Machine Learning Approaches For Building Energy Consumption Prediction

With the growth of population and the development of economy,more and more energy is consumed in the residential and office buildings.Therefore,it is necessary to seek for some strategies that can reduce the energy consumption in building.Building energy conservation plays an important role in the field of reduce energy consumption.However,some ubiquitous issues,e.g.,the poor building management and the unreasonable task scheduling,are impeding the efficiency of the energy conservation policies.To improve the level of building management and the reasonable of building equipment's task scheduling,one effective way is to provide accurate prediction of the building energy consumption.Nowadays,numerous data-driven artificial intelligence approaches have been proposed for building energy consumption prediction and obtained well performances.Nevertheless,the historical building energy consumption data have high levels of uncertainties and randomness due to the influence of the human distribution,the thermal environment,the weather conditions and the working hours in buildings.This lead to accurate and reasonable prediction is difficult.To obtain more accurate and reasonable prediction results,this study take three strategies into account.The first strategy is adopting the more powerful modeling methods to learn the information hidden in the historical data.The second strategy is to incorporate the knowledge or patterns from our experience or data into the prediction models.The last one is to construct a predictive model with the linguistic outputs.This mainly contents of this thesis are listed as follows.First of all,for improving the accuracy of building energy consumption prediction,an extreme deep learning technique is presented.The proposed approach combines the stacked autoencoder(SAE)with the extreme learning machine(ELM)to take advantage of their respective characteristics.In this proposed approach,the SAE is used to extract the building energy consumption features,while the ELM is utilized as a predictor to obtain accurate prediction results.Additionally,in order to examine the performances of the proposed approach,it is compared with some popular machine learning methods,such as the backward propagation neural network(BPNN),support vector regression(SVR),the generalized radial basis function neural network(GRBFNN)and multiple linear regression(MLR).Experimental results demonstrate that the proposed method has the best prediction performance in different cases of the building energy consumption.And then,a modified deep belief network based hybrid model is proposed in order to further improve the accuracy of building energy consumption prediction.The proposed hybrid model combines the outputs from the DBN model with the energy-consuming pattern to yield the final prediction results.The energy-consuming pattern in this study represents the periodicity property of building energy consumption and can be extracted from the observed historical energy consumption data.The residual data generated by removing the energy-consuming pattern from the original data are utilized to train the modified DBN model.The training of the modified DBN includes two steps,the first one of which adopts the contrastive divergence(CD)algorithm to optimize the hidden parameters in a pre-train way,while the second one determines the output weighting vector by the least squares method.In order to examine the advantages of the proposed model,four popular artificial intelligence methods,the backward propagation neural network(BPNN),the generalized radial basis function neural network(GRBFNN),the extreme learning machine(ELM),and the support vector regression(SVR)are chosen as the comparative approaches.Experimental results demonstrate that the proposed DBN based hybrid model has the best performance compared with the comparative techniques both in experiments with various energy-consuming patterns.At last,a great majority of predictive model only can give us point estimation,however,the reasonability and interpretability of such prediction results are not powerful.To solve this issue,this study extends the crisp weights of fuzzy neural network(FNN)to fuzzy ones to obtain linguistic outputs.And,a data-driven design method is proposed to construct this kind of fuzzily weighted FNN(FW-FNN).The proposed model is applied for predicting building energy consumption and the simulation results demonstrate that the linguistic outputs can effectively capture the uncertainties and randomness in the observed data.