Live video streaming is widespread and a heavy consumer of Internet bandwidth. As such, it is important to evaluate the quality of that streaming, particularly over links that may pose challenges to near-real-time content delivery. In this paper, we study the performance of Twitch, one of the leading live streaming platforms, over Geosynchronous Earth Orbit (GEO) satellite networks; GEO networks are a key technology for connecting users in challenging environments, yet they suffer from high latency. To do so, we conduct controlled experiments that compare Twitch live stream performance on a high-latency GEO network to that on a low-latency campus network. We analyze core quality of experience metrics – resolution, frames per second, rebuffering, and playback delay – to pinpoint how satellite-induced delays disrupt streaming quality. Our findings reveal a critical flaw in Twitch’s client scheduling: chunk request intervals are not calibrated to accommodate GEO network latency. As a result, playback buffers deplete before the next video chunk arrives, triggering frequent rebuffering, increased latency, and a notable deterioration in quality of experience. By highlighting this gap, our work underscores the urgency of latency-aware streaming strategies and adaptive scheduling algorithms. These insights offer actionable guidance for platform developers, satellite ISPs, and researchers, ultimately paving the way for more robust, inclusive live stream experiences as the medium’s popularity and influence continue to climb.

Geosynchronous satellite (GEO) networks are a crucial option for users beyond terrestrial connectivity. However, unlike terrestrial networks, GEO networks exhibit high latency and deploy TCP proxies and traffic shapers. The deployment of proxies mitigates the impact of high network latency, while traffic shapers help realize customer-controlled data-saver options that optimize data usage. It is unclear how the interplay between GEO networks' high latency, TCP proxies, and traffic-shaping policies affects the quality of experience (QoE) for commonly used video applications. In our study, we examine this relationship through a series of video streaming experiments at a shaped rate of 900kbps. Our preliminary analysis reveals that 28% of TCP sessions (with TCP proxies) and 18% of gQUIC sessions (without TCP proxies) experience rebuffering events, while the median average resolution is only 380p for TCP and 299p for gQUIC. Additionally, we identify two key factors contributing to sub-optimal performance: (i) unlike TCP, gQUIC only utilizes 63% of network capacity; and (ii) YouTube's chunk request pipelining is imperfect. To avoid potential degradation in video quality, the satellite provider subsequently discontinued providing data saver options that shape video traffic to US residential customers.

Digital equity in Internet access is often measured along three axes: availability, affordability, and adoption. Most prior work focuses on availability; the other two aspects have received less attention. In this paper, we study broadband affordability in the US by focusing on the nature of broadband plans offered by major ISPs. To this end, we develop a broadband plan querying tool (BQT) that obtains broadband plans (upload/download speed and price) offered by seven major wireline US ISPs for any street address in the US. We then use this tool to curate a dataset, querying broadband plans for over 837 k street addresses in thirty cities for these ISPs. We use a plan's carriage value, defined as the Mbps of a user's traffic that an ISP carries for one dollar, to compare plans. Our analysis provides us with the following new insights: (1) ISP plans vary inter-city. Specifically, up to 60% of the census block groups in a city can receive low carriage value plans from an ISP; (2) ISP plans intra-city are spatially clustered, and the carriage value can vary as much as 600% within a city; (3) Cable-based ISPs offer up to 30% higher carriage value to users when they are competing with fiber-based ISPs in a block group compared to when they are operating alone or in conjunction with a DSL-based ISP; and (4) Fiber deployments, which have better carriage values, are associated with higher average income block groups. While we hope our tool, dataset, and analysis in their current form are helpful for policymakers at different levels (city, county, state), they are only a small step toward quantifying digital inequity. We conclude with recommendations to further advance our understanding of broadband affordability.

It is well documented that, in the United States (U.S.), the availability of Internet access is related to several demographic attributes. Data collected through end user network diagnostic tools, such as the one provided by the Measurement Lab (M-Lab) Speed Test, allows the extension of prior work by exploring the relationship between the quality, as opposed to only the availability, of Internet access and demographic attributes of users of the platform. In this study, we use network measurements collected from the users of Speed Test by M-Lab and demographic data to characterize the relationship between the quality-of-service (QoS) metric download speed, and various critical demographic attributes, such as income, education level, and poverty. For brevity, we limit our focus to the state of California. For users of the M-Lab Speed Test, our study has the following key takeaways: (1) geographic type (urban/rural) and income level in an area have the most significant relationship to download speed; (2) average download speed in rural areas is 2.5 times lower than urban areas; (3) the COVID-19 pandemic had a varied impact on download speeds for different demographic attributes; and (4) the U.S. Federal Communication Commission’s (FCC’s) broadband speed data significantly over-represents the download speed for rural and low-income communities compared to what is recorded through Speed Test.

Crowdsourced speed test measurements, such as those by Ookla® and Measurement Lab (M-Lab), offer a critical view of network access and performance from the user's perspective. However, we argue that taking these measurements at surface value is problematic. It is essential to contextualize these measurements to understand better what the attained upload and download speeds truly measure. To this end, we develop a novel Broadband Subscription Tier (BST) methodology that associates a speed test data point with a residential broadband subscription plan. Our evaluation of this methodology with the FCC's MBA dataset shows over 96% accuracy. We augment approximately 1.5M Ookla and M-Lab speed test measurements from four major U.S. cities with the BST methodology. We show that many low-speed data points are attributable to lower-tier subscriptions and not necessarily poor access. Then, for a subset of the measurement sample (80k data points), we quantify the impact of access link type (WiFi or wired), WiFi spectrum band and RSSI (if applicable), and device memory on speed test performance. Interestingly, we observe that measurement time of day only marginally affects the reported speeds. Finally, we show that the median throughput reported by Ookla speed tests can be up to two times greater than M-Lab measurements for the same subscription tier, city, and ISP due to M-Lab's employment of different measurement methodologies. Based on our results, we put forward a set of recommendations for both speed test vendors and the FCC to con-textualize speed test data points and correctly interpret measured performance.

Cloud Radio Access Network (C-RAN) is a new architecture that has been proposed to enable the current hardware to meet the ever-increasing traffic demand, as well as reducing the energy consumption of mobile base stations. This paper mainly focuses on two components of C-RAN, namely Remote Radio Heads (RRH) and Baseband Processing Unit (BBU) pool. The method of association of these two components could potentially affect the Quality of Service (QoS) and energy consumption level of the system. The connection between RRH(s) and BBU(s) is logical in C-RAN, which means that the association of RRH(s) to BBU(s) can be dynamically adjusted. Thus, a BBU-RRH switching scheme is required to manage the computational resource that the BBU pool possesses. This paper proposes a switching algorithm that works in conjunction with the knowledge of the traffic pattern of an area. This algorithm not only reduces the number of BBUs used in comparison with the traditional approach, but also decreases the number of switches required while maintaining a satisfactory level of service. In order to achieve this, the proposed algorithm reduces or limits the load of BBUs when the overall traffic of a BBU is on the rise, and vice versa. Finally, the simulation results illustrate that the proposed algorithm reduces the switching complexity and improves QoS while achieving significant reduction of BBU usage in comparison to traditional RAN.