SHERA: SHAP-Enhanced Resource Allocation for VM Scheduling and Efficient Cloud Computing
Cloud computing plays a crucial role in modern technology, providing scalable and on-demand computing resources. However, excessive resource use can result in higher energy demand, higher operating expenses, and a more significant adverse effect on the environment as per study by Berl et al. (2010)....
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11000120/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Cloud computing plays a crucial role in modern technology, providing scalable and on-demand computing resources. However, excessive resource use can result in higher energy demand, higher operating expenses, and a more significant adverse effect on the environment as per study by Berl et al. (2010). In order to forecast and maximize the energy efficiency in cloud systems, this paper presents a machine learning based methodology. Using the Cloud Efficiency Dataset from Google Cloud, key performance indicators such as CPU usage, memory consumption, network traffic, and power consumption were analyzed. Three machine learning models—Random Forest, Naïve Bayes, and Support Vector Machine (SVM) were trained and assessed based on Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and an Equivalent Accuracy metric. Among them Random Forest model performed the best, achieving an RMSE of 0.16 and an accuracy of 96.8 %. To improve the interpretability of the model Explainable Artificial Intelligence (XAI) techniques were applied, specifically SHapley Additive exPlanations (SHAP), to evaluate feature importance. The findings demonstrated that the most important variables which influence energy efficiency are CPU usage and memory consumption. This work presents a system level integration of SHAP guided VM scheduling rather than a fundamentally new algorithm. Unlike static threshold or heuristic schedulers, our SHAP driven system adapts VM placement decisions in real time with built in interpretability. While SHAP adds an average 0.15s of per job explanation latency (0.05s on GPU), we consider this overhead acceptable given the critical need for transparent, trustable scheduling in production clouds. |
|---|---|
| ISSN: | 2169-3536 |