Method for data transmission in a communication network

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.