TABLE OF CONTENTS A reliable, continuous supply of electric energy is essential for the functioning of today's complex societies. Due to a combination of increasing energy consumption and impediments of various kinds to the extension of existing electric transmission networks, these power systems are operated closer and closer to their limits. This situation requires a significantly less conservative power system operation and control regime which, in turn, is possible only by monitoring the system state in much more detail than was necessary previously.
Fortunately, the large quantity of information required can be provided in many cases through recent advances in telecommunications and computing techniques. There is, however, a lack of evaluation techniques required to extract the salient information and to use it for higher-order processing. Whilst the sheer quantity of available information is always a problem, this situation is aggravated in emergency situations when rapid decisions are required. Furthermore, the behaviour of power systems is highly non-linear. Monitoring and control involves several hundred variables which are only partly available by measurements. Load demands and dynamic loads are difficult to model. Therefore models appropriate for normal situations might become invalid in emergency situations.
These problems provide important motivation to explore novel data processing and programming techniques from the vast pool of artificial intelligence techniques.
The following section gives a short introduction to static security assessment. In Section 3 we discuss merits and pitfalls of different artificial intelligence approaches. We will then focus on the application of artificial neural...
