Various techniques, including feed-forward neural networks, are applied to the time series prediction problem. The forecasting of occupancy on a telephone trunk group is taken as a case study. The relative performances of the techniques are reported. Theoretical justifications are provided for the results.

In this paper the application of neural networks to some of the network management tasks carried out in a regional Bell telephone company is described. Network managers monitor the telephone network for abnormal conditions and have the ability to place controls in the network to improve traffic flow. Conclusions are drawn regarding the utility and effectiveness of the neural networks in automating the network management tasks.

A report is given on an expert system called NOAA, Network Operations Analyzer and Assistant, that manages the Pacific Bell Californian telephone network. Progress towards automatic implementation of expansive controls is complete. Progress towards restrictive controls is partially complete. Comments are made on current research including the use of neural networks for Time Series Prediction.

The control of telephony traffic is the task of network management and routing algorithms. In this paper, a study of two trunk groups carrying telephony traffic is used to show that instabilities can arise if there is a delay in getting feedback information for a network controller. The network controller seeks to balance the traffic in the two trunk groups, which may represent two paths from a source to a destination. An analysis shows how factors such as holding time, controller gain and feedback delay influence stability. Simulation of a two service case is also carried out to show that the same instabilities can arise.