Cloud computing offers flexible, interactive, and observable access to shared resources on the Internet. It frees users from the requirements of managing computing on their hardware. It enables users to not only store their data and computing over the internet but also can access it whenever and wherever it is required. The frequent use of smart devices has helped cloud computing to realize the need for its rapid growth. As more users are adapting to the cloud environment, the focus has been placed on load balancing. Load balancing allocates tasks or resources to different devices. In cloud computing, and load balancing has played a major role in the efficient usage of resources for the highest performance. This requirement results in the development of algorithms that can optimally assign resources while managing load and improving quality of service (QoS). This paper provides a survey of load balancing algorithms inspired by swarm intelligence (SI). The algorithms considered in the discussion are Genetic Algorithm, BAT Algorithm, Ant Colony, Grey Wolf, Artificial Bee Colony, Particle Swarm, Whale, Social Spider, Dragonfly, and Raven roosting Optimization. An analysis of the main objectives, area of applications, and targeted issues of each algorithm (with advancements) is presented. In addition, performance analysis has been performed based on average response time, data center processing time, and other quality parameters.

This chapter presents analysis on death rate predictions due to corona virus. Staring in the Hubie province of China in early December 2019, the novel virus (also known as Covid-19) is caused by severe acute respiratory syndrome Corona-virus2 (SARS-Cov2). It was declared a global pandemic by the World Health Organization on 11 March 2020. Its consequences have affected almost the entire world. It affected millions of lives in different countries with Around 13,000 deaths and approximately 2.8 million new diagnoses were confirmed globally in the weekend of 9–15 January 2023. In addition, the Covid-19 also caused damage to economies. It impacted developing countries as well. It is very difficult for developing countries to manage because of limited resources. In this chapter, autoregressive integrated moving average (ARIMA) is used for forecasting the future of Covid-19 cases and deaths. ARIMA is used because of its versatility in different applications, such as tourism, demand management, banking, stock market, aviation, etc. Data gathered from a renowned compatible source website, Worldometer, has been used to train the model to predict the upcoming cases, upcoming deaths numbers, and total cases. This chapter compares predicted outcomes with the actual values to confirm the performance of the trained model. The data was collected from 15 February 2020 to 26 February 2021. The aim of this chapter is to propose a methodology to predict the cumulative number of related cases and deaths in order to examine and compare forecasting validity of the model whose results may provide an insight to organizations, especially governments, to investigate and review policies regarding Covid-19.