Energy aware resource allocation via MS-SLnO in cloud data center

Cloud computing has evolved as a cutting-edge platform of consumer and business opportunities. It also allows the users to view apps and data from any place. Companies will borrow services from the cloud for storage and other operational tasks, which dramatically reduces the technology costs. Also, it gives the benefits of company-wide platform accessibility built on the pay-as-you-go model. There is no need of purchasing specific product licenses. However, resource allocation becomes the most important pitfalls in cloud computing. This paper aims to implement a new optimization-assisted resource allocation approach that maximizes sales with minimized costs. Prior to this allocation, the workload (allocated tasks) clustering is performed using an advanced k-means clustering with the Lion with Advanced Mating Process (LAAM) that fine-tunes the centroid. The clustering of tasks is undergone depending on the QoS (trust) and task time. Finally, a hybrid algorithm termed as Moth Search Adapted Sealion optimization (MS-SLnO) for optimal resource allocation under the consideration of Power Usage Effectiveness (PUE), CPU usage, and execution time. Furthermore, the suggested work's performance was compared to that of the latest systems in regard to energy use, execution time, and resource usage.