TY - JOUR
T1 - Action-Based Scheduling
T2 - Leveraging App Interactivity for Scheduler Efficiency
AU - Tadrous, John
AU - Eryilmaz, Atilla
AU - Sabharwal, Ashutosh
N1 - Funding Information:
Manuscript received March 21, 2017; revised April 27, 2018 and September 5, 2018; accepted November 13, 2018; approved by IEEE/ACM TRANSACTIONS ON NETWORKING Editor W. Wang. Date of publication December 10, 2018; date of current version February 14, 2019. This work was supported in part by NSF under Grant CCSS-EARS-1444026, Grant CNS-NeTS-1514260, Grant CNS-NeTS-1717045, Grant CMMI-SMOR-1562065, Grant CNS-ICNWEN-1719371, and Grant CNS-SpecEES-1824337, in part by DTRA under Grant HDTRA1-15-1-0003 and Grant HDTRA1-18-1-0050, in part by QNRF under Grant NPRP 7-923-2-344, and in part by NSF under Grant CNS-1314822. (Corresponding author: John Tadrous.) J. Tadrous is with the Department of Electrical and Computer Engineering, Gonzaga University, Spokane, WA 99202 USA (e-mail: tadrous@gonzaga.edu).
Publisher Copyright:
© 2018 IEEE.
PY - 2019/2
Y1 - 2019/2
N2 - The dominant portion of smartphone traffic is generated by apps that involve human interactivity. Particularly, when human users receive information from a server, they spend a few seconds of information processing before taking an action. The user processing time creates an idle communication period during the app session. Moreover, the generation of the future traffic depends on the service of the current query-response pair. In this paper, we aim at leveraging the properties of such interactions to reap quality-of-experience gains. Existing schedulers, both in practice and theory, are not designed in view of the aforementioned traffic characteristics. Theoretical works predominantly focus on scheduling of traffic that is either generated independently or directly controlled, but not governed by the specific dynamics caused by human interactions. Schedulers in practice, on the other hand, employ round-robin and processor-sharing methods to serve multiple ongoing sessions. We show that neither of these approaches is effective for serving apps that involve human interactivity. Instead, we show that optimal scheduling for interactive traffic is non-randomized over packets, which we call action-based, as it avoids breaking ongoing service of actions in order to align human response times with the service of other actions. Since the design of optimal action-based policy is computationally prohibitive, we develop low-complexity suboptimal action-based policies that are optimal for two ongoing sessions. Our numerical studies based on a real-data trace reveal that our proposed action-based policies can reduce total delay by 22% with respect to packet-based equal processor sharing.
AB - The dominant portion of smartphone traffic is generated by apps that involve human interactivity. Particularly, when human users receive information from a server, they spend a few seconds of information processing before taking an action. The user processing time creates an idle communication period during the app session. Moreover, the generation of the future traffic depends on the service of the current query-response pair. In this paper, we aim at leveraging the properties of such interactions to reap quality-of-experience gains. Existing schedulers, both in practice and theory, are not designed in view of the aforementioned traffic characteristics. Theoretical works predominantly focus on scheduling of traffic that is either generated independently or directly controlled, but not governed by the specific dynamics caused by human interactions. Schedulers in practice, on the other hand, employ round-robin and processor-sharing methods to serve multiple ongoing sessions. We show that neither of these approaches is effective for serving apps that involve human interactivity. Instead, we show that optimal scheduling for interactive traffic is non-randomized over packets, which we call action-based, as it avoids breaking ongoing service of actions in order to align human response times with the service of other actions. Since the design of optimal action-based policy is computationally prohibitive, we develop low-complexity suboptimal action-based policies that are optimal for two ongoing sessions. Our numerical studies based on a real-data trace reveal that our proposed action-based policies can reduce total delay by 22% with respect to packet-based equal processor sharing.
KW - Interactive apps
KW - non-convex optimization
KW - scheduling
UR - http://www.scopus.com/inward/record.url?scp=85058182293&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85058182293&partnerID=8YFLogxK
U2 - 10.1109/TNET.2018.2882557
DO - 10.1109/TNET.2018.2882557
M3 - Article
AN - SCOPUS:85058182293
VL - 27
SP - 112
EP - 125
JO - IEEE/ACM Transactions on Networking
JF - IEEE/ACM Transactions on Networking
SN - 1063-6692
IS - 1
M1 - 8571178
ER -