Application of Improved Least Squares Support Vector Machine in the Forecast of Daily Water Consumption
In order to better predict city daily water consumption to achieve the optimal scheduling of city water supply system, based on the research progress summarizing the city daily water consumption forecasting at home and abroad, we take the predicted daily water consumption main influence factors and predicted daily related water use after noise reduction as input, and the predicted daily water consumption after noise reduction as output. In addition, we adopt the multiple scale chaos genetic with strong global search capability and faster search speed to optimize the parameters of least square support vector machine. Moreover, we establish a prediction model of daily water consumption of least squares support vector machine based on wavelet multiple scale chaos genetic. The case analysis results show that the model proposed in this paper has strong prediction ability, compared with the least square support vector machine prediction model based on multiple scale chaos genetic, least square support vector machine prediction model based on wavelet, and prediction model based on genetic least square support vector machine algorithm. At last, it is concluded that the improved least square support vector machine has good performance in the application in daily water consumption prediction.
KeywordsLeast squares support vector machine Daily water consumption prediction Chaos optimization Modeling prediction
The authors acknowledge the National Natural Science Foundation of China (Grant No. 61662045).
Funding was provided by National Natural Science Foundation of China (Grant No. 61662045) and the Science & Technology Foundation for Selected overseas Chinese scholar of Tianjin 2017.
- 1.Pham, B. T., Bui, D. T., Dholakia, M. B., Prakash, I., & Pham, H. V. (2016). A comparative study of least square support vector machines and multiclass alternating decision trees for spatial prediction of rainfall-induced landslides in a tropical cyclones area. Geotechnical and Geological Engineering, 34(6), 1807–1824.CrossRefGoogle Scholar
- 9.Zhang, Y., Huang, J., & Xu, K. (2015). Indoor positioning algorithm for WLAN based on principal component analysis and least square support vector regression. Yi Qi Yi Biao Xue Bao/Chinese Journal of Scientific Instrument, 36(2), 408–414.Google Scholar