JORA: Blockchain-based efficient joint computing offloading and resource allocation for edge video streaming systems

Abstract

Edge computing has been widely applied in video streaming systems, aiming to provide low-latency video streaming services. However, limited resources and a lack of incentivization affect the performance of edge video streaming systems. In this paper, we propose an efficient Joint computing Offloading and Resource Allocation (JORA) method for blockchain-supported edge video streaming systems (BEVS). Specifically, we develop a novel incentive mechanism based on the blockchain smart contract to enable automatic incentivization. Meanwhile, we customize a system prototype of BEVS on Amazon EC2 using Apache Storm. Preliminary experiments with the customized prototype reveal the coupling impacts of the offloading mode, the allocation scheme, and video redundancy on system performance and resource demand. Motivated by the results, we formulate joint computing offloading, resource allocation, and video adaptive compression as an optimization problem. We transform the original problem into a convex problem and a mixed-integer programming problem (MIP). We then develop an algorithm based on the generalized Benders decomposition (GBD) to solve the original problem in an iterative way. Extensive experiments demonstrate that the proposed scheme achieves full resource utilization and an effective trade-off between energy consumption and accuracy.