Cellular data network infrastructure characterization and implication on mobile content placement

Abstract

Despite the tremendous growth in the cellular data network usage due to the popularity of smartphones, so far there is rather limited understanding of the network infrastructure of various cellular carriers. Understanding the infrastructure characteristics such as the network topology, routing design, address allocation, and DNS service configuration is essential for predicting, diagnosing, and improving cellular network services, as well as for delivering content to the growing population of mobile wireless users. In this work, we propose a novel approach for discovering cellular infrastructure by intelligently combining several data sources, i.e., server logs from a popular location search application, active measurements results collected from smartphone users, DNS request logs from a DNS authoritative server, and publicly available routing updates. We perform the first comprehensive analysis to characterize the cellular data network infrastructure of four major cellular carriers within the U.S. in our study.We conclude among other previously little known results that the current routing of cellular data traffic is quite restricted, as it must traverse a rather limited number (i.e., 4-6) of infrastructure locations (i.e., GGSNs), which is in sharp contrast to wireline Internet traffic. We demonstrate how such findings have direct implications on important decisions such as mobile content placement and content server selection. We observe that although the local DNS server is a coarse-grained approximation on the user's network location, for some carriers, choosing content servers based on the local DNS server is accurate enough due to the restricted routing in cellular networks. Placing content servers close to GGSNs can potentially reduce the end-to-end latency by more than 50% excluding the variability from air interface.

Tackling bufferbloat in 3G/4G networks

“…Even if the client and server are close to each other geographically, the propagation delay between them could still be hundreds of milliseconds. The reason is that all the cellular data have to go through a few IP gateways [31] deployed across the country by the carriers. Due to this detour, the natural RTTs in cellular networks are relatively large.…”

“…Such long propagation delays are common in cellular networks since all traffic must detour through the gateway[31]. DRWA improves the throughput by 23% in AT&T HSPA+ network and 30% in Verizon LTE network when the BDP of the underlying network is large.…”

An Energy Efficient Multi-Core Modem Architecture for LTE Mobile Terminals

“…But this is not applied because to the auther's best knowldge, no data is available about the amount of power consumed by peripherals of the system under consideration. We have explored various studies and research focused on patterns of user behavior such as [19], [20], [21] to direct power optimizations. Our goal is to study the high-level characteristics of mobile terminals usage, which help to understand the implications on optimizing the hardware design.…”

Go this way

“…Huang et al [10] studied the performance of 3G and WiFi from smart phones. Xu et al [20] analyzed the infrastructure characteristics of cellular networks. Deshpande et al [7] compared the performance of 3G and Metro-Scale WiFi.…”