发明名称 |
Method for data transmission in a communication network |
摘要 |
A method for data transmission from a first node to a second node in a communication network includes: analyzing data arriving in a buffer of the first node to generate an arrival history curve describing the amounts of data arriving in the buffer over a past time period; processing the arrival history curve to generate a plurality of signals corresponding to filtered components of the wavelet transform; processing each signal in a separate neural network trained with training patterns based on previously received and buffered data to generate forecast signals for future data arrivals; recombining the forecast signals to generate an arrival forecast curve describing the amounts of data arriving in the buffer in a future period; the first node generating bandwidth reservation requests based on the arrival forecast curve and transmitting the bandwidth requests to the second node; the second node allocating bandwidth based on the bandwidth requests; and transmitting data from the first node to the second node within the allocated bandwidth. |
申请公布号 |
US8811427(B2) |
申请公布日期 |
2014.08.19 |
申请号 |
US201113579137 |
申请日期 |
2011.01.28 |
申请人 |
Siemens Aktiengesellschaft |
发明人 |
Mogre Parag;Vernet Guillaume;Ziller Andreas |
分类号 |
H04J3/16;H04L12/56;H04L12/64 |
主分类号 |
H04J3/16 |
代理机构 |
King & Spalding L.L.P. |
代理人 |
King & Spalding L.L.P. |
主权项 |
1. A method for data transmission in a communication network comprising a plurality of nodes where a data transmission from a first node to a second node in the network comprises:
(a) analysing data arriving in a data buffer of the first node such that an arrival history curve describing the amounts of data arriving in the buffer over a past time period is generated; (b) processing the arrival history curve, said processing including a wavelet transform on the arrival history curve and resulting in a plurality of signals, each signal corresponding to a filtered component of the wavelet transform; (c) processing each signal in a separate neural network trained with training patterns which are based on data arrived in the past in the buffer, resulting in forecast signals for data arrivals in the future; (d) recombining the forecast signals resulting in an arrival forecast curve describing the amounts of data arriving in the buffer in a future time period; (e) the first node generating bandwidth requests for reserving bandwidth based on the arrival forecast curve and transmitting the bandwidth requests to the second node; (f) the second node allocating bandwidth based on the bandwidth requests received from the first node; and (g) transmitting data from the first node to the second node within the allocated bandwidth. |
地址 |
Munich DE |