Prof. Zhou Jiantao's research team from the School of Computer Science (Software School) focuses on research in areas related to computing networks and software engineering, including cloud computing, big data, software testing and validation, and formal description techniques. Recently, the team made significant progress in the field of key technologies in cloud computing and formal description. Below are the brief summaries of the research findings:

In the area of key technologies in cloud computing, the team published a research paper titled "A Reinforcement Learning-Based Framework for Holistic Energy Optimization of Sustainable Cloud Data Centers." This work was published in IEEE Transactions on Services Computing (TSC), a top international journal in the field of service computing and an A-class journal recommended by the China Computer Federation (CCF).

(DOI: 10.1109/TSC.2024.3495495, Paper link: https://ieeexplore.ieee.org/abstract/document/10749972)

The rapid growth in the scale and number of cloud data centers has led to significant increases in energy consumption and carbon emissions. Major cloud service providers have started exploring hybrid power sources, combining traditional electricity with renewable energy to power cloud data centers. However, due to the randomness of resource requests and the volatility and intermittency of renewable energy, cloud data centers utilizing hybrid power often face issues such as excessive virtualization or overcooling, leading to overall energy waste. To address this issue, the paper proposes a deep reinforcement learning-based framework for optimizing the overall energy consumption of cloud data centers, based on the "MAPE" (Monitor, Analyze, Plan, and Execute) design principles.