Research on the Prediction of the Water Demand of Construction Engineering Based on the BP Neural Network

Table 5

Prediction results of different models.

Time	Actual water consumption	BP	PSO-BP	GA-BP	Pluralistic return
21 June	1430.37	1397.56	1446.50	1449.50	967.29
22 June	860.32	605.91	857.48	883.10	554.43
23 June	610.36	702.29	581.46	633.88	571.73
24 June	604.13	876.12	615.22	557.52	516.61
25 June	1560.54	1367.86	1528.54	1619.99	463.06
26 June	1910.00	2315.52	1888.37	1876.97	468.56
27 June	752.87	618.75	786.22	779.86	485.53
28 June	758.39	722.45	763.90	746.23	420.71
29 June	1601.37	1409.33	1668.54	1719.87	551.14
30 June	702.36	1029.35	673.01	655.37	450.15