A Completion Time-Based Flow Scheduling for Inter-Data Center Traffic Optimization

Hu, Wenbo; Liu, Jiang; Huang, Tao; Liu, Yunjie

doi:10.1109/access.2018.2834482

Cited by 8 publications

(8 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, given two non-zero integers a and b, (10, 3) = 55. The difference between P (s,d) (3, 10) and P (s,d) (10,3) lies in the former TS-MLG having more temporal links, while the latter has more spatial links. Intuitively, as the number of feasible paths offered in both cases is the same, the complexity and performance of scheduling a request in such TS-MLGs should be correspondingly similar.…”

Section: A Analytic Models For Snf Scheduling On a Fixed Routementioning

confidence: 99%

“…Bulk transfer demands from the data-intensive applications, such as online backups, multimedia transfers and data migration, usually do not require being delivered immediately, but need to be completed within certain time periods (e.g., hours) [3]. In other words, they are delay-tolerant.…”

Section: Introductionmentioning

confidence: 99%

“…In general, DC providers buy networking resources from ISPs or deploy dedicated inter-DCN based on peak demand. To sustain the rapid growth of bulk data flows, DC providers must keep buying more networking resources or upgrading the transmission capacity of their dedicated lines, even though the average utilization is low [3]. Moreover, due to the reliability reasons [10], the average utilization of wide area network (WAN) links usually remains 30-40%.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Time-Space Decoupled SnF Scheduling of Bulk Transfers Across Inter-Datacenter Optical Networks

et al. 2020

View full text Add to dashboard Cite

To meet the increasing inter-datacenter traffic, datacenter storage is brought in the forwarding path. Bulk data that are delay-tolerant can be temporarily stored and forwarded (SnF) at a later time when link is less busy. However, the use of storage transforms the conventional routing problem into a scheduling problem, where both bandwidth and storage resources must be allocated and both spatial routing and temporal scheduling must be performed. Such an SnF scheduling problem is critically important for the efficiency of SnF approaches. Most prior solutions aimed to jointly solve its temporal and spatial components and formulated this problem into difficult optimization problems, which contributes to a huge expansion size of the problem and hence are too complex for large networks and dynamic traffic. In this paper, we present analytic models to quantify the performance-complexity tradeoff in the SnF scheduling problem. Our key findings reveal that desirable performance can be obtained by considering only a few pre-selected routes rather than searching in the entire network topology. Thus, we propose a time-space decoupled (TSD) SnF scheduling method. Compared to the conventional joint methods, the advantages of the TSD method are as follows: (i) by decoupling the problem and solving them separately, the TSD method reduces the quadratic complexity of the joint methods to linear complexity; (ii) by condensing the redundant states, the TSD method obtains a longer horizon of temporal scheduling, given the same computational cost; (iii) by bounding the spatial hop count of routing paths, the TSD method avoids the detour issue faced by the joint methods and hence uses bandwidth more efficiently; (iv) by formulating the problem into a routing problem, the TSD method greatly simplifies the problem for dynamic traffic. Simulations demonstrate that the TSD method can outperform the conventional joint method, especially when the traffic load is moderate-to-high. INDEX TERMS Bulk data transfers, inter-datacenter networks, optical circuit switching, routing, store-and-forward.

show abstract

Section: A Analytic Models For Snf Scheduling On a Fixed Routementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Time-Space Decoupled SnF Scheduling of Bulk Transfers Across Inter-Datacenter Optical Networks

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The bandwidth-hungry and long-lived nature of bulk data flows imposes a great challenge on the inter-datacenter networks (inter-DCNs) [2]- [4]. To tackle this, prior studies exploited the delay-tolerance of bulk transfers to provide extra flexibility in scheduling and resource allocation [2]- [7].…”

Section: A Backgroundmentioning

confidence: 99%

“…Due to the diurnal traffic pattern, the bursty user demands and the time zones between DC sites, the network traffic can peak on different sites and at different hours. As a result, residual bandwidth in inter-DCNs varies in both time and space [7]. The bandwidth bottleneck of a bulk data flow may occur on different links and at different hours.…”

Section: A Backgroundmentioning

confidence: 99%

A Partial Store-and-Forward Scheduling Method for Inter-Datacenter Bulk Data Transfers

et al. 2020

View full text Add to dashboard Cite

Temporarily storing delay-tolerant data at peak hours and forwarding the data at offpeak hours, i.e., performing Store-and-Forward (SnF) using datacenter storage, can mitigate peak-hour congestion and exploit off-peak-hour bandwidth in inter-datacenter networks. Most prior studies considered a case where all nodes along their routing paths provided SnF options for the scheduling decision making. Intuitively, their solutions maximize the scheduling flexibility. However, the computational complexity of their solutions increases exponentially with the hop count. Meanwhile, SnF operations are generally performed on a portion of nodes rather than every node along the path. Thus, the considered case seems to be unnecessary in practice. In this paper, our studies reveal that desirable performance can be attained by involving a portion of nodes rather than all nodes along the path in the decision making. Thus, we propose a partial SnF scheduling method, which involves a portion of nodes in scheduling and introduces a network abstraction based on the involved nodes. Simulations demonstrate that the proposed method has lower complexity while achieving high performance.

show abstract

A Link Load Balancing Algorithm Based on Ant Colony Optimization in Data Center Network

Tang

Wang

2021

Communications and Networking

View full text Add to dashboard Cite

With the continuous increase of types of services and data volume in data center, the traffic loads of some links are excessive, and how to balance the link load and ensure the quality of network service have become research hotpots. However, the traditional link load balancing mechanisms ignore the complexity of network and the Quality of Service (QoS) requirement of the flow when calculating the forwarding paths. Therefore, we propose a link load balancing algorithm based on Ant Colony Optimization (LLBA) in data center network. The algorithm redefines the heuristic function according to the number of elephant flows on the link and the real-time load of links, and updates the pheromones according to the path length. Then, the algorithm customizes the optimal path determination rule according to the path transmission delay and the real-time loads, so as to find a best forwarding path for the current flow under the multiple constraints including the path length, link load, and transmission delay. The experiment results show that, the proposed algorithm improves the link utilization and network throughput effectively, and also reduces the delay and delay jitter to some extent, as compared with the traditional mechanisms.

show abstract

A Completion Time-Based Flow Scheduling for Inter-Data Center Traffic Optimization

Cited by 8 publications

References 16 publications

Time-Space Decoupled SnF Scheduling of Bulk Transfers Across Inter-Datacenter Optical Networks

Time-Space Decoupled SnF Scheduling of Bulk Transfers Across Inter-Datacenter Optical Networks

A Partial Store-and-Forward Scheduling Method for Inter-Datacenter Bulk Data Transfers

A Link Load Balancing Algorithm Based on Ant Colony Optimization in Data Center Network

Contact Info

Product

Resources

About