AT-96-21-4 -- Optimising System Control with Load Prediction by Neural Networks for an Ice- Storage System PDF

Describes the performance of a partial ice storage system with a controller that predicts the load by neural networks. Compares the two control strategies - chiller priority control and predictive control - using simulation. Chiller priority is the commonest control strategy for existing thermal storage systems. The predictive control proposed in the study uses an hourly thermal load prediction by neural networks. Describes the predictive control in detail. Finds that the accuracy of the load prediction is a key for optimising the system control. The predictive control can significantly reduce the operating cost without energy shortage.

KEYWORDS: year 1996, Energy storage, ice storage, controls, expert systems, computer programs, comparing, predictive controls, weather, accuracy