Separating predictable and unpredictable flows via dynamic flow mining for effective traffic engineering

Takahashi, Yoshiko; Ishibashi, Keisuke; Tsujino, Masayuki; Kamiyama, Noriaki; Shiomoto, Kohei; Otoshi, Tatsuya; Ohsita, Yuichi; Murata, Masayuki

doi:10.1109/icc.2016.7511371

Cited by 8 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This grouping will also lead to improving scalability. Another solution is aggregating all traffic to a small number of flows and handling only predictable flow patterns (e.g., using [41]). Although these grouping and aggregation are effective to limit the demand patterns, the performance of allocation will be decreased due to coarse-grained allocation.…”

Section: J Discussionmentioning

confidence: 99%

Cooperative Multi-Agent Deep Reinforcement Learning for Dynamic Virtual Network Allocation With Traffic Fluctuations

Suzuki

Kawahara

Harada

2022

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

Network traffic and computing demand have been changing dramatically due to the growth of various types of network services, e.g., high-quality video delivery and operating system (OS) updates. To maximize the utilization efficiency of limited network resources, network resource control technology is required for smooth and quick operation when network demands change. Therefore, we propose a dynamic virtual network (VN) allocation method based on cooperative multi-agent deep reinforcement learning (Coop-MADRL). This method can quickly optimize network resources even while network demands are drastically changing by learning the relationship between network demand patterns and optimal allocation by using deep reinforcement learning (DRL) in advance. The key idea is to use a multi-agent technique for a reinforcement learning (RL) based dynamic VN allocation method, which can reduce the number of candidate actions per agent and can improve the performance for VN allocation. Moreover, a cooperation technique improves the efficiency of VN allocation. From results of a simulation evaluation, Coop-MADRL can calculate effective allocation within 1 s, which reduces the maximum server and link utilization and drastically reduces the constraint violations compared with that of the static VN allocation method. Furthermore, we revealed that the learning with various mixed traffic models could achieve a high generalization performance for all traffic patterns.

show abstract

Section: J Discussionmentioning

confidence: 99%

Cooperative Multi-Agent Deep Reinforcement Learning for Dynamic Virtual Network Allocation With Traffic Fluctuations

Suzuki

Kawahara

Harada

2022

IEEE Trans. Netw. Serv. Manage.

View full text Add to dashboard Cite

show abstract

“…Input : Flow data, Macroflow parameters Output: Macroflow data 1 Step 1) Summarize flow data 2 Step 2) Generate an initial candidate macroflow set 3 repeat 4 Step 3) Select an operation randomly Step 4) Update a candidate macroflow set 9 until termination conditions;…”

Section: Algorithm 1: Algorithm For Generating Macroflowsmentioning

confidence: 99%

“…* A preliminary version of this work appeared in IEEE ICC2016 [1]. a) E-mail: ishibashi.keisuke@lab.ntt.co.jp DOI: 10.1587/transcom.2017EBT0001 switches in the network.…”

Section: Introductionmentioning

confidence: 99%

Separating Predictable and Unpredictable Flows via Dynamic Flow Mining for Effective Traffic Engineering

Takahashi

Ishibashi

Tsujino

et al. 2018

IEICE Trans. Commun.

Self Cite

View full text Add to dashboard Cite

To efficiently use network resources, internet service providers need to conduct traffic engineering that dynamically controls traffic routes to accommodate traffic change with limited network resources. The performance of traffic engineering (TE) depends on the accuracy of traffic prediction. However, the size of traffic change has been drastically increasing in recent years due to the growth in various types of network services, which has made traffic prediction difficult. Our approach to tackle this issue is to separate traffic into predictable and unpredictable parts and to apply different control policies. However, there are two challenges to achieving this: dynamically separating traffic according to predictability and dynamically controlling routes for each separated traffic part. In this paper, we propose a macroflow-based TE scheme that uses different routing policies in accordance with traffic predictability. We also propose a trafficseparation algorithm based on real-time traffic analysis and a framework for controlling separated traffic with software-defined networking technology, particularly OpenFlow. An evaluation of actual traffic measured in an Inter-net2 network shows that compared with current TE schemes the proposed scheme can reduce the maximum link load by 34% (at the most congested time) and the average link load by an average of 11%.

show abstract

“…The increase of network traffic requires more high-speed and large-capacity communications for optical networks [1,2]. Accordingly, data traffic in a data center is explosively growing [3,4], and the power consumption is also increasing due to a large number of pieces of communication equipment [5,6,7]. In the optical communication systems, a transimpedance amplifier (TIA) [8], which converts currents of a photodiode to voltage signals and amplifies it to drive following circuits, is the most essential circuit for the frequency bandwidth of the optical receiver [9,10,11], but to achieve high-performance transimpedance, TIAs require large power consumption [12].…”

Section: Introductionmentioning

confidence: 99%

A wideband current-reuse-RGC TIA circuit with low-power consumption

Hida

Nakane

Mizuno

et al. 2019

IEICE Electron. Express

View full text Add to dashboard Cite

This paper presents a new Gain-Adder (GA) circuit for Current-Reuse (CR)-RGC TIA. The proposed GA circuit employs one transistor alone to enhance bandwidth and decrease power consumption. The proposed CR-RGC TIA circuit is designed in a 65-nm CMOS technology. The simulation results confirmed that the proposed CR-RGC TIA circuit improves bandwidth by 83% and decreases the power consumption by 34% in comparison with the conventional one.

show abstract

Separating predictable and unpredictable flows via dynamic flow mining for effective traffic engineering

Cited by 8 publications

References 14 publications

Cooperative Multi-Agent Deep Reinforcement Learning for Dynamic Virtual Network Allocation With Traffic Fluctuations

Cooperative Multi-Agent Deep Reinforcement Learning for Dynamic Virtual Network Allocation With Traffic Fluctuations

Separating Predictable and Unpredictable Flows via Dynamic Flow Mining for Effective Traffic Engineering

A wideband current-reuse-RGC TIA circuit with low-power consumption

Contact Info

Product

Resources

About