Power Systems Application of Artificial Neural Networks. (ANN) Introduction Brief history. Structure How they work Sample Simulations. (EasyNN) Why use them (Merits and Demerits)? Current Applications NN & Power Systems Conclusion
Introduction Derived from biological neuron. Connection of processing nodes that transfer activity to the next. Likened to the Brain. Mostly one-way connection. Architecture Feedforward Feedback Network Layers Perceptron
Architecture FeedforwardPerceptron Network
How They Work. Inputs to NN compared with pre- processed data. Outputs compared to desired response. NN “learn” system patterns. NN are “trained” to respond. Learning Supervised Unsupervised Reinforced EasyNN software.
EasyNN Not the best model for NN
Output Graph
Why Use NN (Merits)? Adaptive Learning Self Organization Real-Time Organization. Fault Tolerance.
Current Applications. Sales Forecasting Industrial Process Control Data Validation Risk Management (Insurance) Banking (loan processing). Medical
Power Systems Application. Integrated Power Systems. Load Forecasting (Blackout) Power Plants. Many other areas.
Conclusion. NN – great potential for future systems. Need for much more research. Could prove vital in power management and distribution.