The Analysis of Combined Prediction Model of Building Energy Consumption with Grey Theory and RBF Neural Network

Abstract

A kind of new combined modeling method with GM(1,1) and RBNN (Radial Basis Neural Network) is brought forward, according to the idea that the method of neural network can bring grey prediction model a good modified effect. Based on the analysis of the energy consumption data of the existing and the annually-increased building area, the GM(1,1) model was then constructed. And the RBF neural network was used for the model residual error revising. The simulation and experiment results show that the novel model is more effective than the common grey model.

Towards developing a systematic knowledge trend for building energy consumption prediction

“… Superior in solving nonlinear problems with high-dimensional datasets  Can handle large and incomplete datasets  Self-adapting, selforganizing and real-time learning network  Easy to construct the network models  Requires a large amount of data  Extremely computationally expensive to train  The internal working is unknown  The meta parameter and network topology selection is hard Table 3. Summary of articles that explored hybrid methods, their associated sub-methods and functions Reference Algorithm Function [67] Physical Simulates the building energy performance Genetic Algorithm Identifies the buildings' internal mass model parameters [68] GM (1,1) Predicts the buildings' energy consumption Radial basis neural network Revises the residual errors of the grey model [69] RReliefF Accounts for interdependencies between variables so as to select the optimal variable subset SVM Predicts the buildings' energy consumption [70] Improved real coded genetic algorithm…”

The Analysis of Building Subsidence Prediction Based on Grey Model Combined with Radial Basis Neural Network

“…Recently, many prediction methods are used for subsidence prediction [2]. Among these methods, Grey Theory has been widely applied to many disciplines, such as population, economics, sociology, engineering, network traffic, and so forth [3] due to its advantages of fewer requirements on original data scale, less limitation of the distribution pattern and simpler algorithm in modeling. Neural network, especially the radial basis function neural network has been also widely applied to many disciplines due to its advantages of swift and self-learning [4].…”