DCNEJul 26, 2015

Modeling Website Workload Using Neural Networks

arXiv:1507.07204v11 citations
Originality Synthesis-oriented
AI Analysis

This work addresses workload prediction for web servers, but it is incremental as it applies an existing method to a specific dataset without major innovations.

The paper tackled the problem of modeling website workload by using artificial neural networks for time-series forecasting of requests per day and per second on the 1998 FIFA World Cup website, presenting results from 13 experimental cases.

In this article, artificial neural networks (ANN) are used for modeling the number of requests received by 1998 FIFA World Cup website. Modeling is done by means of time-series forecasting. The log traces of the website, available through the Internet Traffic Archive (ITA), are processed to obtain two time-series data sets that are used for finding the following measurements: requests/day and requests/second. These are modeled by training and simulating ANN. The method followed to collect and process the data, and perform the experiments have been detailed in this article. In total, 13 cases have been tried and their results have been presented, discussed, compared and summarized. Lastly, future works have also been mentioned.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes