DOI: 10.14704/nq.2018.16.6.1541

Prediction Method for Energy Consumption of High-rise Buildings Based on Artificial Neural Network and Big Data Analysis

Wenbin Kuai


In terms of the fact that the thermal load of high-rise buildings is affected by a series of influence factors, including outdoor meteorological environment, architectural characteristics, and building envelope, it is difficult to use the traditional mechanism to construct the prediction model because there are many difficult parameters and the reliability of the predicted result is low. Based on big data, the energy consumption of high-rise buildings is predicted by BP and RBF artificial neural network analysis methods because the artificial neural network does not rely on the model. The experimental result shows that the two models can well predict the energy consumption of high-rise buildings. What’s more, RBF artificial neural network is more stable than BP in prediction, so it is more suitable to predict the energy consumption of high-rise buildings.


Artificial Neural Network, Energy Consumption of High-rise Buildings, Big Data, Prediction

Full Text:



Abarghouei HB, Kousari MR, Zarch MAA. Prediction of drought in dry lands through feedforward artificial neural network abilities. Arabian Journal of Geosciences 2013; 6(5): 1417-33.

Barabási AL, Author, Crandall RE. The new science of networks. Physics Today 2003; 6(5): 243-70.

Bataineh K, Taamneh Y. Performance analysis of stand-alone solar dish Stirling system for electricity generation, International Journal of Heat and Technology 2017; 35(1): 498-508.

Bosch J, Rodrigo A, Navarro D. Plant-pollinator networks: adding the pollinator’s perspective. Ecology Letters 2009; 12(5): 409-19.

Brahm AB, Varas E. Learning time reduction in artificial neural networks applied to hydrology. Ingeniería Hidráulica En México 2003; 18(2): 69-82.

Carla B, Giuseppe P. Numerical multiphysics modelling for the assessment of thermo-physical and energy performance of an advanced semi-opaque active façade, International Journal of Heat and Technology 2017; 35(1): 639-44.

Dong B, Cao C, Lee SE. Applying support vector machines to predict building energy consumption in tropical region. Energy & Buildings 2005; 37(5): 545-53.

Du HW, Xiong W, Xu C, Jiang ZA. Research on the controllability and energy saving of the pneumatic direct drive system, International Journal of Heat and Technology 2017; 35(4): 997-1004.

Filho AJP, Santos CCD. Modeling a densely urbanized watershed with an artificial neural network, weather radar and telemetric data. Journal of Hydrology 2006; 317(1): 31-48.

Gardner MW, Dorling SR. Artificial neural networks (the multilayer perceptron) - ma review of applications in the atmospheric sciences. Atmospheric Environment 1998; 32(14-15): 2627-36.

Gen M, Lin L. Multiobjective genetic algorithm for scheduling problems in manufacturing systems. Industrial Engineering & Management Systems 2012; 11(11): 310-30.

Gokmentafur. Artificial neural networks for sheet sediment transport. International Association of Scientific Hydrology Bulletin 2002; 47(6): 879-92.

Gorantla K, Shaik S, Setty AB. Thermal and cost analysis of float and various tinted double window glass configurations on heat gain into buildings of hot & dry climatic zone in India, International Journal of Heat and Technology 2018; 36(1): 252-60.

Hellmann T, Staudigl M. Evolution of social networks. European Journal of Operational Research 2014; 234(3): 583-96.

Kreider JF. Artificial neural networks demonstration for automated generation of energy use predictors for commercial buildings. ASHIRAE Transactions 1991; 97(1): 775-79.

Liu CM, Liu L, Liu CB. Analysis of wind resistance of high-rise building structures based on computational fluid dynamics simulation technology, International Journal of Heat and Technology 2018; 36(1): 376-80.

Lodi C, Malaguti V, Contini FM, Sala L, Muscio A, Tartarini P. University energy planning for reducing energy consumption and GHG emissions: the case study of a university campus in Italy, International Journal of Heat and Technology 2017; 35(S1): S27-S32.

Magrini A, Lazzari S, Marenco L, Guazzi G. A procedure to evaluate the most suitable integrated solutions for increasing energy performance of the building’s envelope, avoiding moisture problems, International Journal of Heat and Technology 2017; 35(4): 689-99.

Miguélez M, Puertas J, Rabuñal JR. Artificial Neural Networks in Urban Runoff Forecast. Bio-Inspired Systems: Computational and Ambient Intelligence. Berlin: Springer, 2009.

Nielsen HA, Madsen H. Modelling the heat consumption in district heating systems using a grey-box approach. Energy & Buildings 2006; 38(1): 63-71.

Sadaghiyani OK, Boubakran MS, Hassanzadeh A. Energy and exergy analysis of parabolic trough collectors, International Journal of Heat and Technology 2018; 36(1): 147-58.

Wang HB, Guo XG. Transient analysis of thermal and moisture transfer in building materials, International Journal of Heat and Technology 2017; 35(4): 821-26.

Wang XR, Ren GL, Zhang JX. (2018). Numerical simulation and optimization analysis of thermal balance of heavy oil box-type substation louver arrangement, Mathematical Modelling of Engineering Problems 2018; 5(1): 21-26.

Whitney W, Rana S, Dzubera J, Mathias KE. Evaluating evolutionary algorithms. Artificial Intelligence 1996; 84(1-2): 357-58.

Yetis CM, Gou T, Jafar SA, Kayran AH. On feasibility of interference alignment in mimo interference networks. IEEE Transactions on Signal Processing 2010;58(9): 4771-82.

Supporting Agencies

| NeuroScience + QuantumPhysics> NeuroQuantology :: Copyright 2001-2019