Abstract
Two time delay neural network based forecasting systems are proposed to perform dynamic bandwidth reservation for real-time, variable bit rate (VBR) video service in ATM networks. The networks are found to give highly reliable predictions even in a non-stationary environment. Their performance is quantified through simulation experiments on clippings from the movie, `Star Wars'. In particular, the time-delay pi-sigma network based dynamic bandwidth reservation achieves high network utilization, loss-free transmission and reasonable delay, and its lower computational requirements make it suitable for on-line operation.
Original language | English |
---|---|
Pages | 275-280 |
Number of pages | 6 |
State | Published - 1993 |
Event | Proceedings of the 1993 Artificial Neural Networks in Engineering, ANNIE'93 - St.Louis, MO, USA Duration: 14 Nov 1993 → 17 Nov 1993 |
Conference
Conference | Proceedings of the 1993 Artificial Neural Networks in Engineering, ANNIE'93 |
---|---|
City | St.Louis, MO, USA |
Period | 14/11/93 → 17/11/93 |
Other files and links
Fingerprint
Dive into the research topics of 'ANN based forecasting of VBR video traffic for dynamic bandwidth allocation in ATM networks'. Together they form a unique fingerprint.
View full fingerprint
Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver
Chong, S., Li, S. Q., & Ghosh, J. (1993). ANN based forecasting of VBR video traffic for dynamic bandwidth allocation in ATM networks. 275-280. Paper presented at Proceedings of the 1993 Artificial Neural Networks in Engineering, ANNIE'93, St.Louis, MO, USA.
Chong, Song ; Li, San qi ; Ghosh, Joydeep. / ANN based forecasting of VBR video traffic for dynamic bandwidth allocation in ATM networks. Paper presented at Proceedings of the 1993 Artificial Neural Networks in Engineering, ANNIE'93, St.Louis, MO, USA.6 p.
@conference{c6f2211777c24036985c6dbe7be6ca0a,
title = "ANN based forecasting of VBR video traffic for dynamic bandwidth allocation in ATM networks",
abstract = "Two time delay neural network based forecasting systems are proposed to perform dynamic bandwidth reservation for real-time, variable bit rate (VBR) video service in ATM networks. The networks are found to give highly reliable predictions even in a non-stationary environment. Their performance is quantified through simulation experiments on clippings from the movie, `Star Wars'. In particular, the time-delay pi-sigma network based dynamic bandwidth reservation achieves high network utilization, loss-free transmission and reasonable delay, and its lower computational requirements make it suitable for on-line operation.",
author = "Song Chong and Li, {San qi} and Joydeep Ghosh",
year = "1993",
language = "English",
pages = "275--280",
note = "Proceedings of the 1993 Artificial Neural Networks in Engineering, ANNIE'93 ; Conference date: 14-11-1993 Through 17-11-1993",
}
Chong, S, Li, SQ & Ghosh, J 1993, 'ANN based forecasting of VBR video traffic for dynamic bandwidth allocation in ATM networks', Paper presented at Proceedings of the 1993 Artificial Neural Networks in Engineering, ANNIE'93, St.Louis, MO, USA, 14/11/93 - 17/11/93 pp. 275-280.
ANN based forecasting of VBR video traffic for dynamic bandwidth allocation in ATM networks. / Chong, Song; Li, San qi; Ghosh, Joydeep.
1993. 275-280 Paper presented at Proceedings of the 1993 Artificial Neural Networks in Engineering, ANNIE'93, St.Louis, MO, USA.
Research output: Contribution to conference › Paper › peer-review
TY - CONF
T1 - ANN based forecasting of VBR video traffic for dynamic bandwidth allocation in ATM networks
AU - Chong, Song
AU - Li, San qi
AU - Ghosh, Joydeep
PY - 1993
Y1 - 1993
N2 - Two time delay neural network based forecasting systems are proposed to perform dynamic bandwidth reservation for real-time, variable bit rate (VBR) video service in ATM networks. The networks are found to give highly reliable predictions even in a non-stationary environment. Their performance is quantified through simulation experiments on clippings from the movie, `Star Wars'. In particular, the time-delay pi-sigma network based dynamic bandwidth reservation achieves high network utilization, loss-free transmission and reasonable delay, and its lower computational requirements make it suitable for on-line operation.
AB - Two time delay neural network based forecasting systems are proposed to perform dynamic bandwidth reservation for real-time, variable bit rate (VBR) video service in ATM networks. The networks are found to give highly reliable predictions even in a non-stationary environment. Their performance is quantified through simulation experiments on clippings from the movie, `Star Wars'. In particular, the time-delay pi-sigma network based dynamic bandwidth reservation achieves high network utilization, loss-free transmission and reasonable delay, and its lower computational requirements make it suitable for on-line operation.
UR - http://www.scopus.com/inward/record.url?scp=0027898017&partnerID=8YFLogxK
M3 - Paper
AN - SCOPUS:0027898017
SP - 275
EP - 280
T2 - Proceedings of the 1993 Artificial Neural Networks in Engineering, ANNIE'93
Y2 - 14 November 1993 through 17 November 1993
ER -
Chong S, Li SQ, Ghosh J. ANN based forecasting of VBR video traffic for dynamic bandwidth allocation in ATM networks. 1993. Paper presented at Proceedings of the 1993 Artificial Neural Networks in Engineering, ANNIE'93, St.Louis, MO, USA.