Autonomic computing refers to the capability of the software system to monitor environmental changes by itself. The primary objective of the proposed approach is to identify the quality of software components concerning complexity metrics. In this article, extreme learning machine (ELM) supported multiobjective gray wolf optimization (MOGWO) is proposed to predict the quality products. The proposed methodology considers four component-based system metrics such as failure response time, throughput rate, interface surface consistency (ISC) and bounded interface complexity metrics (BICM) to resolve the complexity issues. The ELM is utilized in this article to conduct a prediction in the complexity metrics on the context-awareness self-adaptive autonomous system application. MOGWO is then utilized to optimize the cost metric.The evaluation results are compared with the existing approaches such as ELM, ANN, and ANN-GWO. From the simulations, the overall accuracy rate of the prediction model is obtained to be 95%.
K E Y W O R D Sautonomous computing system, complexity metrics, extreme learning machine, failure response time, multiobjective gray wolf optimization algorithm, throughput rate
INTRODUCTIONAutomatic computing is a fundamental component, and its main goal is to develop and design the system based on the system environment. 1,2 The self-managing systems are aimed at a vision that is to be adapt, optimize, evolved, and manage, or another system with the avoidance of human intervention. 3,4 The characteristic feature of automatic computing is divided into four main categories: self-configuration, self-optimization, self-protection, and self-healing. 3 The adaptation mechanism of an autonomic system component dynamically adapts to any changes arising in its environments using the instructions is called self-configuration. 5 The mechanism of fixing the malfunctions that occurred in the autonomic system is called self-healing. 6The tuning of system resources to reduce the workload of an autonomic system is called self-optimization. 7 To prevent the autonomic system from malicious attacks or the danger of crashing is known as self-protection. 8 Autonomic computing refers to a computing environment capable of managing itself and can adapt to changes dynamically under business policies. 9 This system with a control loop monitors itself and its environment analyses the situation and takes actions to change either the environment or its behavior. 9 However, unless deployment is carried out, interaction is performed by the system, such as development, operations, management, and regulation. 10 Improving system abilities is the main aim of the autonomic computing system (ACS). 11 Designing and implementing ACSs dynamically support self-managing operations, but different system quality metrics are affected, and performance and security requirements need to be satisfied. 12,13