Scheme to measure One-Way Delay Variation with detection and removal of clock skew

Abstract

One-Way Delay Variation ( ) has become increasingly of interest to evaluate network state and service quality, especially for real-time and streaming services such as VoIP and video. Measurement of these parameters needs to be performed with the layout infrastructure. Many schemes for OWD measurements require clock synchronization at the source and destination through Global-Positioning System (GPS) or the Network Time Protocol (NTP). In clock-synchronized approaches, the accuracy of the measurement of depends on the achieved accuracy of clock synchronization. GPS provides high-accuracy clock synchronization. However, the deployment of GPS on legacy network equipment might be slow and costly. This paper proposes a method for measuring without recurring to clock synchronization. However, clock skew may affect the measurement of . The proposed approach is based on the measurement of Inter-Packet Delay ( ) and Accumulated (AOWDV). This paper shows the performance of the proposed scheme via simulation and through experimentation in a VoIP network. The presented simulation and experimental results indicate that clock skew can be efficiently measured and removed and that can be measured without requiring clock synchronization.Index Terms-delay measurement, clock skew, clock rate adjustment, one-way delay, inter-packet delay.

Coexisting Parallelogram Method to Handle Jump Point on Hough Transform-based Clock Skew Measurement

“…All areas used clock skew depends on the accurate value of the measured clock skew. For this, many scholars have proposed methods to estimate its value on devices with digital clocks [2], [4], [11], [16], [19], [21]. These methods initiate the estimation through a measurer that collects a target device's timestamps over a network connection [30].…”

“…Picking only offsets in the lower region of the scatter diagram (minimum offsets) to avoid the outliers would be a very promising solution. Paxson [21], Aoki [2], and Huang et al [14] proposed this kind of solution with their own scheme. Paxson [21] combines the minimum offsets method with a median technique, Aoki [2], meanwhile, uses several windows with similar size, and Huang et al [14] proposed their sliding windows method.…”

“…Paxson [21], Aoki [2], and Huang et al [14] proposed this kind of solution with their own scheme. Paxson [21] combines the minimum offsets method with a median technique, Aoki [2], meanwhile, uses several windows with similar size, and Huang et al [14] proposed their sliding windows method. Later, Moon et al [19] with their linear programming algorithm (LPA) shows a robust method that is unaffected by outliers, just by drawing a line below all the offsets.…”

“…Hence, we omit the effect of the jump point by obtaining the skew from skews of some subsets of the offsetset which are no longer contain the jump point. Our evaluation results show that compared with LPA [20], Aoki's method [2], and the Hough transform based method [31], only the proposed method can handle the problem accurately. The following section describes in detail the voting scheme we used in this paper.…”

Estimation of the packet processing time of hosts in the presence of interrupt coalescence

“…1 shows. However, as time stamping after packet creation at src (PPT src ) and packet receiving at dst (PPT dst ) takes place at the application layer, the measured OWD includes these PPTs plus the interrupt coalescence (IC) of the NICs [4,5,6,7] as an apparent OWD (OWD 0 ) of P between src and dst, or:…”