Abstract: A method, processing system and processor-readable medium for generating network configurations using a graph neural network (GNN) are provided. The method may include receiving a first matrix M generated based on a set of network requirements; storing a GNN having a plurality of nodes v and a plurality of edges; initializing the GNN based on a second matrix Xv having a plurality of elements, each element corresponding to a node from a plurality of nodes v of the GNN; and generating an output matrix having a plurality of nodes labelled based on the first matrix M.

Abstract: A method, processing system and processor-readable medium for generating network configurations using a graph neural network (GNN) are provided. The method may include receiving a first matrix M generated based on a set of network requirements; storing a GNN having a plurality of nodes v and a plurality of edges; initializing the GNN based on a second matrix Xv having a plurality of elements, each element corresponding to a node from a plurality of nodes v of the GNN; and generating an output matrix having a plurality of nodes labelled based on the first matrix M.

Abstract: A method, system, and medium are provided for controlling power usage in a wireless telecommunications network, the method comprising transmitting a pilot signal to a mobile station over a wireless channel, receiving a response that includes a signal-to-interference-and-noise ratio associated with said pilot signal, determining an instantaneous channel rate to be used for a subsequent data transmission to said mobile station based at least on said signal-to-interference-and-noise ratio, selecting a transmit power level for said data transmission; and transmitting data to said mobile station at said channel rate and said power level.

Abstract: A method, system, and medium are provided for controlling power usage in a wireless telecommunications network, the method comprising transmitting a pilot signal to a mobile station over a wireless channel, receiving a response that includes a signal-to-interference-and-noise associated with said pilot signal, determining an instantaneous channel rate to be used for a subsequent data transmission to said mobile station based at least on said signal-to-interference-and-noise, selecting a transmit power level for said data transmission; and transmitting data to said mobile station at said channel rate and said power level.

Abstract: A method and system, are provided for dynamically allocating channel resources in a wireless network. The wireless network may be a multi-rate network having a base station controller that adapts wireless channel rates associated with a communication session based on a TCP sending rate associated with a sending device. The base station controller includes a scheduler and optimization engine that probes the wireless network to gather TCP parameters, such as round trip times, etc. The optimization engine utilizes a long-term sending rate to generate a subset of channel rates from available channel rates associated with the wireless network. The scheduler engine utilizes the instantaneous sending rate to adapt the wireless channel rate by selecting a channel rate from the subset of channel rates.

Abstract: A media, method, and system, are provided for dynamically allocating channel resources to multiple TCP sessions in a wireless network. The wireless network may be a multi-rate network having a base station controller that adapts wireless channel rates associated with a communication session based on a preemption probability associated with a high-rate channel. The base station controller includes a scheduler and optimization engine that probes the wireless network to gather TCP parameters, such as round trip times, etc. The optimization engine utilizes a long-term sending rate to generate a subset of channel rates from available channel rates associated with the wireless network. The scheduler engine utilizes the instantaneous sending rate to adapt the wireless channel rate by selecting a channel rate from the subset of channel rates.

Abstract: A call admission method and apparatus are disclosed which maximizes the wireless channel utilization subject to a predetermined bound on the call dropping and packet loss probabilities for variable-bit-rate traffic in a packet switched network. The call admission scheme is stochastic and dynamic, hence it is able to adapt to a wide range of traffic fluctuations and mobility patterns. The call admission scheme disclosed satisfies a set of constraints on call dropping and packet loss probabilities while maintaining high bandwidth utilization.