Hourly Heat Load Prediction Model Based on Temporal Convolutional Neural Network

Song, Jiancai; Xue, Guixiang; Xuhua, Pan; Ma, Yunpeng; Li, Han

doi:10.1109/access.2020.2968536

Cited by 63 publications

(24 citation statements)

References 39 publications

(42 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The MAE, MAPE, and RMSE can be used to evaluate the performance of the CNN-TCN load forecasting model based on PCRD. The formulas for calculating these assessment indicators are as follows [30]:…”

Section: The Framework Of the Cnn-tcn Model Based On Pcrd Methodsmentioning

confidence: 99%

A per‐unit curve rotated decoupling method for CNN‐TCN based day‐ahead load forecasting

Liu

et al. 2021

IET Generation Trans & Dist

View full text Add to dashboard Cite

The existing load forecasting method based on the per-unit curve static decoupling (PCSD) would easily lead to the deviation and translation of forecasting results. To tackle this challenge, a per-unit curve rotated decoupling (PCRD) method is proposed for day-ahead load forecasting with convolutional neural network and temporal convolutional network framework. The PCRD method decomposes the load into three parts: the rotated per-unit load curve, the 0 AM load, and the daily average load. The shape feature of the load curve is extracted by CNN, the temporal features of the 0 AM load and daily average load are extracted by TCN. The rotation operation is to rotate the per-unit load curve at the midpoint of the curve until the first load point is aligned to the same point, in order to improve the similarity of per-unit load curves and to alleviate the deflection of forecasting results. The 0 AM load can verify the accuracy of the daily average load, which alleviates the translation of forecasting results. Several experimental results show that the proposed method has higher accuracy and stability than the existing PCSD method. After repeated experiments on multiple data sets, the generalization ability of the model is also verified.

show abstract

Section: The Framework Of the Cnn-tcn Model Based On Pcrd Methodsmentioning

confidence: 99%

A per‐unit curve rotated decoupling method for CNN‐TCN based day‐ahead load forecasting

Liu

et al. 2021

IET Generation Trans & Dist

View full text Add to dashboard Cite

show abstract

“…Song et al proposes a heating load prediction model based on temporal convolutional neural network (TCN). The proposed model could effectively improve the prediction accuracy [16]. The ANN model and SVM model are also wildly used in the prediction of electricity consumption [17,18].…”

Section: A Load Prediction Methodsmentioning

confidence: 99%

Ultra-Short-Term Building Cooling Load Prediction Model Based on Feature Set Construction and Ensemble Machine Learning

Ding

Kong

et al. 2020

IEEE Access

View full text Add to dashboard Cite

As the requirements for the optimal control of building systems increase, the accuracy and speed of load predictions should also increase. However, the accuracy of load predictions is related to not only the prediction algorithm, but also the feature set construction. Therefore, this study develops a shortterm building cooling load prediction model based on feature set construction. The impacts of four different feature set construction methods-feature extraction, correlation analysis, K-means clustering, and discrete wavelet transform (DWT)-on the prediction accuracy are compared. To ensure that the effect of the feature set construction method is universal, three different prediction algorithms are used. The influences of the sample dimension and prediction time horizon on the prediction accuracy are also analysed. The prediction model is developed based on an ensemble learning algorithm utilising the cubist algorithm, and the performance of the prediction model is improved when DWT is used for constructing the feature set. Compared with other commonly used prediction models, the proposed model exhibits the best performance, with R-squared and CV-RMSE values of 99.8% and 1.5%, respectively. INDEX TERMS Cooling load prediction, Feature extraction, Ensemble learning algorithms, Discrete wavelet transform Nomenclature RF Random forest R-squared Square correlation coefficient GBM Gradient boosting machine FOG First order 5-h gradient DWT Discrete wavelet transform MSG Mean value of the square of the 1-h gradients in the past 5 h CA Correlation analysis FS Feature sets PCA Principal component analysis Large sample FS1 t-SNE t-distributed stochastic neighbour embedding Small sample FS10 g Principal component contribution ratio ARE Absolute value of relative error between predicted and actual values rspearman Spearman rank correlation coefficient IR Degree of improvement in the prediction accuracy Dk Sum of intra-cluster distances At Actual value SSE Sum of the squared error Ft Predicted value MSE Mean square error n Sample size CV-RMSE Root-mean-square error coefficient of variation Reduction ratio Reduction values between two time points

show abstract

“…On the one hand, the load data of most industrial customers has potential temporal correlations [4]. The TCN can extract the temporal correlations in the features due to the integration of the CNN's extraction ability and the RNN's time-domain modeling ability [29]. Moreover, the LightGBM is able to handle large-scale data accurately and quickly considering the load data scale of industrial customers in real practice.…”

Section: The Load Forecasting Framework Based On Tcn-lightgbm Modelmentioning

confidence: 99%

“…The model is used extensively in many fields such as pattern recognition [25], [26], anomaly detection [27] and mental assessment [28], but its application to the feature extraction task for load forecasting is relatively limited. Due to the integration of both the parallel feature processing of the CNN and the time-domain modeling capability of the RNN [29], the TCN is superior in extracting long-term time series features. In addition, a light gradient boosting machine (LightGBM) model [30] is selected to conduct load forecasting for industrial customers.…”

Section: Introductionmentioning

confidence: 99%

Short-Term Load Forecasting for Industrial Customers Based on TCN-LightGBM

Wang

Chen

et al. 2021

IEEE Trans. Power Syst.

205

View full text Add to dashboard Cite

show abstract

Hourly Heat Load Prediction Model Based on Temporal Convolutional Neural Network

Cited by 63 publications

References 39 publications

A per‐unit curve rotated decoupling method for CNN‐TCN based day‐ahead load forecasting

A per‐unit curve rotated decoupling method for CNN‐TCN based day‐ahead load forecasting

Ultra-Short-Term Building Cooling Load Prediction Model Based on Feature Set Construction and Ensemble Machine Learning

Short-Term Load Forecasting for Industrial Customers Based on TCN-LightGBM

Contact Info

Product

Resources

About