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

Line loss accounts for most of the energy loss in low‐voltage distribution network. Accurate prediction of line loss rate (LLR) is of great significance to eliminate abnormal transmission line faults in time and ensure power supply safety. The existing prediction methods for LLR seldom consider the seasonal trend data that affect it, and there is a hysteresis effect in predicting non‐stationary line loss sequences. To solve the above problems, this paper proposes a prediction method based on multi‐dimensional information matrix and dimensional attention mechanism‐long‐and short‐term time‐series network (DAM‐LSTNet). Firstly, the maximum information coefficient (MIC) method is used to screen the distribution network characteristics and seasonal trend parameters. Secondly, the variational mode decomposition (VMD) method optimized by the genetic algorithm is used to decompose the historical line loss data and form a multi‐dimensional information matrix with the screened characteristic parameters of the network. Finally, the multi‐dimensional information matrix is put into the LSTNet network with dimensional attention mechanism to predict the LLR. The example analysis shows that compared with the existing methods, it has the advantages of sufficient consideration of prediction parameters, adaptive changes of prediction weights, weak hysteresis effect and high prediction accuracy.

Section: Introductionmentioning

confidence: 99%

“…With the further development of artificial intelligence methods, it is possible to use data‐driven methods to make data predictions under the influence of multiple factors [10–12]. Jarkko et al.…”

Section: Introductionmentioning

confidence: 99%

Prediction method of line loss rate in low‐voltage distribution network based on multi‐dimensional information matrix and dimensional attention mechanism‐long‐and short‐term time‐series network

Zhang

Hui

et al. 2022

“…By combining TCN structures with other models, better prediction results have been obtained. He et al [31] proposed a hybrid CNN-TCN model for day-ahead load forecasting. A per-unit curve rotated decoupling (PCRD) method was introduced in the entire framework to improve the similarity of per-unit load curves and alleviate the deflection of forecasting results.…”

Section: Introductionmentioning

confidence: 99%

Temporal inception convolutional network based on multi‐head attention for ultra‐short‐term load forecasting

Tong

Zhang

et al. 2022

Accurate load forecasting is essential for ensuring safe, stable, and economical operation of energy internet. Temporal convolutional networks (TCNs) have demonstrated superior performance, when compared to recurrent neural network models, since their introduction in electrical load forecasting. However, the current TCN‐based models are unable to obtain a large receptive field and strong long‐time feature extraction capability owing to the specific kernel size of the 1D convolution structure. This paper proposes a temporal inception convolutional network based on multi‐head attention (TICN‐Att) for ultra‐short‐term load prediction. By introducing an inception structure into the TCN, the proposed model can extract multi‐dimensional information from the input features, through the multiple hidden convolutional kernels of different scales, without stacking layers depth‐wise. Simultaneously, by introducing a multi‐head attention mechanism, the TICN‐Att model has a long time‐dependent extraction capability, similar to that of the long short‐term memory network models. The generalization and validity of the model are tested using the global energy forecasting competition (GEFCOM2014) dataset, electrical load data of a city in Jiangsu (China), and PJM power system dataset. The experimental results demonstrated that the proposed model has the best prediction effect, compared to the other state‐of‐the‐art models.

“…He et al [24] introduced a hybrid method based on a deep convolutional neural network (CNN) for short-term PV power forecasting. He et al [25] proposed a per-unit curve rotated decoupling (PCRD) method for day-ahead load forecasting with convolutional neural network and temporal convolutional network framework. Wang et al [26] proposed an innovative hybrid model including the variational mode decomposition (VMD), Kullback-Leibler divergence, energy measure and LSTM prediction engine for wind speed causality processing.…”

Section: Introductionmentioning

confidence: 99%

“…He et al. [25] proposed a per‐unit curve rotated decoupling (PCRD) method for day‐ahead load forecasting with convolutional neural network and temporal convolutional network framework. Wang et al.…”

Section: Introductionmentioning

confidence: 99%

A short‐term electricity consumption forecasting approach based on feature processing and hybrid modelling

Wei

Wen

Luo

2022

The short‐term electricity consumption forecasting can help to ensure the safe and reliable operation of the power system. Power companies usually need to report the electricity consumption of the current month five to seven days in advance and make a power generation plan for the next month. The existing studies are usually lack of appropriate feature selection methods and hard to achieve satisfactory results. This paper proposes a short‐term electricity consumption forecasting approach based on feature processing and hybrid modelling. The maximum information coefficient (MIC) is employed to analyse the feature correlation, the electricity consumption curves are converted to several sub‐sequences of different frequency bands by the variational mode decomposition (VMD) to describe signal characteristics accurately, a hybrid model based on bidirectional gated recurrent unit (BiGRU) is innovated to extract the temporal and spatial features of the data and capture the contextual information from the complete time series, attention mechanism is used to do extract useful information and assign weights to make forecast. Compared with several benchmark methods, the proposed approach achieves better electricity consumption curve fitting and higher forecasting accuracy with the increase of forecasting step size.