Forecasting model of building energy consumption based on parallel Kriging sampling algorithm

Parallel Kriging sampling approach (PEIGF) with minimum computing resources is proposed to promote the speed of building energy consumption. In each iteration of PEIGF, the initial sample point is obtained by maximizing the standard expected improvement global fit (EIGF) criterion and the parallel EIGF function is constructed to obtain multiple new sample points by maximizing the PEIGF criterion. Performance of PEIGF is evaluated by comparing the obtained results with four other existing sequence approaches and four artificial intelligence (AI) based models. The results reveal that PEIGF stands out for most of the test cases with good predictive accuracy and computing efficiency. PEIGF runs 4.7-11.6 times, 5.1-12.4 times, 5.0-14.8 times, and 19.7-158.6 times faster than those of combined expectation (CE), EIGF, expected improvement for global fit based on gradient (EIGFG) and maximum mean square error (MMSE) sampling. It obtains the least root mean squared errors for energy consumption prediction, and reduces the total number of samples by 14.9% (heating load) and 14.1% (cooling load), as well as 16.7% compared with other four AI-based models. It is proven to be a promising technique to plan low-cost energy management and facilitate early designs or renovation of energy conserving buildings.