Applying support vector machines to predict building energy consumption in tropical region

2005 ◽  
Vol 37 (5) ◽  
pp. 545-553 ◽  
Author(s):  
Bing Dong ◽  
Cheng Cao ◽  
Siew Eang Lee
Keyword(s):  
Energy Consumption ◽  
Support Vector Machines ◽  
Building Energy ◽  
Support Vector ◽  
Tropical Region ◽  
Building Energy Consumption ◽  
Vector Machines

scholarly journals Applying support vector machines to predict building energy consumption in China

2018 ◽  
Vol 152 ◽  
pp. 780-786 ◽  
Author(s):  
Zhitong Ma ◽  
Cantao Ye ◽  
Huashan Li ◽  
Weibin Ma
Keyword(s):  
Energy Consumption ◽  
Support Vector Machines ◽  
Building Energy ◽  
Support Vector ◽  
Building Energy Consumption ◽  
Vector Machines

scholarly journals Prediksi Konsumsi Energi Pada Bangunan Menggunakan Metode Support Vector Machice Berbasis Algoritma Genetika

2017 ◽  
Vol 2 (1) ◽  
pp. 1
Author(s):  
Wida Prima Mustika
Keyword(s):  
Genetic Algorithm ◽  
Support Vector Machine ◽  
Feature Selection ◽  
Energy Consumption ◽  
Support Vector Machines ◽  
Energy Use ◽  
Building Energy ◽  
Support Vector ◽  
Vector Machines ◽  
Optimization Parameters

Energy consumption is a demand for the amount of energy that must supply the building at any given time. Building energy consumption has continued increased over the last few decades all over the world, and Heating, Ventilating, and Air-Conditioning (HVAC), which has a catalytic role in regulating the temperature in the room, mostly accounted for of building energy use. Models created for in this study support vector machine and support vector machine-based models of genetic algorithm to obtain the value of accuracy or error rate or the smallest error value Root Mean Square Error (RMSE) in predicting energy consumption in buildings is more accurate. After testing the two models of support vector machines and support vector machines based on the genetic algorithm is the testing results obtained by using support vector machines where RMSE value obtained was 2,613. Next was the application of genetic algorithms to the optimization parameters C and γ values obtained RMSE error of 1.825 and a genetic algorithm for feature selection error RMSE values obtained for 1,767 of the 7 predictor variables and the selection attribute or feature resulting in the election of three attributes used. After that is done the optimization parameters and the importance of the value of feature selection mistake or error of the smallest RMSE of 1.537. Thus the support vector machine algorithm based on genetic algorithm can give a solution to the problems in the prediction of energy consumption rated the smallest mistake or error.

Building Energy Consumption Prediction of Housing Industry in China Based on Hybrid Models

2011 ◽  
Vol 201-203 ◽  
pp. 2466-2469 ◽  
Author(s):  
Ying Xie
Keyword(s):  
Energy Consumption ◽  
Building Energy ◽  
Hybrid Models ◽  
Support Vector ◽  
National Bureau ◽  
Building Energy Consumption ◽  
Total Energy Consumption ◽  
Consumption Index ◽  
Housing Industry ◽  
Energy Consumption Prediction

Building energy consumption is a vital part of the total energy consumption in China, it is meaningful to predict the building energy consumption exactly as it is useful in the effective implementation of energy policies and is propitious for further expansion of the housing industry. In this paper, based on the factor analysis theory to reduce the dimension of the building energy consumption index, hybrid models of BP neural network and Least Squares Support Vector Machines are constructed respectively to predict the building energy consumption. Relevant data is collected from National Bureau of Statistics of China (1981~2009). Data analysis shows the proposed models, especially based on LS-SVMs, have more steady performance and higher accuracy.

Prediction of energy consumption in hotel buildings via support vector machines

2020 ◽  
Vol 57 ◽  
pp. 102128 ◽  
Author(s):  
Minglei Shao ◽  
Xin Wang ◽  
Zhen Bu ◽  
Xiaobo Chen ◽  
Yuqing Wang
Keyword(s):  
Energy Consumption ◽  
Support Vector Machines ◽  
Support Vector ◽  
Vector Machines
Sign in / Sign up

Export Citation Format

Share Document