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

• URL: http://arxiv.org/abs/2404.01459v1
• Date: Mon, 1 Apr 2024 20:13:28 GMT
• Title: Game-Theoretic Deep Reinforcement Learning to Minimize Carbon Emissions and Energy Costs for AI Inference Workloads in Geo-Distributed Data Centers
• Authors: Ninad Hogade, Sudeep Pasricha,
• Abstract summary: 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. The proposed technique integrates the principles of non-cooperative Game Theory into a DRL framework, enabling data centers to make intelligent decisions regarding workload allocation.
• Score: 3.3379026542599934
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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 (energy + data transfer) costs. The proposed technique integrates the principles of non-cooperative Game Theory into a DRL framework, enabling data centers to make intelligent decisions regarding workload allocation while considering the heterogeneity of hardware resources, the dynamic nature of electricity prices, inter-data center data transfer costs, and carbon footprints. We conducted extensive experiments comparing our game-theoretic DRL (GT-DRL) approach with current DRL-based and other optimization techniques. The results demonstrate that our strategy outperforms the state-of-the-art in reducing carbon emissions and minimizing cloud operating costs without compromising computational performance. This work has significant implications for achieving sustainability and cost-efficiency in data centers handling AI inference workloads across diverse geographic locations.

Related papers

• D5RL: Diverse Datasets for Data-Driven Deep Reinforcement Learning [99.33607114541861]
  We propose a new benchmark for offline RL that focuses on realistic simulations of robotic manipulation and locomotion environments. Our proposed benchmark covers state-based and image-based domains, and supports both offline RL and online fine-tuning evaluation.
  arXiv  Detail & Related papers  (2024-08-15T22:27:00Z)
• Beyond Efficiency: Scaling AI Sustainably [4.711003829305544]
  Modern AI applications have driven ever-increasing demands in computing. This paper characterizes the carbon impact of AI, including both operational carbon emissions from training and inference as well as embodied carbon emissions from hardware manufacturing.
  arXiv  Detail & Related papers  (2024-06-08T00:07:16Z)
• Spatio-temporal load shifting for truly clean computing [0.5857582826810999]
  We study the impact of shifting computing jobs and associated power loads both in time and between locations. We isolate three signals relevant for informed use of loadblity. The costs of 24/7 CFE are reduced by 1.29$pm$0.07 EUR/MWh for every additional percentage of flexible load.
  arXiv  Detail & Related papers  (2024-03-26T13:36:42Z)
• Hybrid Reinforcement Learning for Optimizing Pump Sustainability in Real-World Water Distribution Networks [55.591662978280894]
  This article addresses the pump-scheduling optimization problem to enhance real-time control of real-world water distribution networks (WDNs) Our primary objectives are to adhere to physical operational constraints while reducing energy consumption and operational costs. Traditional optimization techniques, such as evolution-based and genetic algorithms, often fall short due to their lack of convergence guarantees.
  arXiv  Detail & Related papers  (2023-10-13T21:26:16Z)
• SHIELD: Sustainable Hybrid Evolutionary Learning Framework for Carbon, Wastewater, and Energy-Aware Data Center Management [2.9699290794642366]
  Geo-distributed data centers (GDDCs) have a significant associated environmental impact. This paper proposes a novel framework to co-optimize carbon emissions, water footprint, and energy costs of GDDCs.
  arXiv  Detail & Related papers  (2023-08-24T21:11:55Z)
• Sustainable AIGC Workload Scheduling of Geo-Distributed Data Centers: A Multi-Agent Reinforcement Learning Approach [48.18355658448509]
  Recent breakthroughs in generative artificial intelligence have triggered a surge in demand for machine learning training, which poses significant cost burdens and environmental challenges due to its substantial energy consumption. Scheduling training jobs among geographically distributed cloud data centers unveils the opportunity to optimize the usage of computing capacity powered by inexpensive and low-carbon energy. We propose an algorithm based on multi-agent reinforcement learning and actor-critic methods to learn the optimal collaborative scheduling strategy through interacting with a cloud system built with real-life workload patterns, energy prices, and carbon intensities.
  arXiv  Detail & Related papers  (2023-04-17T02:12:30Z)
• Measuring the Carbon Intensity of AI in Cloud Instances [91.28501520271972]
  We provide a framework for measuring software carbon intensity, and propose to measure operational carbon emissions. We evaluate a suite of approaches for reducing emissions on the Microsoft Azure cloud compute platform.
  arXiv  Detail & Related papers  (2022-06-10T17:04:04Z)
• ANDREAS: Artificial intelligence traiNing scheDuler foR accElerAted resource clusterS [1.798617052102518]
  We propose ANDREAS, an advanced scheduling solution to maximize performance and minimize Data Centers operational costs. experiments show that we can achieve a cost reduction between 30 and 62% on average with respect to first-principle methods.
  arXiv  Detail & Related papers  (2021-05-11T14:36:19Z)
• A Framework for Energy and Carbon Footprint Analysis of Distributed and Federated Edge Learning [48.63610479916003]
  This article breaks down and analyzes the main factors that influence the environmental footprint of distributed learning policies. It models both vanilla and decentralized FL policies driven by consensus. Results show that FL allows remarkable end-to-end energy savings (30%-40%) for wireless systems characterized by low bit/Joule efficiency.
  arXiv  Detail & Related papers  (2021-03-18T16:04:42Z)
• NeurOpt: Neural network based optimization for building energy management and climate control [58.06411999767069]
  We propose a data-driven control algorithm based on neural networks to reduce this cost of model identification. We validate our learning and control algorithms on a two-story building with ten independently controlled zones, located in Italy.
  arXiv  Detail & Related papers  (2020-01-22T00:51:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.