TY - JOUR
T1 - EcoVMS
T2 - LLM-Driven Reinforcement Learning for End-to-End Energy-Optimized VM Scheduling
AU - Xu, Xiaojun
AU - Hu, Jingjing
AU - He, Jialing
AU - Yang, Xiuqi
AU - Liu, Zeyang
AU - Chen, Zhuo
AU - Wang, Jiacheng
N1 - Publisher Copyright:
© 2008-2012 IEEE.
PY - 2026/9/1
Y1 - 2026/9/1
N2 - The rapid expansion of the cloud computing ecosystem necessitates scalable and energy-efficient resource management. However, achieving optimal energy efficiency is severely constrained by the complex interplay between computational workloads and thermal dynamics. Traditional data center (DC) scheduling methods typically rely on computationally expensive mechanistic models, such as computational fluid dynamics (CFD), or inefficient algorithm search, which frequently yield suboptimal solutions and struggle to adapt to real-time environments. To address these challenges, we propose an ecology-conservation-optimization virtual machine scheduling (EcoVMS) framework, a data-driven and end-to-end framework for compute-energy co-optimization. At its core, EcoVMS utilizes a latent reward generation enhanced proximal policy optimization (LARGE-PPO) algorithm, which utilizes large language models (LLMs) to analyze runtime telemetry—including central processing unit (CPU) utilization, thermal boundaries, and power consumption, and then utilizes large-scale semantic priors to generate potential reward factors. This mechanism resolves the sparse reward and credit assignment problems inherent in deep reinforcement learning without requiring complex physical modeling. Extensive simulations demonstrate that EcoVMS significantly outperforms baseline methods across diverse workload scenarios. Under a typical 75% workload, EcoVMS achieved a 12.4% improvement in significant energy savings, improving computing resource utilization while reducing hotspots and lowering service latency, resulting in guaranteed quality of service (QoS).
AB - The rapid expansion of the cloud computing ecosystem necessitates scalable and energy-efficient resource management. However, achieving optimal energy efficiency is severely constrained by the complex interplay between computational workloads and thermal dynamics. Traditional data center (DC) scheduling methods typically rely on computationally expensive mechanistic models, such as computational fluid dynamics (CFD), or inefficient algorithm search, which frequently yield suboptimal solutions and struggle to adapt to real-time environments. To address these challenges, we propose an ecology-conservation-optimization virtual machine scheduling (EcoVMS) framework, a data-driven and end-to-end framework for compute-energy co-optimization. At its core, EcoVMS utilizes a latent reward generation enhanced proximal policy optimization (LARGE-PPO) algorithm, which utilizes large language models (LLMs) to analyze runtime telemetry—including central processing unit (CPU) utilization, thermal boundaries, and power consumption, and then utilizes large-scale semantic priors to generate potential reward factors. This mechanism resolves the sparse reward and credit assignment problems inherent in deep reinforcement learning without requiring complex physical modeling. Extensive simulations demonstrate that EcoVMS significantly outperforms baseline methods across diverse workload scenarios. Under a typical 75% workload, EcoVMS achieved a 12.4% improvement in significant energy savings, improving computing resource utilization while reducing hotspots and lowering service latency, resulting in guaranteed quality of service (QoS).
KW - Cloud computing
KW - QoS
KW - data center
KW - energy efficiency
KW - large language models
KW - reinforcement learning
KW - virtual machine scheduling
UR - https://www.scopus.com/pages/publications/105046896049
U2 - 10.1109/TSC.2026.3720939
DO - 10.1109/TSC.2026.3720939
M3 - Article
AN - SCOPUS:105046896049
SN - 1939-1374
VL - 19
SP - 3447
EP - 3460
JO - IEEE Transactions on Services Computing
JF - IEEE Transactions on Services Computing
IS - 5
ER -