Genetic Algorithm-Based Data Allocation in Multi Media Using Cloud Computing

The recent growth of Internet-of-Things (IoT) applications using cloud computing has been amazing. One of the advancements is heterogeneous cloud computing, which has made it possible to use the cloud for a range of infrastructure solutions, including multimedia big data. The optimizations of on-premise heterogeneous memory have been the subject of several past studies. However, the performance and financial limits brought on by hardware distributions and manipulative techniques are placing restrictions on the heterogeneous cloud memory. It is an NP-hard combinatorial issue to distribute data jobs across dispersed memory with different capacities. In order to provide high performance cloud-based heterogeneous memory service offerings, this study focuses on this problem and suggests a unique solution called Cost-Aware Heterogeneous Cloud Memory Model. It allocates data to the cloud-based memory via genetic programming. In our suggested method, we take into account a number of important elements that have a significant influence on how well Communication expenses, data transfer operating costs, energy performance, and time constraints all play a role in how cloud memories operate. Finally, we put our suggested paradigm to the test via experimental assessments. The trial findings have demonstrated the viability and scalability of our technique as a cost-conscious cloud-based solution.