Financial service composition with various privacy levels in multiple cloud environment

This paper focuses on the financial service composition problem in a multi-cloud environment while ensuring varying levels of privacy. In today's digital era, financial institutions increasingly rely on cloud computing to deliver a wide range of services, necessitating the efficient composition of services across multiple cloud platforms. However, the integration of these services poses significant challenges, particularly in managing privacy levels to protect sensitive financial data. To solve these challenges, a novel approach for financial service composition based on Quaternion Genetic Algorithms (QGA) is proposed. Our method optimizes the scheduling of cloud-based services to minimize execution time, energy consumption, and the file size transferred between clouds, while meeting specified privacy requirements. Simulations show that our proposed method can dynamically adapt to varying privacy constraints and achieve an optimal balance between other targets and privacy requirements.