Is differential traffic management (i.e., prioritizing some forms of Internet traffic over others) a zero-sum practice? Do the benefits of favoring Internet traffic from some edge providers come only at the expense of other edge providers? Or, rather, do the benefits of prioritization exceed the corresponding harms, making this a positive-sum practice that enhances aggregate welfare?In paragraphs 125-32 of the 2015 Open Internet Order, the FCC laid out its case for why “paid prioritization” — defined as “the management of a broadband provider’s network to directly or indirectly favor some traffic over other traffic, including through use of techniques such as traffic shaping, prioritization, resource reservation, or other forms of preferential traffic management, either (a) in exchange for consideration (monetary or otherwise) from a third party, or (b) to benefit an affiliated entity” — should be banned, ex ante, as a per se unreasonable practice. To justify this proscription, the FCC pointed to support in the record from commenters asserting that differential traffic management is “inherently a zero-sum practice,” which will inevitably lead to a bifurcated Internet wherein certain edge providers are relegated to a “slow lane” with degraded performance. The FCC also cited to multiple opposing comments in the record that argued traffic prioritization is not a zero-sum game, but, evidently, did not find these arguments persuasive.Drawing on principles of game theory, cognitive psychology, and statistics, this paper examines this discrete issue and posits that — contrary to the arguments accepted by the FCC — differential traffic management on the Internet is not a zero-sum practice. Specifically, this paper recognizes the relationship between the quality of service (QoS) for edge services and quality of experience (QoE) for users, and observes that while these two variables are positively correlated for all edge services, the strength of such correlation differs significantly. For edge services that are particularly sensitive to latency, packet loss, or bandwidth constraints (e.g., live video, online multiplayer gaming), the users’ QoE will have a strong direct correlation to the services’ QoS. Conversely, for edge services that are comparatively insensitive to latency, packet loss, and bandwidth constraints (e.g., email, software updates), the direct correlation between QoS and QoE will be significantly weaker.Thus, if an ISP were to prioritize services that fall into the former category, and de-prioritize services that fall into the latter category, the benefits yielded to the former (i.e., higher user QoE) would outweigh the harms done to the latter (i.e., slightly lower user QoE), so the network as a whole would work better and aggregate consumer welfare would be increased. For example, in such a system, users streaming live video would be much happier, while users checking their email would be only a little worse off, and may see no significant reduction in QoE. This suggests that the FCC should perhaps reconsider its view of such traffic management practices going forward, particularly as new services with greater QoS demands (e.g., VR-based services) begin to enter the market.
Search from 250 M+ research papersSearch from 250 M+ research papers
Open Access
Jan 1, 2020
Lyubov Kolobashkina + 1
