Abstract

The scheduling and distribution of tasks is one of the biggest problems with cloud computing, a platform that is becoming more and more popular for everyday use and financial applications. However, one of the main problems in the financial segment remains to be cloud security. Several studies have demonstrated that the financial cloud load balancing system manages the arrangement of n tasks in the process flow on cloud devices, which is critical to the effectiveness of the system. To research load balancing and dynamic task prioritization in financial cloud systems, a novel adaptive weighted round robin based versatile random forest (AWRR-VRF) strategy was suggested in this research. The suggested strategy uses the versatile random forest (VRF) method for dynamic task prioritization depending on security requirements and the adaptive weighted round robin (AWRR) approach for effective load balancing in the financial cloud. To categorize the task-oriented priority of requests and enable efficient task performance, the VRF is implemented based on user behavior patterns. Based on the suggested methodology, this research is carried out using the Python program and performance is examined in terms of CPU utilization (0.0100), energy consumption (62.675), task prioritization (77,600) and optimized memory usage (5102.50) measures. Task security is enhanced to minimize security threats and maximize the protection of financial data. By using the experimental assessment, this research determined that the suggested AWRR-VRF technique maximizes the financial cloud systems security and performance components.