Variable bit rate video traffic prediction based on kernel least mean square method. Issue 9 (1st September 2015)

• Record Type: Journal Article
• Authors: Haghighat, Nasser; Kalbkhani, Hashem; Shayesteh, Mahrokh G.; Nouri, Mehdi
• Is Part Of: IET image processing. Volume 9:Issue 9(2015)
• Page Start: 777
• Page End: 794
• Publication Date: 2015-09-01
• Subjects: telecommunication traffic -- least mean squares methods -- bandwidth allocation -- multimedia communication -- quality of service -- autoregressive processes -- parameter estimation -- integral equations -- video communication; Wiener–Hopf optimum solution -- video trace -- BDS test -- parameter estimation -- KLMS‐based method -- autoregressive model -- multimedia quality of service control strategy -- dynamic bandwidth allocation -- VBR video traffic prediction -- kernel least mean square method -- variable bit rate video traffic prediction; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2014.1035
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : In this study, the problem of variable bit rate (VBR) video traffic prediction is addressed. VBR traffic prediction is necessary in dynamic bandwidth allocation for multimedia quality of service control strategies. Autoregressive (AR) models have been widely used in VBR traffic prediction where the least mean square (LMS)‐based methods were utilised for parameter estimation. However, they are ineffective when the traffic is dynamic in nature. In this study, using the Brock, Dechert, and Scheinkman (BDS) test, it is shown that the video traffic is non‐linear. Kernel is an efficient tool to convert non‐linear data into linear one in a higher‐dimensional space. The kernel LMS (KLMS) method is proposed to forecast the next frame sizes of I, B and P frames as well as the next group‐of‐pictures (GOP) size of video traffic. Extensive simulations were performed on different video traces where different performance metrics were considered. KLMS results were very close to those of the Wiener–Hopf optimum solution and better than the results of commonly used normalised LMS and other algorithms such as the least mean kurtosis (LMK), wavelet LMK, adaptive network fuzzy inference system (ANFIS) and neural networks.