Resource Management Scheme Based on Ubiquitous Data Analysis

Abstract EN

Resource management of the main memory and process handler is critical to enhancing thesystem performance of a web server.

Owing to the transaction delay time that affects incomingrequests from web clients, web server systems utilize several web processes to anticipate futurerequests.

This procedure is able to decrease the web generation time because there are enoughprocesses to handle the incoming requests from web browsers.

However, inefficient processmanagement results in low service quality for the web server system.

Proper pregeneratedprocess mechanisms are required for dealing with the clients’ requests.

Unfortunately, it isdifficult to predict how many requests a web server system is going to receive.

If a web serversystem builds too many web processes, it wastes a considerable amount of memory space, andthus performance is reduced.

We propose an adaptive web process manager scheme based on theanalysis of web log mining.

In the proposed scheme, the number of web processes is controlledthrough prediction of incoming requests, and accordingly, the web process management schemeconsumes the least possible web transaction resources.

In experiments, real web trace data wereused to prove the improved performance of the proposed scheme.