In this paper, the use of fuzzy neural network (FNN) to identify appropriate Box-Jenkins models for the electricity load forecasting in Hong Kong is presented. FNN is found to be suitable for identifying the Box-Jenkins model. By using such model, one can forecast the load accurately.

In this paper we will utilize the GA algorithm to evolve the weight and the interconnection of the neural network to solve the unit commitment problem. We will emphasize on the determination of the appropriate GA parameters to evolve the neural network, i.e. the population size and probabilities of crossover and mutation, and the method used for selection amongst generations such as tournament selection, roulette wheel selection and ranking selection. Performance comparisons are conducted to analyze the learning curve of different parameters, to find out which has a dominant influence on the effectiveness of the algorithm.

The overall design issues for broadband asynchronous transfer mode (ATM) networks are investigated. Three kinds of network design requirements are considered: user grade-of-service (GOS) requirements, network manager requirements, and system designer requirements. The design balance among user, network manager, and designer performance measures is shown. It is shown that the design parameters for broadband ATM exchange can be tuned within the acceptable sets by the layering concept on performance objectives.>