Performance prediction of robust header compression version 2 for RTP audio streaming using linear regression

Modern cellular networks utilising the long-term evolution (LTE) and the coming 5G set of standards face an ever-increasing demand for mobile data with low latency from connected devices. Header compression is employed to minimise the overhead for IP-based cellular network traffic, thereby decreasing the overall bandwidth usage, which consequently results in decreased delay for transmissions. In this paper, we evaluate a basic linear function to predict Robust Header Compression version 2's (RFC 5225) RTP compression savings on-the-fly, which will enable the compression to adapt to varying channel conditions dynamically. We find that this approach can achieve more than 90%accuracy for low error rates while being computationally non-demanding. This will aid future compressors to minimise compression overhead, thereby increasing the compression gain even further.