Study and application of non-linear time series prediction in ground source heat pump system

This paper presents the calculation of economic indicators which can reflect the geothermal energy utilization of ground source heat pump system. We forecast the technical and economic indicators based on the non-liner time-series data from ground source heat pump and building integrated systems. The paper selects SMOreg and M5P two different non-liner algorithms for forecasting. Through comparing the predictable results from two algorithms, the experimental results show that SMOreg algorithm has higher accuracy when predicting the indicators. In addition, we select more data to experiment for further verifying the forecast accuracy of SMOreg algorithm.