Summary of Multiscale Representation Enhanced Temporal Flow Fusion Model For Long-term Workload Forecasting, by Shiyu Wang et al.
Multiscale Representation Enhanced Temporal Flow Fusion Model for Long-Term Workload Forecasting
by Shiyu Wang, Zhixuan Chu, Yinbo Sun, Yu Liu, Yuliang Guo, Yang Chen, Huiyang Jian, Lintao Ma, Xingyu Lu, Jun Zhou
First submitted to arxiv on: 29 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper presents a novel framework for accurate workload forecasting in cloud computing systems, leveraging self-supervised multiscale representation learning to capture both long-term and near-term patterns. The proposed approach encodes long-term history through multiscale representations and models near-term observations via temporal flow fusion. These representations are fused using an attention mechanism and characterized with normalizing flows to handle non-Gaussian/non-linear distributions of time series. The framework outperforms existing methods on 9 benchmarks, demonstrating its effectiveness in workload forecasting. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps computers predict how much work they need to do in the future. This is important because it lets companies manage their computer resources better and schedule tasks more efficiently. Right now, predicting workload isn’t very accurate because old data doesn’t help as much as new data does. The authors propose a new way of learning about workload patterns that takes into account both old and new data. They test their method on several different datasets and show it works better than existing methods. |
Keywords
» Artificial intelligence » Attention » Representation learning » Self supervised » Time series
