Evaluation of network traffic workload scaling techniques

Performance testing on a network that is loaded by realistic background traffic, is an important issue in the design of network applications. To obtain this background traffic, a packet stream can be captured on a real network. For testing the application under varying network loads, straightforward techniques can be applied to alter the originally captured traffic trace. An example thereof is faster replay of the packet stream. The drawback of these simple techniques is that the packet stream will be altered in many ways, and thus a simple multiplication of the load that is inflicted by the packet stream on a network cannot be guaranteed. This paper presents and analyzes some frequently used load scaling methods. Next to the computationally more demanding use of traffic models, a novel technique is introduced based on the rotation of the bin vector, that combines better accuracy with computational simplicity.