SparkGrid: Blockchain Assisted Secure Query Scheduling and Dynamic Risk Assessment for Live Migration of Services in Apache Spark-Based Grid Environment

Abstract

Grid computing is an emerging technology that enables the heterogeneous collection of data and provision of services to users. Due to the high amount of incoming heterogeneous requests, grid computing needs efficient scheduling to reduce execution time and satisfy service level agreement (SLA) and quality of service (QoS) requirements. For that purpose, we proposed the SprakGrid method to reduce execution time and satisfy SLA, and QoS requirements. The proposed work includes four consecutive phases which are explained as follows, in first we perform user authentication to ensure the legitimacy of the users using the elliptic curve-based chaos theory algorithm which generates a secret key and stores it in the blockchain. In the second we perform query scheduling for resource discovery using the soft actor critic algorithm by considering 3P's parameters which is performed by spark environment that schedules optimal resources based on the service request. Third, we perform a risk assessment and request dropping, in which the risk nodes of workers are evaluated by the master node. To address the resource wastage by attackers, this research dynamically evaluates the risk value using Shannon entropy. Based on the risk assessment the requests are classified into two classes such as normal and malicious. Fourth we perform service live migration, in which the malicious requests are dropped and normal requests are migrated from the source node to the target node using multi-constraints based emperor penguin optimization. Finally, simulation is performed by GridSim and the simulation results demonstrate that the proposed SparkGrid method achieves superior performance compared to other state-of-the-art methods.