AI-Driven Energy Management in Green Cloud Computing: A Systematic Review
Abstract
The rapid expansion of cloud computing has significantly increased energy consumption, now accounting for an estimated 2–4% of global carbon dioxide emissions (Jones, 2023). In response, Artificial Intelligence (AI) has become a vital enabler in enhancing energy efficiency within the framework of Green Cloud Computing (GCC). This comprehensive review draws insights from 35 scholarly publications spanning from 2015 to 2024, focusing on how AI techniques are applied to energy management in cloud environments. The analysis highlights the use of Machine Learning (ML) methods—such as LSTM and Random Forest—for accurate workload prediction and allocation. It also examines Deep Reinforcement Learning (DRL) models like Deep Q-Networks (DQN) and Proximal Policy Optimization (PPO) for dynamically adjusting resource usage in response to changing system demands. Additionally, Federated Learning (FL) is explored as a strategy for distributed optimization, reducing the need for centralized data processing. The findings reveal that AI applications can lower data centre energy consumption by 20% to 40% (Zhang et al., 2022), though issues such as real-time adaptability and system compatibility remain barriers. The review concludes by identifying future research directions, including the integration of quantum-enhanced AI and edge-cloud collaboration to further improve energy efficiency and sustainability in cloud infrastructures.
How strong is the evidence?
Evidence Hub reads this as a systematic review. Its evidence level is 1 of 5 (Highest · pooled evidence). Pooled evidence from several studies sits at the top of the evidence pyramid.
Read the paper
Related studies
- Chaos and quantum thermalization
- The Dalton quantum chemistry program system
- Cord Blood Leptin and Adiponectin as Predictors of Adiposity in Children at 3 Years of Age: A Prospective Cohort Study
- Quantitative metabolomics by H-NMR and LC-MS/MS confirms altered metabolic pathways in diabetes
- Stable adiabatic quantum batteries
- A novel self-lipid antigen targets human T cells against CD1c(+) leukemias
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.