Real-time prediction of sub-item building energy consumption based on PCA-AR-BP method

Qian, Qing; Tang, Guizhong; Zhang, Guangming

doi:10.1088/1757-899x/366/1/012043

Cited by 3 publications

(2 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Research studies have long focused on the energy consumption prediction of urban rail transit. Prevailing prediction methods include multivariate linear regression method [3], artificial neural network method [4][5][6], support vector machine [7,8], genetic algorithm [9], grey theory method [10,11], and time series method [12].…”

Section: Introductionmentioning

confidence: 99%

[Retracted] A Method for Short‐Term Prediction of the Metro Station’s Individual Energy Consumption Item Based on G‐ACO‐BP Model

Sha¹,

Qian²

2021

Computational Intelligence and Neuroscience

Self Cite

View full text Add to dashboard Cite

This paper proposes a new method to make short-term predictions for the three kinds of primary energy consumption of power, lighting, and ventilated air conditioning in the metro station. First, the paper extracts the five main factors influencing metro station energy consumption through the kernel principal component analysis (KPCA). Second, improved genetic-ant colony optimization (G-ACO) was fused into the BP neural network to train and optimize the connection weights and thresholds between each BP neural network layer. The paper then builds a G-ACO-BP neural model to make short-term predictions about different energy consumption in the metro station to predict the energy consumed by power, lighting, and ventilated air conditioning. The experimental results showed that the G-ACO-BP neural model could give a more accurate and effective prediction for the main energy consumption in a metro station.

show abstract

Section: Introductionmentioning

confidence: 99%

[Retracted] A Method for Short‐Term Prediction of the Metro Station’s Individual Energy Consumption Item Based on G‐ACO‐BP Model

Sha¹,

Qian²

2021

Computational Intelligence and Neuroscience

Self Cite

View full text Add to dashboard Cite

show abstract

“…Artificial neural network: Back-propagation [45], [122], [137], [141], [204], Hopfield network [54], Radial basis function network [54], [74], [78], [116]  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 large amount of data  Extremely computationally expensive to train  Full details of the internal working principles could be challenging to understand  The meta parameter and network topology selection is challenging…”

Section: Neural Networkmentioning

confidence: 99%

Towards developing a systematic knowledge trend for building energy consumption prediction

Qiao

Yunusa‐Kaltungo

Edwards

2021

Journal of Building Engineering

View full text Add to dashboard Cite

Research on multi-objective optimization of building energy efficiency based on energy consumption and thermal comfort

Jun,

Fei

2024

Building Services Engineering Research and Technology

View full text Add to dashboard Cite

Building design optimization (BDO) provides an approach for decreasing global energy consumption and achieving the goal of carbon neutrality. However, energy efficiency and comfort performance are two conflicting objectives when making optimal building design schemes. This study proposes a surrogate model-based multiple-objective optimization framework to balance the conflicting objectives and obtain an optimal design scheme for buildings. Firstly, an energy simulation model for generating energy consumption and design parameters is constructed, and the obtained data are utilized to train the surrogate model with the random forest (RF) algorithm. Then, multi-objective optimization algorithms are employed to generate a set of alternative plans for building schemes and determine the optimal building design solutions that can equilibrate the requirements for both energy conservation and building comfort. To verify the proposed optimization method in this paper, a residential building in Suzhou was selected as a case study. The study considered 10 building design parameters that are related to energy efficiency and thermal comfort. The results indicate that the RF surrogate model accurately predicts energy consumption, with a predicted MSE of 0.00012 and R2 of 0.99. In evaluating the Pareto set size, Pareto solution diversity, Pareto front proximity, and best solution quality, NSGA-II proved to be the most effective optimization algorithm for BDO problems. The final optimal solution of design parameters obtained by NSGA-II obviously improves the building performance of comfort and energy efficiency, and the results of the performance evaluation for different optimization algorithms provide guidance to make decisions on suitable algorithms and hyperparameter settings based on the greatest preference of the performance criteria. This study will help determine the best design options for buildings to achieve better energy efficiency in sustainable development and provide reference for similar projects. Practical applications This research makes valuable contributions in the following aspects:(a) It establishes a multi-objective optimization design model for a virtual building environment. This enables the visualization and digitization of the building model and further facilitates the transformation of the optimization model, thereby providing users with convenient decision-making tools; (b) The study provides designers and other stakeholders with comprehensive simulation-based analysis results and optimization techniques. These tools aid in making energy-saving multi-objective optimization decisions;(c) The research compares various optimization algorithms and presents their strengths and limitations, which will help designers select suitable algorithms based on practical requirements.

show abstract

Real-time prediction of sub-item building energy consumption based on PCA-AR-BP method

Cited by 3 publications

References 3 publications

[Retracted] A Method for Short‐Term Prediction of the Metro Station’s Individual Energy Consumption Item Based on G‐ACO‐BP Model

[Retracted] A Method for Short‐Term Prediction of the Metro Station’s Individual Energy Consumption Item Based on G‐ACO‐BP Model

Towards developing a systematic knowledge trend for building energy consumption prediction

Research on multi-objective optimization of building energy efficiency based on energy consumption and thermal comfort

Contact Info

Product

Resources

About