Game-Theoretic Deep Reinforcement Learning to Minimize Carbon Emissions and Energy Costs for AI Inference Workloads in Geo-Distributed Data Centers

arXiv:2404.01459v1 Announce Type: cross
Abstract: Data centers are increasingly using more energy due to the rise in Artificial Intelligence (AI) workloads, which negatively impacts the environment and raises operational costs. Reducing operating expenses and carbon emissions while maintaining performance in data centers is a challenging problem. This work introduces a unique approach combining Game Theory (GT) and Deep Reinforcement Learning (DRL) for optimizing the distribution of AI inference workloads in geo-distributed data centers to reduce carbon emissions and cloud operating …

abstract artificial artificial intelligence arxiv carbon costs cs.ai cs.dc cs.lg data data centers distributed distributed data emissions energy energy costs environment game geo impacts inference intelligence performance raises reinforcement reinforcement learning the environment type workloads