Study On The Application Of BP Neural Network In The Prediction Of Office Building Energy Consumption

With the rapid development of network technology, people are increasingly dependent on the internet. When BP neural network (BNN) performs simulation calculation, it has the advantages of fast training speed, high accuracy, and strong robustness and is widely used in large-scale public (LSP) building energy consumption (BEC) monitoring platforms (LPB). Therefore, the purpose of this paper to study the energy consumption monitoring platform of large public (LP) buildings is to better monitor the energy consumption of public buildings, so as to supplement or remedy at any time. This article mainly uses the data analysis method and the experimental method to carry on the relevant research and the system test to the BNN. The experimental results show that the monitoring system (MS) platform designed in this paper has real-time performance, and its time consumption is between 2 s and 3 s, and the data accords with theory and reality.

Download Full-text

Research on the Combined Prediction Model of Residential Building Energy Consumption Based on Random Forest and BP Neural Network

Geofluids ◽

10.1155/2021/7271383 ◽

2021 ◽

Vol 2021 ◽

pp. 1-12

Author(s):

Xuenan Zhang ◽

Jinxin Zhang ◽

Jinhua Zhang ◽

YuChuan Zhang

Keyword(s):

Neural Network ◽

Energy Efficiency ◽

Energy Consumption ◽

Random Forest ◽

Prediction Model ◽

Bp Neural Network ◽

Residential Building ◽

Building Energy ◽

Building Energy Consumption ◽

Data Set

As the energy consumption of residential building takes a large part in the building energy consumption, it is important to promote energy efficiency in residential building for green development. In order to evaluate the energy consumption of residential building more effectively, this paper proposes a combined prediction model based on random forest and BP neural network (RF-BPNN). To verify the prediction effect of the RF-BPNN combined model, experiments were performed by using the energy efficiency data set in the UCI database, and the model was evaluated with five indicators: mean absolute error, root mean square deviation, mean absolute percentage error, correlation coefficient, and coincidence index. Compared with the random forest, BP neural network model, and other existing models, respectively, it is proven by the experimental results that the RF-BPNN model possesses higher prediction accuracy and better stability.

Download Full-text

Study and analysis of office building energy consumption performance in severe cold and cold region, China

Advances in Mechanical Engineering ◽

10.1177/1687814017734110 ◽

2017 ◽

Vol 9 (11) ◽

pp. 168781401773411 ◽

Cited By ~ 1

Author(s):

Zequn Ding ◽

Hongqing Zhu ◽

Yang Wang ◽

Xiaoling Ge

Keyword(s):

Energy Consumption ◽

Building Energy ◽

Office Building ◽

Building Energy Consumption ◽

Cold Region

Download Full-text

An Artificial Neural Network-Based Prediction of Government-Owned Building Energy Consumption with Design Variables

ICSDEC 2012 ◽

10.1061/9780784412688.001 ◽

2012 ◽

Author(s):

H. Son ◽

S. Lee ◽

C. Kim

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Energy Consumption ◽

Building Energy ◽

Building Energy Consumption ◽

Design Variables ◽

Artificial Neural

Download Full-text

Regression models for predicting UK office building energy consumption from heating and cooling demands

Energy and Buildings ◽

10.1016/j.enbuild.2012.12.005 ◽

2013 ◽

Vol 59 ◽

pp. 214-227 ◽

Cited By ~ 65

Author(s):

Ivan Korolija ◽

Yi Zhang ◽

Ljiljana Marjanovic-Halburd ◽

Victor I. Hanby

Keyword(s):

Energy Consumption ◽

Regression Models ◽

Building Energy ◽

Office Building ◽

Building Energy Consumption ◽

Heating And Cooling

Download Full-text

Impact of Building Orientation and Window-Wall Ratio on the Office Building Energy Consumption

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.409-410.606 ◽

2013 ◽

Vol 409-410 ◽

pp. 606-611 ◽

Cited By ~ 4

Author(s):

Zhen Yu ◽

Wei Lin Zhang ◽

Ting Yong Fang

Keyword(s):

Energy Consumption ◽

Air Conditioning ◽

Building Energy ◽

Simulation Software ◽

Office Building ◽

Building Energy Consumption ◽

Total Energy Consumption ◽

Building Orientation ◽

Heating Energy Consumption ◽

Energy Consumption Simulation

Using the energy consumption simulation software to research the HVAC in fall air conditioning mode, different building orientation and window-wall ratio of the office building energy consumption. The study found that the heating energy consumption, air-conditioning energy consumption and total energy consumption is gradually increased with the increase of the window-wall ratio under the same orientation. The result provides some reference for public buildings in setting of building orientation and window-wall ratio.

Download Full-text

Building Energy Consumption Raw Data Forecasting Using Data Cleaning and Deep Recurrent Neural Networks

Buildings ◽

10.3390/buildings9090204 ◽

2019 ◽

Vol 9 (9) ◽

pp. 204 ◽

Cited By ~ 5

Author(s):

Yang ◽

Tan ◽

Santamouris ◽

Lee

Keyword(s):

Neural Network ◽

Neural Networks ◽

Energy Consumption ◽

Missing Data ◽

Recurrent Neural Networks ◽

Building Energy ◽

Building Energy Consumption ◽

Data Set ◽

Raw Data ◽

Deep Recurrent Neural Network

With the rising focus on building energy big data analysis, there lacks a framework for raw data preprocessing to answer the question of how to handle the missing data in the raw data set. This study presents a methodology and framework for building energy consumption raw data forecasting. A case building is used to forecast the energy consumption by using deep recurrent neural networks. Four different methodologies to impute missing data in the raw data set are compared and implemented. The question of sensitivity of gap size and available data percentage on the imputation accuracy was tested. The cleaned data were then used for building energy forecasting. While the existing studies explored only the use of small recurrent networks of 2 layers and less, the question of whether a deep network of more than 2 layers would be performing better for building energy consumption forecasting should be explored. In addition, the problem of overfitting has been cited as a significant problem in using deep networks. In this study, the deep recurrent neural network is then used to explore the use of deeper networks and their regularization in the context of an energy load forecasting task. The results show a mean absolute error of 2.1 can be achieved through the 2*32 gated neural network model. In applying regularization methods to overcome model overfitting, the study found that weights regularization did indeed delay the onset of overfitting.

Download Full-text

Neural-Network-Based Building Energy Consumption Prediction with Training Data Generation

Processes ◽

10.3390/pr7100731 ◽

2019 ◽

Vol 7 (10) ◽

pp. 731 ◽

Cited By ~ 1

Author(s):

Sanghyuk Lee ◽

Jaehoon Cha ◽

Moon Keun Kim ◽

Kyeong Soo Kim ◽

Van Huy Pham ◽

...

Keyword(s):

Neural Network ◽

Energy Consumption ◽

False Negative ◽

Building Energy ◽

Training Data ◽

Superior Performance ◽

Data Generation ◽

Building Energy Consumption ◽

Data Set ◽

Input Variables

The importance of neural network (NN) modelling is evident from its performance benefits in a myriad of applications, where, unlike conventional techniques, NN modeling provides superior performance without relying on complex filtering and/or time-consuming parameter tuning specific to applications and their wider ranges of conditions. In this paper, we employ NN modelling with training data generation based on sensitivity analysis for the prediction of building energy consumption to improve performance and reliability. Unlike our previous work, where insignificant input variables are successively screened out based on their mean impact values (MIVs) during the training process, we use the receiver operating characteristic (ROC) plot to generate reliable data with a conservative or progressive point of view, which overcomes the issue of data insufficiency of the MIV method: By properly setting boundaries for input variables based on the ROC plot and their statistics, instead of completely screening them out as in the MIV-based method, we can generate new training data that maximize true positive and false negative numbers from the partial data set. Then a NN model is constructed and trained with the generated training data using Levenberg–Marquardt back propagation (LM-BP) to perform electricity prediction for commercial buildings. The performance of the proposed data generation methods is compared with that of the MIV method through experiments, whose results show that data generation using successive and cross pattern provides satisfactory performance, following energy consumption trends with good phase. Among the two options in data generation, i.e., successive and two data combination, the successive option shows lower root mean square error (RMSE) than the combination one by around 400~900 kWh (i.e., 30%~75%).

Download Full-text