Support vector machine for hourly cooling load prediction of commercial building

2014 ◽  
Author(s):  
D.S. He ◽  
C. Hou ◽  
X.W. Fan ◽  
Y. Zhang
Keyword(s):  
Support Vector Machine ◽  
Support Vector ◽  
Cooling Load ◽  
Commercial Building ◽  
Load Prediction

Cooling Load Prediction Based on the Combination of Rough Set Theory and Support Vector Machine

2006 ◽  
Vol 12 (2) ◽  
pp. 337-352 ◽  
Author(s):  
Zhijian Hou ◽  
Zhiwei Lian ◽  
Ye Yao ◽  
Xinjian Yuan
Keyword(s):  
Support Vector Machine ◽  
Set Theory ◽  
Rough Set ◽  
Rough Set Theory ◽  
Support Vector ◽  
Cooling Load ◽  
Load Prediction

An Online LS-SVM Prediction Model of Building Space Cooling Load

2011 ◽  
Vol 354-355 ◽  
pp. 789-793 ◽  
Author(s):  
Shuang Hua Cao ◽  
Jiang Tao Zhang ◽  
Fang Liu ◽  
Min Si Li
Keyword(s):  
Support Vector Machine ◽  
Correlation Analysis ◽  
Simulation Software ◽  
Office Building ◽  
Support Vector ◽  
Cooling Load ◽  
Load Prediction ◽  
Space Cooling ◽  
Svm Model ◽  
Simulation Results

Building space cooling load affected by lots of factors,was transient, multi-dimensional and highly interactive. A model of online least squares support vector machine (LS-SVM) was established to forecast the space cooling load of building, and correlation analysis was used to find out the main influencing factors, such as, dry-bulb temperature, solar irradiance, and so on. As an example, the hourly space cooling load of an office building in shanghai was investigated. The hourly space cooling load was firstly calculated by the simulation software of DEST, and then, an online LS-SVM model was presented to forecast the load. The simulation results showed that the online LS-SVM model was effective for space cooling load prediction.

scholarly journals Uncertainty Analysis of Weather Forecast Data for Cooling Load Forecasting Based on the Monte Carlo Method

Energies ◽  
2018 ◽  
Vol 11 (7) ◽  
pp. 1900 ◽  
Author(s):  
Jing Zhao ◽  
Yaoqi Duan ◽  
Xiaojuan Liu
Keyword(s):  
Monte Carlo ◽  
Monte Carlo Method ◽  
Load Forecasting ◽  
Weather Forecast ◽  
Weather Data ◽  
Support Vector ◽  
Cooling Load ◽  
Load Prediction ◽  
The Monte Carlo Method ◽  
Forecast Data

Recently, the cooling load forecasting for the short-term has received increasing attention in the field of heating, ventilation and air conditioning (HVAC), which is conducive to the HVAC system operation control. The load forecasting based on weather forecast data is an effective approach. The meteorological parameters are used as the key inputs of the prediction model, of which the accuracy has a great influence on the prediction loads. Obviously, there are errors between the weather forecast data and the actual weather data, but most of the existing studies ignored this issue. In order to deal with the uncertainty of weather forecast data scientifically, this paper proposes an effective approach based on the Monte Carlo Method (MCM) to process weather forecast data by using the 24-h-ahead Support Vector Machine (SVM) model for load prediction as an example. The data-preprocessing method based on MCM makes the forecasting results closer to the actual load than those without process, which reduces the Mean Absolute Percentage Error (MAPE) of load prediction from 11.54% to 10.92%. Furthermore, through sensitivity analysis, it was found that among the selected weather parameters, the factor that had the greatest impact on the prediction results was the 1-h-ahead temperature T(h–1) at the prediction moment.

Building Cooling Load Forecasting Based on Support Vector Machines with Simulated Annealing

2010 ◽  
Vol 108-111 ◽  
pp. 1003-1008
Author(s):  
Xue Mei Li ◽  
Li Xing Ding ◽  
Jin Hu Lǔ ◽  
lan Lan Li
Keyword(s):  
Simulated Annealing ◽  
Support Vector Machines ◽  
Support Vector ◽  
Cooling Load ◽  
Load Prediction ◽  
Promising Alternative ◽  
Vector Machines ◽  
Accurate Forecast ◽  
Electricity Load ◽  
Building Cooling

Accurate forecasting of building cooling load has been one of the most important issues in the electricity industry. Recently, along with energy-saving optimal control, accurate forecast of electricity load has received increasing attention. Because of the general nonlinear mapping capabilities of forecasting, artificial neural networks have played a crucial role in forecasting electricity load. Support vector machines (SVMs) have been successfully employed to solve nonlinear regression and time series problems. In order to improve time efficiency of prediction, a new hourly cooling load prediction model and method based on Support Vector Machine in this paper. Moreover, simulated annealing (SA) algorithms were employed to choose the parameters of a SVM model. Subsequently, examples of cooling load data from Guangzhou were used to illustrate the proposed SVM-SA model. A comparison of the performance between SVM optimized by Particle Swarm Optimization (SVM-PSO) and SVM-SA is carried out. Experiments results demonstrate that SVM-SA can achieve better accuracy and generalization than the SVM-PSO. Consequently, the SVM-SA model provides a promising alternative for forecasting building load.

Weighted LS-SVM Method for Building Cooling Load Prediction

2010 ◽  
Vol 121-122 ◽  
pp. 606-612
Author(s):  
Xue Mei Li ◽  
Jia Shu Chen ◽  
Li Xing Ding
Keyword(s):  
Time Series ◽  
Time Window ◽  
Weighted Least Squares ◽  
Superior Performance ◽  
Support Vector ◽  
Model Parameters ◽  
Cooling Load ◽  
Load Prediction ◽  
On Line ◽  
Building Cooling

A number of different forecasting methods have been proposed for cooling load forecasting including historic method, real-time method, time series analysis, and artificial neural networks, but accuracy and time efficiency in prediction are a couple of contradictions to be hard to resolve for building cooling load prediction. In order to improve the prediction accuracy of cooling load time series, weighted least squares support vector machine regression (WLS-SVM) method for a chaotic cooling load prediction is proposed. In this method, a sliding time window is built and data in the sliding time window are employed to reconstruct the dynamic model. Different weights are assigned to different data in the sliding time window, and the model parameters are refreshed on-line with the rolling of the time window. The results show that the method has more superior performance than other methods like LS-SVM.

Sign in / Sign up

Export Citation Format

Share Document