A Hybrid System Based on LSTM for Short-Term Power Load Forecasting

Jin, Yu; Guo, Honggang; Wang, Jianzhou; Song, Aiyi

doi:10.3390/en13236241

Cited by 54 publications

(36 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, in wavelet decomposition and VMD, it is necessary to determine the wavelet basis function and the decomposition level. Although in EMD it is not necessary to determine the number of decomposition levels, mode aliasing and insufficient noise separation cannot be solved (Jin et al, 2020). Therefore, it is very important to extract the nonlinear peculiarities of carbon prices by using appropriate data preprocessing methods.…”

Section: Statistical Measurement Methodsmentioning

confidence: 99%

An Ensemble Prediction System Based on Artificial Neural Networks and Deep Learning Methods for Deterministic and Probabilistic Carbon Price Forecasting

Yang

Guo

Jin

et al. 2021

Front. Environ. Sci.

Self Cite

View full text Add to dashboard Cite

Carbon price prediction is important for decreasing greenhouse gas emissions and coping with climate change. At present, a variety of models are widely used to predict irregular, nonlinear, and nonstationary carbon price series. However, these models ignore the importance of feature extraction and the inherent defects of using a single model; thus, accurate and stable prediction of carbon prices by relevant industry practitioners and the government is still a huge challenge. This research proposes an ensemble prediction system (EPS) that includes improved data feature extraction technology, three prediction submodels (GBiLSTM, CNN, and ELM), and a multiobjective optimization algorithm weighting strategy. At the same time, based on the best fitting distribution of the prediction error of the EPS, the carbon price prediction interval is constructed as a way to explore its uncertainty. More specifically, EPS integrates the advantages of various submodels and provides more accurate point prediction results; the distribution function based on point prediction error is used to establish the prediction interval of carbon prices and to mine and analyze the volatility characteristics of carbon prices. Numerical simulation of the historical data available for three carbon price markets is also conducted. The experimental results show that the ensemble prediction system can provide more effective and stable carbon price forecasting information and that it can provide valuable suggestions that enterprise managers and governments can use to improve the carbon price market.

show abstract

Section: Statistical Measurement Methodsmentioning

confidence: 99%

An Ensemble Prediction System Based on Artificial Neural Networks and Deep Learning Methods for Deterministic and Probabilistic Carbon Price Forecasting

Yang

Guo

Jin

et al. 2021

Front. Environ. Sci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Wu et al [42] One min Gansu, China MAPE = 2.8839% CNN, GRU Jin et al [43] One hour Queensland, Australia MAPE = 0.7653% VMD, BEGA, LSTM Nie et al [44] One hour Australia MAPE = 0.7280% CEEMD, SSA, RBF, ELM, GRNN Heydari et al [45] One hour America MAPE = 0.8657% VMD, GRNN, GSA Shao et al [46] Half day PJM MAPE = 3.13% LSTM, CAE, K-means Bedi et al [47] One day Himachal Pradesh, India MAPE = 3.04% VMD, ACA, EVM-S, LSTM Deng et al [48] One day Yichun, China MAPE = 2.057% VMD, DBN Mansoor et al [49] One day Milan, Italy MAPE = 2.937% FFNN, ESN Yin et al [50] One day Guangxi, China MAPE = 1.89% MTCN Kong et al [51] One day Tianjin, China MAPE = 3.104% DMD, EVCM, SVR…”

Section: Authors and Ref Forecast Horizon Data Sources Evaluation Indmentioning

confidence: 99%

An Ensemble Model based on Deep Learning and Data Preprocessing for Short-Term Electrical Load Forecasting

Shen

Deng

et al. 2021

Sustainability

View full text Add to dashboard Cite

Electricity load forecasting is one of the hot concerns of the current electricity market, and many forecasting models are proposed to satisfy the market participants’ needs. Most of the models have the shortcomings of large computation or low precision. To address this problem, a novel deep learning and data processing ensemble model called SELNet is proposed. We performed an experiment with this model; the experiment consisted of two parts: data processing and load forecasting. In the data processing part, the autocorrelation function (ACF) was used to analyze the raw data on the electricity load and determine the data to be input into the model. The variational mode decomposition (VMD) algorithm was used to decompose the electricity load raw-data into a set of relatively stable modes named intrinsic mode functions (IMFs). According to the time distribution and time lag determined using the ACF, the input of the model was reshaped into a 24 × 7 × 8 matrix M, where 24, 7, and 8 represent 24 h, 7 days, and 8 IMFs, respectively. In the load forecasting part, a two-dimensional convolutional neural network (2D-CNN) was used to extract features from the matrix M. The improved reshaped layer was used to reshape the extracted features according to the time order. A temporal convolutional network was then employed to learn the reshaped time-series features and combined with the fully connected layer to complete the prediction. Finally, the performance of the model was verified in the Eastern Electricity Market of Texas. To demonstrate the effectiveness of the proposed model data processing and load forecasting, we compared it with the gated recurrent unit (GRU), TCN, VMD-TCN, and VMD-CNN models. The TCN exhibited better performance than the GRU in load forecasting. The mean absolute percentage error (MAPE) of the TCN, which was over 5%, was less than that of the GRU. Following the addition of VMD to the TCN, the basic performance of the model was 2–3%. A comparison between the SELNet model and the VMD-TCN model indicated that the application of a 2D-CNN improves the forecast performance, with only a few samples having an MAPE of over 4%. The model’s prediction effect in each season is discussed, and it was found that the proposed model can achieve high-precision prediction in each season.

show abstract

“…In order to minimize the forecast error of electrical loads, scholars have carried out many studies on combined forecasting models based on data preprocessing and electrical load forecasting models. Typically, these scholars use wavelet transform (WT) [23], empirical modal decomposition (EMD) [24], variational modal decomposition (VMD) [25], and singular spectrum analysis [26] for noise reduction.…”

Section: Literature Reviewmentioning

confidence: 99%

A Combined Model Based on EOBL-CSSA-LSSVM for Power Load Forecasting

et al. 2021

View full text Add to dashboard Cite

Inaccurate electricity load forecasting can lead to the power sector gaining asymmetric information in the supply and demand relationship. This asymmetric information can lead to incorrect production or generation plans for the power sector. In order to improve the accuracy of load forecasting, a combined power load forecasting model based on machine learning algorithms, swarm intelligence optimization algorithms, and data pre-processing is proposed. Firstly, the original signal is pre-processed by the VMD–singular spectrum analysis data pre-processing method. Secondly, the noise-reduced signals are predicted using the Elman prediction model optimized by the sparrow search algorithm, the ELM prediction model optimized by the chaotic adaptive whale algorithm (CAWOA-ELM), and the LSSVM prediction model optimized by the chaotic sparrow search algorithm based on elite opposition-based learning (EOBL-CSSA-LSSVM) for electricity load data, respectively. Finally, the weighting coefficients of the three prediction models are calculated using the simulated annealing algorithm and weighted to obtain the prediction results. Comparative simulation experiments show that the VMD–singular spectrum analysis method and two improved intelligent optimization algorithms proposed in this paper can effectively improve the prediction accuracy. Additionally, the combined forecasting model proposed in this paper has extremely high forecasting accuracy, which can help the power sector to develop a reasonable production plan and power generation plans.

show abstract

A Hybrid System Based on LSTM for Short-Term Power Load Forecasting

Cited by 54 publications

References 45 publications

An Ensemble Prediction System Based on Artificial Neural Networks and Deep Learning Methods for Deterministic and Probabilistic Carbon Price Forecasting

An Ensemble Prediction System Based on Artificial Neural Networks and Deep Learning Methods for Deterministic and Probabilistic Carbon Price Forecasting

An Ensemble Model based on Deep Learning and Data Preprocessing for Short-Term Electrical Load Forecasting

A Combined Model Based on EOBL-CSSA-LSSVM for Power Load Forecasting

Contact Info

Product

Resources

About