Job2Vec: A Self-Supervised Contrastive Learning Based HPC Job Power Consumption Prediction Framework

• Published in: 2023 IEEE 29th International Conference on Parallel and Distributed Systems (ICPADS) pp. 745 - 750
• Main Authors: Zhang, Jie, Song, Jian, Li, Xiang, Tian, Xuesen, Zhao, Zhigang, Wu, Lu, Wang, Chunxiao
• Format: Conference Proceeding
• Language: English
• Published: IEEE 17.12.2023
• Subjects: Contrastive Learning; Distributed databases; Energy consumption; Federated learning; HPC; Power Consumption Prediction; Power demand; Self-supervised learning; Shape; Training
• ISSN: 2690-5965
• DOI: 10.1109/ICPADS60453.2023.00113

In the context of the rapid development of big data and artificial intelligence, the field of HPC is facing significant challenges in energy consumption. To address this challenge, this paper proposes a power consumption prediction framework for HPC jobs based on self-supervised contrastive learning, named Job2Vec. Firstly, HPC jobs are clustered into different clusters based on job logs and power consumption curve shapes. Next, high-quality features of power consumption data at different granularities within each cluster are captured through self-supervised contrastive learning. Lastly, an incremental update strategy is introduced to handle the dynamic changes in HPC data. The experimental results demonstrate that, on the Jinan Supercomputing dataset comprising 1170 HPC jobs, the Job2Vec framework outperforms the baseline models overall in terms of prediction performance. Additionally, we also investigated the model's performance in single-step and multi-step forecasting, the impact of different indicators on prediction accuracy, and conducted ablation experiments to confirm the indispensability of each module. This is the first time that self-supervised contrastive learning has been introduced into the HPC field, aiming to provide support for energy scheduling in data centers.