We examine the impact of wholesale markets on operations of the bulk power system and elaborate some basic implications of engineering practices for designs of wholesale markets. This analysis is intended to provide a basis for enhancements to existing principles of engineering management. Wholesale markets bring economic and financial aspects that alter the context in which system operations are conducted, and introduce incentive and benefit-cost considerations that might alter operating procedures that previously were based on reliability considerations. The principles addressed are those relevant to the interface between engineering aspects of system operations, and economic aspects of market operations. We outline ways that engineering practices developed in the era of vertically integrated utilities might be adapted to the wholesale markets introduced since restructuring began in 1998 in the United States.

A brief overview is given of the nature of present day artificial neural net computing and the authors emphasize the theme that in this mode of computing, knowledge is not represented symbolically, but in the form of distributed processing and localized decision rules. The authors propose that in neural-net computing, the processing is the representation. In other words, the very nature of the processing encodes the knowledge. There is no place and no need for a separate body of global rules to be used by the network for inferencing. If rules exist at all, they are in the nature of local processing steps carried out at individual processors in response to stimuli from other neurons. The authors develop this theme together with a theme which is closely related to it. The second notion is that neural networks may also be thought of and implemented in terms of heterogeneous networks, rather than always or only in terms of massive arrays of identical elemental processors.>

A novel approach to the analysis of transient signals is proposed and demonstrated. This approach is based on the use of a neural net to estimate the future values of a transient time sequence. In the course of training the net, it learns a model of the process which is the source of the transient signal. This type of analysis is similar to the act of parsing in syntactic pattern recognition, and the act of synthesizing a model of the process is similar to grammar inference in syntactic pattern recognition, except that in the present case the signal values are numeric and are continuously valued. The approach is demonstrated with use of a nonlinear dynamic model as the signal generator. With this model, it is possible to move from simple signal environments to chaotic regions. Numerical results are presented to illustrate highly accurate predictive estimates of the signal source output

Pattern-recognition based methodology implemented in the architecture of artificial neural networks can be used to model knowledge-intensive feedback control systems. The procedure for development and practical design of a neural-net based control system is described and demonstrated by the example of a nonlinear hydraulic system. The neural-net control system has been trained to provide stabilizing controls and to detect and identify malfunctioning sensors. The results of computer simulations and experiments are presented to illustrate the proposed approach. They show that the neural-net control system is capable of maintaining any desired level of liquid in a tank, for tanks of various shapes; of stabilizing the system in the presence of large disturbances; of detecting and identifying defective level sensors; and of estimating parameters in nonlinear processes.>