https://www.academicpublishers.org/journals/index.php/ijdsml 57 A MERICAN ACADEMIC PUBLISHER shown to be effective in analyzing telemetry data to forecast the next failure, and deep learning models are capable of catching complicated fault patterns not captured by classical rule-based systems. Figure 2: AI-based approaches on Self-Healing Systems Recent advances in large language models have helped open new opportunities for natural language-based system diagnostics and automated troubleshooting actions. Such AI-enabled strategies have shown enormous potential for increasing system reliability, shortening recovery times, and improving the system performance in comparison with traditional self-healing