An Approach to Pre-Schedule Traffic in Time-Dependent Pricing Systems
Time-dependent pricing (TDP) sets different prices in different time slots in order to motivate users to shift their delay-tolerant flows from congested time slots to less congested ones, thus helping Internet service providers (ISPs) utilize their network capacity more efficiently. In existing TDP approaches, however, once a flow is delayed to a less congested time slot by a user, the user has to wait until that time slot to consume the flow, even if there is idle capacity in earlier time slot(s) to accommodate the flow. In addition, in case that the traffic usage shifted to some time slots is so aggressive that new congestion is caused, it is hard for the ISP to accommodate more bursty traffic. To address these issues, in this paper we propose an approach to pre-schedule the delayed flows before their deadlines. Our results from extensive simulations show that the proposed approach could benefit both users and ISPs. For example, an ISP can smooth its bandwidth usage, which in turn makes it possible to accommodate more bursty traffic.
M. Jin et al., "An Approach to Pre-Schedule Traffic in Time-Dependent Pricing Systems," IEEE Transactions on Network and Service Management, vol. 16, no. 1, pp. 334 - 347, Institute of Electrical and Electronics Engineers (IEEE), Mar 2019.
The definitive version is available at https://doi.org/10.1109/TNSM.2018.2875549
Intelligent Systems Center
Second Research Center/Lab
Center for High Performance Computing Research
Keywords and Phrases
Costs; Delay tolerant networks; Optimization; Bandwidth usage; Bursty traffic; Delay tolerant; Extensive simulations; Mobile access networks; Network Capacity; Pre-schedule; Time-dependent pricing; Traffic congestion; Time Dependent Pricing
International Standard Serial Number (ISSN)
Article - Journal
© 2019 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.
01 Mar 2019