Two methods of dynamic channel allocation using neural networks are investigated. Both methods continuously optimize the mobile network based on changes in calling traffic. The first method uses backpropagation model predictions to aid the channel allocator. Each cell contains a backpropagation model which provides the channel allocator a call traffic prediction allowing the channel allocator to effectively optimize the network. The second method uses the same backpropagation models along with actor-critic models to perform the channel allocation. The actor-critics learn to model traffic activity between adjacent cells in real-time, and thereby learn to allocate channels dynamically between cells. The learning criterion is used to minimize the number of subscribers lost from each cell. A comparison shows that both methods significantly outperform fixed channel allocation, even when the call traffic activity deviates from the previously learned models of the call traffic activity. The implementation and continual adaptation characteristics are illustrated and discussed.
- Actor-Critic Models,
- Adjacent Cells,
- Backpropagation,
- Backpropagation Model Predictions,
- Call Traffic Activity,
- Call Traffic Prediction,
- Calling Traffic,
- Cellular Radio,
- Channel Allocator,
- Continual Adaptation Characteristics,
- Dynamic Channel Allocation,
- Fixed Channel Allocation,
- Learned Models,
- Learning Criterion,
- Mobile Network,
- Neural Nets,
- Neural Network Controlled Allocation,
- Radio Networks,
- Telecommunication Computing,
- Telecommunication Congestion Control,
- Telecommunication Traffic,
- Traffic Activity
Available at: http://works.bepress.com/kelvin-erickson/4/