Simplified Neural Network Model Design with Sensitivity Analysis and Electricity Consumption Prediction in a Commercial Building

Kim, Moon Keun; Cha, Jaehoon; Lee, Eun-Mi; Pham, Van Huy; Lee, Sanghyuk; Theera-Umpon, Nipon

doi:10.3390/en12071201

Cited by 16 publications

(26 citation statements)

References 32 publications

(63 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In previous research [23,24], the mean impact value (MIV) was used to predict building electricity consumption and improve the prediction accuracy of building energy consumption, where we proposed a simplified neural network and verified its effectiveness. During the investigation, we applied several neural network algorithms, and compared their sensitivities.…”

Section: Introductionmentioning

confidence: 97%

“…During the investigation, we applied several neural network algorithms, and compared their sensitivities. Finally, a neural network algorithm with a data-driven approach was selected and the result was well suited to building energy consumption prediction based on how each environmental element influences the electricity consumption in a building [24]. It is recognized that understanding the sensitivity of building energy consumption models is important because the sensitivity is also closely related to the performance and robustness of the system [16][17][18][19].…”

Section: Introductionmentioning

confidence: 99%

“…As previously mentioned, NN SA has been carried out by analyzing output variance with respect to the variation of inputs and connected weights [21,22]. Besides analytical SA, MIV is also applied to analyze the effect on the output by the variation of input variables [23,24]. Due to the NN structure, which can be considered as a black box, we measure the output variation under perturbation in the input data set.…”

Section: Introductionmentioning

confidence: 99%

“…In the paper, we use actual electricity consumption data from a shopping mall in Dalian, China, to predict energy consumption [27]. However, we face the issue of data insufficiency in applying NN prediction models; this could be an issue, too, when we use few reliable data from the plenty of available data [24]. In order to overcome the issue of insufficient training data, therefore, we systematically generate more training data based on the ROC plot.…”

Section: Introductionmentioning

confidence: 99%

“…Next, we constitute a new training set from the original and generated data set and apply test data to verify the performance of the proposed NN in this paper, which is compared with that of the simplified NN from [24]. Results show how the reliability of data affects the output performance.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Neural-Network-Based Building Energy Consumption Prediction with Training Data Generation

et al. 2019

Self Cite

View full text Add to dashboard Cite

The importance of neural network (NN) modelling is evident from its performance benefits in a myriad of applications, where, unlike conventional techniques, NN modeling provides superior performance without relying on complex filtering and/or time-consuming parameter tuning specific to applications and their wider ranges of conditions. In this paper, we employ NN modelling with training data generation based on sensitivity analysis for the prediction of building energy consumption to improve performance and reliability. Unlike our previous work, where insignificant input variables are successively screened out based on their mean impact values (MIVs) during the training process, we use the receiver operating characteristic (ROC) plot to generate reliable data with a conservative or progressive point of view, which overcomes the issue of data insufficiency of the MIV method: By properly setting boundaries for input variables based on the ROC plot and their statistics, instead of completely screening them out as in the MIV-based method, we can generate new training data that maximize true positive and false negative numbers from the partial data set. Then a NN model is constructed and trained with the generated training data using Levenberg–Marquardt back propagation (LM-BP) to perform electricity prediction for commercial buildings. The performance of the proposed data generation methods is compared with that of the MIV method through experiments, whose results show that data generation using successive and cross pattern provides satisfactory performance, following energy consumption trends with good phase. Among the two options in data generation, i.e., successive and two data combination, the successive option shows lower root mean square error (RMSE) than the combination one by around 400~900 kWh (i.e., 30%~75%).

show abstract

Section: Introductionmentioning

confidence: 97%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Neural-Network-Based Building Energy Consumption Prediction with Training Data Generation

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

Hierarchical multi-scale parametric optimization of deep neural networks

Zhang,

Vassiliadis,

Dorneanu

et al. 2023

Appl Intell

View full text Add to dashboard Cite

Traditionally, sensitivity analysis has been utilized to determine the importance of input variables to a deep neural network (DNN). However, the quantification of sensitivity for each neuron in a network presents a significant challenge. In this article, a selective method for calculating neuron sensitivity in layers of neurons concerning network output is proposed. This approach incorporates scaling factors that facilitate the evaluation and comparison of neuron importance. Additionally, a hierarchical multi-scale optimization framework is proposed, where layers with high-importance neurons are selectively optimized. Unlike the traditional backpropagation method that optimizes the whole network at once, this alternative approach focuses on optimizing the more important layers. This paper provides fundamental theoretical analysis and motivating case study results for the proposed neural network treatment. The framework is shown to be effective in network optimization when applied to simulated and UCI Machine Learning Repository datasets. This alternative training generates local minima close to or even better than those obtained with the backpropagation method, utilizing the same starting points for comparative purposes within a multi-start optimization procedure. Moreover, the proposed approach is observed to be more efficient for large-scale DNNs. These results validate the proposed algorithmic framework as a rigorous and robust new optimization methodology for training (fitting) neural networks to input/output data series of any given system. Graphical Abstract

show abstract

Double regulation Levenberg–Marquardt neural networks: an aero-engine fuel flow prediction method

Yan,

Cui,

et al. 2023

Nonlinear Dyn

View full text Add to dashboard Cite

Simplified Neural Network Model Design with Sensitivity Analysis and Electricity Consumption Prediction in a Commercial Building

Cited by 16 publications

References 32 publications

Neural-Network-Based Building Energy Consumption Prediction with Training Data Generation

Neural-Network-Based Building Energy Consumption Prediction with Training Data Generation

Hierarchical multi-scale parametric optimization of deep neural networks

Double regulation Levenberg–Marquardt neural networks: an aero-engine fuel flow prediction method

Contact Info

Product

Resources

About