دانلود رایگان مقاله اندازه گیری ظرفیت سبک برای شبکه های تلفن همراه

Abstract

Mobile data traffic is increasing rapidly and wireless spectrum is becoming a more and more scarce resource. This makes it highly important to operate mobile networks efficiently. In this paper we are proposing a novel lightweight measurement technique that can be used as a basis for advanced resource optimization algorithms to be run on mobile phones. Our main idea leverages an original packet dispersion based technique to estimate per user capacity. This allows passive measurements by just sampling the existing mobile traffic. Our technique is able to efficiently filter outliers introduced by mobile network schedulers and phone hardware. In order to asses and verify our measurement technique, we apply it to a diverse dataset generated by both extensive simulations and a week-long measurement campaign spanning two cities in two countries, different radio technologies, and covering all times of the day. The results demonstrate that our technique is effective even if it is provided only with a small fraction of the exchanged packets of a flow. The only requirement for the input data is that it should consist of a few consecutive packets that are gathered periodically. This makes the measurement algorithm a good candidate for inclusion in OS libraries to allow for advanced resource optimization and application-level traffic scheduling, based on current and predicted future user capacity.

8. Conclusions

We presented a lightweight measurement technique that lever- ages adaptive filtering over the packet dispersion time. This allows to estimate the per user capacity in mobile cellular networks. Ac- curate estimates can be achieved exploiting as few as 5% of the 794 information obtained from TCP data flows. Given that this solution can support dense throughput sampling, it is ideal for capacity pre- diction and optimized resource allocation. In fact, if the future ca- pacity availability is known, it is possible to predict when it is best to communicate by doing so when it is cheaper (i.e., more capacity available). In addition, our solution is able to estimate the fast ca- pacity variations from a mobile terminal by monitoring the traffic 801 generated under normal daily usage. We validated our technique over a week-long measurement and an extensive simulation campaign. We achieved good estimation 804 accuracy even when using only short lived TCP connections. Since our technique is based on simple post-processing operations on the packet timestamps, it is possible to easily integrate it in back- ground processes or OS routines. We are planning to extend our measurement application with filter based prediction capabilities in order to provide mobile phones with a complete capacity forecasting tool, which, in turn, will allow for advanced resource allocation mechanisms. Fi- nally, we are planning additional measurement campaigns in or- der to further extend these encouraging results on passive and 814 lightweight measurement tools.