A novel scalable representative-based forecasting approach of service quality
- PDF / 2,275,725 Bytes
- 30 Pages / 439.37 x 666.142 pts Page_size
- 105 Downloads / 197 Views
A novel scalable representative-based forecasting approach of service quality Hamdi Yahyaoui1 · Hala S. Own2 · Ahmed Agwa3 · Zakaria Maamar4 Received: 6 September 2019 / Accepted: 11 March 2020 © Springer-Verlag GmbH Austria, part of Springer Nature 2020
Abstract Several approaches to forecast the service quality based on its quality of service (QoS) properties are reported in the literature. However, their main disadvantage resides in their limited scalability. In fact, they elaborate a forecasting model for each quality attribute per service, which cannot scale well for large or even medium size datasets of services. Accordingly, we propose a novel scalable representative-based forecasting approach of QoS. The QoS is modeled as a multivariate time series in which the values of service attributes are evaluated at each time instant and forecasted based on three stages. First, a data aggregation function is applied to the multivariate time series data. Then, principal component analysis (PCA) is applied to the quality attributes to determine the most relevant ones. The reduced data is then clustered, so that, a representative for each cluster is computed. Finally, a forecasting model is built for each cluster representative for the sake of deriving other services’ forecasting models. A set of extensive experiments are carried out to assess the efficiency and accuracy of the proposed approach on a dataset of real services. The experimental results show that the proposed approach is up to 75% more efficient than direct forecasting approaches using time measurements while increasing the number of forecasted services and that the elaborated forecasting models enjoy insignificant forecasting errors. Keywords Quality of service · Representative · Forecasting · Time series Mathematics Subject Classification 68U01
B
Hamdi Yahyaoui [email protected]
1
Computer Science Department, Kuwait University, Kuwait City, State of Kuwait, Kuwait
2
Department of Solar and Space Research, National Research Institute of Astronomy and Geophysics, Cairo, Egypt
3
Department of Statistics and Operations Research, Kuwait University, Kuwait City, State of Kuwait, Kuwait
4
College of Technological Innovation, Zayed University, Dubai, UAE
123
H. Yahyaoui et al.
1 Introduction There are no doubts that competition is healthy and has a positive impact on any society. On the one hand, providers strive to continuously improve their products and services so that they sustain their growth and competitiveness advantage. On the other hand, users (consumers) have the opportunity of comparing products/services and selecting those that satisfy their needs (e.g., taxi booking) and requirements (e.g., budget). Because providers’ survivability depends on user satisfaction, they ought to “keep an eye” on what is being circulated about their products/services on different means like social media, nowadays [28,29]. In the context of online services (aka e-services), a plethora exist ranging from food ordering and course tutoring to ticket booking a
Data Loading...
