Mark J. Damborg

Electric load forecasting using an artificial neural network

An artificial neural network (ANN) approach is presented for electric load forecasting. The ANN is used to learn the relationship among past, current and future temperatures and loads. In order to provide the forecasted load, the ANN interpolates among the load and temperature data in a training data set. The average absolute errors of the 1 h and 24 h-ahead forecasts in tests on actual utility data are shown to be 1.40% and 2.06%, respectively. This compares with an average error of 4.22% for 24 h ahead forecasts with a currently used forecasting technique applied to the same data. >

Suboptimal control of linear systems with state and control inequality constraints

A suboptimal controller based upon on-line quadratic programming is described. Theoretical results are presented to show that such a controller is optimal under the assumption that there are no constraints on the computation time. Finally, an implementation of a suboptimal controller that takes such constraints into account is described.

Heuristically enhanced feedback control of constrained discrete-time linear systems

Recent advances in computer technology have spurred new interest in the use of feedback controllers based upon on-line minimization for the control of constrained linear systems. Still the use of computers in the feedback loop has been hampered by the fact that the amount of time available for computation in most sampled data systems is not enough to achieve a complete solution using conventional algorithms. Several “ad hoc” techniques have been proposed, but their applicability is restricted by the lack of supporting theory. In this paper we present a theoretical framework to analyze the stability of the closed-loop system resulting from the use of on-line optimization in the feedback loop. Using these results we show that a suboptimal algorithm, based upon the use of heuristic search techniques, yields asymptotically stable systems, provided that enough computation power is available to solve at each sampling interval an optimization problem considerably simpler than the original. The controller presented in this paper is valuable for situations where the customary approaches of using Pontryagins minimum principle or storing a family of extremal curves are not applicable due to limitations in the computational resources available.

Artificial neural networks for power system static security assessment

An artificial neural network (ANN) is used to assess the static security of a test system. It is demonstrated that an ANN can be a useful tool for static security assessment of power systems. It is shown that ANNs perform significantly better than a nearest-neighbor search in terms of classification, recall time, and data storage requirements. The ANN, however, requires a great deal of time for offline training. This problem is compounded as the system size increases. Learning complexity theory can be used to better understand this scaling problem. Alterations which may lead to better performance include accelerated learning algorithms and the use of oracle-based learning.<<ETX>>

Short term electric load forecasting using an adaptively trained layered perceptron

The authors address electric load forecasting using artificial neural network (NN) technology. They summarize research for Puget Sound Power and Light Company. In this study, several structures for NNs are proposed and tested. Features extraction is implemented to capture strongly correlated variables to electric loads. The NN is compared to several forecasting models. Most of them are commercial codes. The NN performed as well as the best and most sophisticated commercial forecasting systems.<<ETX>>

An adaptive controller for a one-legged mobile robot

An adaptive controller based upon the online minimization of a performance criterion is described. The adaptive controller is used to improve the performance of a one-legged mobile robot, removing problems experienced with previous controllers. Specifically, this controller eliminates the problem of a bias in the forward velocity experienced with the nonadaptive controller and, at the same time, provides the flexibility required to allow a dynamically stabilized legged machine to perform satisfactorily under the widely varying conditions that exist in the real world. The performance of several minimization algorithms is analyzed, and the adaptive step size random search algorithm is selected. Finally, a series of experiments illustrating the ability of the adaptive controller to handle a changing environment is presented. >

Application of Relational Database to Computer-Aided-Engineering of Transmission Protection Systems

When applying computer aids to engineering problems, a major difficulty is data handling. We have used a database management system as the central strucutre for a package of computer-aided-engineering (CAE) software for utility engineers concerned with transmission system protection. This paper discusses the design of the database and its role in the CAE package. The use of database management systems in all such CAE tools is discussed.

Potential of artificial neural networks in power system operation

The potential applicability of artificial neural networks (ANNs) to electric power systems, with an emphasis on aiding dispatchers with decision-making (particularly with decisions relating to power system security), is discussed. Examples illustrate how ANNs can alert dispatchers to security threats due to possible constraint violations, unstable dynamics, and uncertain loads. The problems that must be overcome before an ANN dispatchers aid is realizable are reviewed.<<ETX>>

Fundamental Structure of Input-Output Stability for Feedback Systems

An approach to the input-output stability of feedback systems is discussed. This approach incorporates the natural inverse operator model to describe these systems. Using this operator, the input-output stability problem is decomposed into five subproblems. One of these subproblems involves the causality of the input-output operator, a property not recognized in previous feedback system stability studies. Following the development of the model and the stability definition some general stability theorems are presented.

Web-based tutoring in power engineering

This paper deals with the application of web-based technologies to power engineering education in an interactive student/mentor environment. The modern teaching/learning concepts and new technologies to support these concepts have been developed. This project incorporates web-based tools, including Internet, videoconferencing, and educational intelligent system modules for power engineering education. Different student learning styles are adapted for power engineering applications. The proposed interactive learning environment allows the mentor and students to best utilize the facilities for effective teaching and learning.