Font Size: a A A

Forecasting Methods, Support Vector Machine-based Telecommunications Traffic

Posted on:2009-01-05Degree:MasterType:Thesis
Country:ChinaCandidate:D B ChenFull Text:PDF
GTID:2199360245982932Subject:Control Science and Engineering
Abstract/Summary:PDF Full Text Request
Traffic forecasting technology is one of important means for network communication system designing, planning and optimization, and it also can provide decision support for telecom enterprise when marketing strategy development. Currently there have been more studies in theory and complemented methods of traffic forecasting and obtained some achievement. New theory and new technology based traffic forecasting researches have been developed continuously. As new technology of data mining, support vector machines(SVM) have been successfully applied in pattern recognition and regression problem,et al.This paper proposes to use its advantages of non-linear processing and generating ability to accomplish short-term traffic forecasting of telecom system, so as to improve forecasting precision. Consequently the study is significant in theory and is valuable in practice.Because of numerous traffic influence factors having a great of complex characteristics, and the pattern, without selecting input vectors, will lead to reduce of the precision and increase of the computering time. Therefore this paper adopts an effective fuzzy clustering analysis and process technology for the traffic data and combines the clustering algorithm with SVM. A new SVM method based on FCM fuzzy clusting algorithm for short-term traffic forecasting is first presented in this paper. This method chooses training samples by fuzzy clustering according to similarity degree of the input samples in consideration of the periodic characteristic of traffic change, which means take the same type of the data as the learning samples for forecasting, guarantee the consistency of the data characteristic and enhance the history data regulation.This paper analyses the basic theories of SVM. SVM have the remarkable advantages of non-linear regression, high forecasting accuracy and small time complexity. The results of numerical experiments show that SVM really has great prediction ability. In addition, we discusses on gauss kernel SVM and how the parameterσinfluences the quality of SVM in tail. We also show that gauss kernel function can describe the likeness degree of the sample. Moreover, we propose a new algorithm for finding a good parameterσ, we called inflexion method. What's more, we point out the influence of standardize to predict, and then give mostly scope of the excellent parameterσ, which in gauss kernel function after standardized. According the non-linear relationship between the forecasting traffic and its influence factors, this paper proposes a short-term traffic forecasting model based on SVM. Compared with the forecasting method of artificial neural networks (ANN) and circle time series, the simulation results of the practical application show that the SVM method is much better than others.
Keywords/Search Tags:support vector machines, fuzzy clusting, forecasting model, gauss kernel function
PDF Full Text Request
Related items