A machine learning-based framework for predicting game server load
- PDF / 1,073,200 Bytes
- 20 Pages / 439.37 x 666.142 pts Page_size
- 44 Downloads / 201 Views
A machine learning-based framework for predicting game server load Çağdaş Özer 1 & Taner Çevik 2 & Ahmet Gürhanlı 3 Received: 27 November 2019 / Revised: 10 September 2020 / Accepted: 7 October 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
Server load prediction can be utilized for load-balancing and load-sharing in distributed systems. The use of machine learning (ML) algorithms for load estimation in distributed system applications can increase the availability and performance of servers. Hence, a number of machine learning algorithms have been applied thus far for server load estimation. This study focuses on increasing the performance of game servers by accurately predicting the workload of game servers in short, medium and long term prediction situations. While doing this, various machine learning techniques have been applied and the algorithms that give the best results are presented. In terms of implementation, companies using their servers and data centers can try to increase their level of satisfaction by using these algorithms. A prediction model is developed and the estimation performances of a number of fundamental ML methods i.e., Naïve Bayes (NB), Generalized Linear Model (GLM), Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), Gradient Boosted Trees (GBT), Support Vector Machine (SVM), Fast Large Margin (FLM), Convolutional Neural Network CNN are analyzed. The data used during the training stage is obtained by listening to the TCP/IP packet traffic and the real-data is extracted by performing an extensive analysis of the total transferred-data that includes also the payload. In the analysis phase, the goodput is considered in order to reveal exact resource requirements. Comprehensive simulations are performed under various conditions for high accuracy performance analysis. Experimental results indicate that the proposed ML-based prediction shows promising performance in terms of load prediction when compared to the common approaches present in the literature. Keywords Machine learning . Load prediction . Game server
* Taner Çevik [email protected]
1
Department of Computer Engineering, Istanbul University Cerrahpasa, Istanbul, Turkey
2
Department of Computer Engineering, Istanbul Arel University, Istanbul, Turkey
3
Department of Computer Engineering, Istanbul Aydin University, Istanbul, Turkey
Multimedia Tools and Applications
1 Introduction In recent years, the rapidly growing Internet has made servers and systems more and more complex, so balancing and sharing servers’ load has become even more important. As data processing shifts from clients to servers for specific applications, such as games, the load of the servers increases exponentially and performance management challenges arise. It is very important to estimate the performance workload (user requests - workload) efficiently and accurately when using existing work resources at an optimal level. Accurate predictions will improve the performance of servers, resulting in user
Data Loading...
