Towards Quantum Computing Algorithms for Datacenter Workload Predictions

Datacenters depend on intelligent management of underlying CPU, memory, network, and storage resources. A variety of techniques such as load balancing, load consolidation, and remote memory allocation rely on successful prediction of the workloads within the cloud. Recent promising developments in quantum computing seem ideal for performing this overhead work. As a step towards this goal, this paper proposes a host resource usage prediction approach, based on a complex-valued neural network. The algorithm can be further modified in the future to be applicable to quantum computing environments. A proof-of-concept is evaluated on real world load traces from a grid. The algorithm is compared against some current state-of-the-art host-load prediction algorithms to demonstrate its accuracy.