Learning-Aided Heuristics Design for Storage System

TL;DR

This paper introduces a learning-aided heuristic design approach that leverages deep reinforcement learning to generate interpretable, human-readable strategies for storage system resource allocation, outperforming traditional methods.

Contribution

The paper presents a novel method combining deep reinforcement learning with heuristic design to produce transparent strategies for storage systems.

Findings

Outperforms default storage resource allocation settings

Generates human-readable strategies from DRL agents

Achieves better performance than handcrafted strategies

Abstract

Computer systems such as storage systems normally require transparent white-box algorithms that are interpretable for human experts. In this work, we propose a learning-aided heuristic design method, which automatically generates human-readable strategies from Deep Reinforcement Learning (DRL) agents. This method benefits from the power of deep learning but avoids the shortcoming of its black-box property. Besides the white-box advantage, experiments in our storage productions resource allocation scenario also show that this solution outperforms the systems default settings and the elaborately handcrafted strategy by human experts.