The authors present an intelligent distribution control system operating in conjunction with a SCADA system with minimum supervision and interaction with a human operator. The application of a model-based expert system results in an intelligent power distribution system with learning, self organising and diagnostic capabilities. The work deviates from previous approaches in two important aspects: the use of model-based reasoning allows many different application knowledge bases (e.g. fault diagnosis, restoration, maintenance planning, etc.) to operate on the common model of the distribution network thus making it very compact and versatile, and it introduces for the first time the concept of intelligence in a power distribution system. To support modular development and simple maintenance of the expert system, the knowledge required to do the reasoning has been separated into a model of the distribution system and several knowledge bases which work on it. The frame-based object-oriented knowledge representation provides the flexibility to extend the model without adversely affecting the performance. The expert system has been tested extensively for operation with a real-time 22 kV SCADA system covering a large area of 180 substations. The expert system gives accurate fault analysis for all the fault cases and proposes the best restoration plans in less than 15 seconds. In addition, it advises the control centre operators in cases of emergency, helps them in maintenance planning and can be used as a training simulator in offline mode.