An Approach to Pre-Schedule Traffic in Time-Dependent Pricing Systems

作者:Jin, Mingshuang; Gao, Shuai*; Luo, Hongbin*; Li, Jiawei; Zhang, Yuming; Das, Sajal K.
来源:IEEE Transactions on Network and Service Management, 2019, 16(1): 334-347.
DOI:10.1109/TNSM.2018.2875549

摘要

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.