An Iterative Feedback Mechanism for Auto-Optimizing Software Resource Allocation in Multi-Tier Web Systems

Software resource allocation has a significant impact on the quality of service and the performance of multi-tier web systems. It poses a great challenge to compute the allocation of different software resources in order to meet performance requirements under dynamic workloads conditions. To this end, this paper proposes an iterative feedback mechanism to optimize software resource allocation of multi-tier web systems. Specifically, we propose a Q-learning network-based approach for performance prediction. The predictor involves a deep Q-learning network for capturing the dynamics of online software resource allocation, and then computing the current optimal policy. We implement the approach in the RUBiS benchmark system, and the experimental results demonstrate its significant advantages.