Research on building energy consumption prediction model based on fractal theory

ABSTRACT Nowadays, the energy problem is becoming more and more serious, and the actual energy consumption of the building is one of the important links in the field of building energy conservation. At present, most prediction algorithms fail to fully consider the complex characteristics of building energy consumption, resulting in unsatisfactory prediction results. Fractal theory can directly analyze some rules of abstract composite complex nonlinear things and then analyze and predict them correctly. Therefore, it is also a new way to analyze fractal theory and solve the problem of large-scale public construction energy consumption prediction. Taking a building as the object, an energy consumption prediction model using the fractal collage principle and fractal interpolation algorithm is proposed. In order to verify the validity of the model, a prediction model of traditional mature BP neural network is established, and the experimental results of the two models were compared. Mean relative error (MRE) and root mean square error (RMSE) basis are used to evaluate the performance of the model on the daily. The results show that the fractal prediction model has good prediction effect and accuracy. The energy prediction data provided by the model can provide a scientific basis for energy management and energy conservation control of such buildings.

[1]  Benjamin C. M. Fung,et al.  A decision tree method for building energy demand modeling , 2010 .

[2]  Andrew Kusiak,et al.  Predictive modeling and optimization of a multi-zone HVAC system with data mining and firefly algorithms , 2015 .

[3]  Jiejin Cai,et al.  Applying support vector machine to predict hourly cooling load in the building , 2009 .

[4]  Jian Chu,et al.  Forecasting building energy consumption using neural networks and hybrid neuro-fuzzy system: A compa , 2011 .

[5]  Jesús M. Zamarreño,et al.  Prediction of hourly energy consumption in buildings based on a feedback artificial neural network , 2005 .

[6]  Shengwei Wang,et al.  Development of prediction models for next-day building energy consumption and peak power demand using data mining techniques , 2014 .

[7]  Dongxiao Niu,et al.  Short-Term Electric Load Forecasting Based on Data Mining , 2017 .

[8]  Nora El-Gohary,et al.  A review of data-driven building energy consumption prediction studies , 2018 .

[9]  Jui-Sheng Chou,et al.  Modeling heating and cooling loads by artificial intelligence for energy-efficient building design , 2014 .

[10]  B. Dong,et al.  Applying support vector machines to predict building energy consumption in tropical region , 2005 .

[11]  Surapong Chirarattananon,et al.  An OTTV-based energy estimation model for commercial buildings in Thailand , 2004 .

[12]  Wil L. Kling,et al.  Pseudo Dynamic Transitional Modeling of Building Heating Energy Demand Using Artificial Neural Network , 2014, ArXiv.

[13]  Michael F. Barnsley,et al.  Fractal functions and interpolation , 1986 .