Summary of Approximating G(t)/gi/1 Queues with Deep Learning, by Eliran Sherzer et al.
Approximating G(t)/GI/1 queues with deep learning
by Eliran Sherzer, Opher Baron, Dmitry Krass, Yehezkel Resheff
First submitted to arxiv on: 11 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Probability (math.PR)
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 The paper proposes a supervised machine-learning approach to solve a fundamental problem in queueing theory: estimating the transient distribution of the number in the system for a G(t)/GI/1. The Moment-Based Recurrent Neural Network (RNN) method (MBRNN) uses a RNN architecture based on the first several moments of time-dependent inter-arrival and stationary service time distributions to provide a fast and accurate predictor of these distributions for moderate horizon lengths and practical settings. The MBRNN requires only the first four inter-arrival and service time moments, outperforming simulation modeling in terms of runtime while achieving high accuracy. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper uses machine learning to solve a problem in queueing theory. It creates a special kind of neural network that can quickly estimate how many customers are in a system over time. This helps by being much faster than using simulations to model the system, which takes a lot of time and computing power. The method works well even when it’s not perfect, and could be used for other types of systems too. |
Keywords
» Artificial intelligence » Machine learning » Neural network » Rnn » Supervised
