Name
Title | ||
|---|---|---|
Router power reduction by active performance control realized with support vector machines |
Abstract | ||
|---|---|---|
The machine-learning-based dynamic performance control of routers is proposed to reduce router power consumption. In order to achieve fast adaptability to catch the changing traffic characteristics, we introduce two sequential classification measures; normalization with performance thresholds, and periodic staggered use of learning machine sets in combination with Support Vector Machine (SVM). Numerical experiments using several real Internet traffic data sets elucidate that the router power consumption reduction reaches 50-65%. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1109/ICCNC.2015.7069400 | Computing, Networking and Communications |
Keywords | Field | DocType |
learning (artificial intelligence),power consumption,support vector machines,telecommunication computing,telecommunication network routing,telecommunication power management,telecommunication traffic,internet traffic data sets,svm,changing traffic characteristics,learning machine sets,machine-learning-based dynamic performance control,normalization,performance thresholds,router power consumption,sequential classification measures,support vector machine,dynamic perfomance control,electrical router,energy efficiency,machine learning,routing,engines,packet loss | Adaptability,Data set,Normalization (statistics),Computer science,Efficient energy use,Support vector machine,Packet loss,Real-time computing,Router,Internet traffic | Conference |
Citations | PageRank | References |
0 | 0.34 | 5 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hiroshi Kawase | 1 | 0 | 0.68 |
| Hiroshi Hasegawa | 2 | 18 | 15.70 |
| Ken-ichi Sato | 3 | 22 | 17.17 |