A novel gated dual convolutional neural network model with autoregressive method and attention mechanism for probabilistic load forecasting
Tóm tắt
Accurate load forecasting is prime in the electric power industry, while the complexity and variability of the load data make it a challenging problem. Therefore, the probabilistic load forecasting is used to provide a prediction interval for the power system. However, the input scale insensitive problem has rarely been addressed in existing works when exploring the multi-load zones data, resulting in a lack of robustness. In addition, the coverage and width of the prediction interval have seldom been simultaneously considered, affecting the forecasting accuracy. Therefore, to overcome the above drawbacks and achieve reliable forecasting results, a novel gated dual convolutional neural network model with autoregressive method and attention mechanism is proposed. Firstly, the autoregressive method is adopted as a linear component of the probabilistic load forecasting model to handle the input scale insensitive problem and enhance the modeling robustness. Then, a dual convolutional neural network is extended with the gating mechanism and is employed to capture the vertical correlation of information among multi-load zones and enhance the coverage of the prediction interval. Next, the attention mechanism is extended with pooling operation to extract the significant horizontal correlation of information among multi-load zones and obtain a narrower prediction interval. Finally, the superiority of the proposed model was validated through both ablation and comparison experiments on two real-world datasets.
Tài liệu tham khảo
Alvarez V, Mazuelas S, Lozano JA (2021) Probabilistic load forecasting based on adaptive online learning. IEEE Trans Power Syst 36(4):3668–3680
Xu L, Wang SW, Tang R (2019) Probabilistic load forecasting for buildings considering weather forecasting uncertainty and uncertain peak load. Appl Energy 237:180–195
Sheng ZY, Wang HW, Chen G, Zhou B, Sun J (2021) Convolutional residual network to short-term load forecasting. Appl Intell 51(4):2485–2499
Barman M, Choudhury NBD (2019) Season specific approach for short-term load forecasting based on hybrid FA-SVM and similarity concept. Energy 174:886–896
Liu H, Fang S, Zhang ZL, Li DTC, Lin K, Wang JZ (2022) MFDNet: collaborative poses perception and matrix fisher distribution for head pose estimation. IEEE Trans Multimed 24:2449–2460
Liu TT, Wang JX, Yang B, Wang X (2021) NGDNet: nonuniform Gaussian-label distribution learning for infrared head pose estimation and on-task behavior understanding in the classroom. Neurocomputing 436:210–220
Imani M (2021) Electrical load-temperature CNN for residential load forecasting. Energy 227:120480
Jalali SMJ, Ahmadian S, Khosravi A, Shafie-khah M, Nahavandi S, Catalão JP (2021) A novel evolutionary-based deep convolutional neural network model for intelligent load forecasting. IEEE Trans Ind Inform 17(12):8243–8253
Huang Q, Li JH, Zhu MS (2020) An improved convolutional neural network with load range discretization for probabilistic load forecasting. Energy 203:117902
Zhang WJ, Quan H, Srinivasan D (2018) Parallel and reliable probabilistic load forecasting via quantile regression forest and quantile determination. Energy 160:810–819
Wen HL, Gu J, Ma JH, Yuan L, Jin ZJ (2021) Probabilistic load forecasting via neural basis expansion model based prediction intervals. IEEE Trans Smart Grid 12(4):3648–3660
Brusaferri A, Matteucci M, Spinelli S, Vitali A (2022) Probabilistic electric load forecasting through Bayesian mixture density networks. Appl Energy 309:118341
Wan C, Cao Z, Lee WJ, Song Y, Ju P (2021) An adaptive ensemble data driven approach for nonparametric probabilistic forecasting of electricity load. IEEE Trans Smart Grid 12(6):5396–5408
Jeong D, Park C, Ko YM (2021) Short-term electric load forecasting for buildings using logistic mixture vector autoregressive model with curve registration. Appl Energy 282:116249
Wang Y, Gan DH, Sun MY, Zhang N, Lu ZX, Kang CQ (2019) Probabilistic individual load forecasting using pinball loss guided LSTM. Appl Energy 235:10–20
Arora P, Khosravi A, Panigrahi BK, Suganthan PN (2022) Remodelling state-space prediction with deep neural networks for probabilistic load forecasting. IEEE Trans Emerg Topics Comput Intell 6(3):628–637
Lai GK, Chang WC, Yang YM, Liu HX (2018) Modeling long-and short-term temporal patterns with deep neural networks. In the 41st international ACM SIGIR conference on Research & Development in information retrieval, July 8-12, MI, USA, pp 95–104
Zhang WJ, Quan H, Srinivasan D (2018) An improved quantile regression neural network for probabilistic load forecasting. IEEE Trans Smart Grid 10(4):4425–4434
Yang YD, Hong WJ, Li SF (2019) Deep ensemble learning based probabilistic load forecasting in smart grids. Energy 189:116324
Meinshausen N, Ridgeway G (2006) Quantile regression forests. J Mach Learn Res 7(6):983–999
He YY, Qin Y, Wang S, Wang X, Wang C (2019) Electricity consumption probability density forecasting method based on LASSO-quantile regression neural network. Appl Energy 233:565–575
Zang HX, Xu RQ, Cheng LL, Ding T, Liu L, Wei ZN, Sun GQ (2021) Residential load forecasting based on LSTM fusing self-attention mechanism with pooling. Energy 229:120682
Gan DH, Wang Y, Yang S, Kang CQ (2018) Embedding based quantile regression neural network for probabilistic load forecasting. J Mod Power Syst Clean Energy 6(2):244–254
Xie J, Hong T (2018) Temperature scenario generation for probabilistic load forecasting. IEEE Trans Smart Grid 9(3):1680–1687
Lou YW, Huang Y, Xing XL, Cao YZ, Wang HP (2022) MTS-LSTDM: multi-time-scale long short-term double memory for power load forecasting. J Syst Archit 125:102443
Liu H, Liu T, Chen Y, Zhang Z, Li YF (2022) EHPE: skeleton cues-based gaussian coordinate encoding for efficient human pose estimation. IEEE Trans Multimed:1–12. https://doi.org/10.1109/TMM.2022.3197364
Liu H, Nie HW, Zhang ZL, Li YF (2021) Anisotropic angle distribution learning for head pose estimation and attention understanding in human-computer interaction. Neurocomputing 433:310–322
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780
Deng JF, Cheng LL, Wang ZW (2021) Attention-based BiLSTM fused CNN with gating mechanism model for Chinese long text classification. Comput Speech Lang 68:101182
Peng YQ, Xiao TF, Yuan HT (2022) Cooperative gating network based on a single BERT encoder for aspect term sentiment analysis. Appl Intell 52(5):5867–5879
Wu ZH, Pan SR, Long GD, Jiang J, Zhang CQ (2019) Graph wavenet for deep spatial-temporal graph modeling. In the 28th International Joint Conference on Artificial Intelligence, august 10-16, Macao, China, pp 1907–1913
Ienco D, Interdonato R (2023) Deep semi-supervised clustering for multi-variate time-series. Neurocomputing 516:36–47
Afrasiabi M, Mohammadi M, Rastegar M, Stankovic L, Afrasiabi S, Khazaei M (2020) Deep-based conditional probability density function forecasting of residential loads. IEEE Trans Smart Grid 11(4):3646–3657
Liu RH, Chen T, Sun GP, Muyeen SM, Lin SF, Mi Y (2022) Short-term probabilistic building load forecasting based on feature integrated artificial intelligent approach. Electr Power Syst Res 206:107802
Liu H, Zheng C, Li DTCL, Shen XX, Lin K, Wang JZ et al (2021) EDMF: efficient deep matrix factorization with review feature learning for industrial recommender system. IEEE Trans Ind Inform 18(7):4361–4371
Li ZF, Liu H, Zhang ZL, Liu TT, Xiong NN (2022) Learning knowledge graph embedding with heterogeneous relation attention networks. IEEE Trans Neural Netw Learn Syst 33(8):3961–3973
Liu JS, Kang Y, Li H, Wang HN, Yang XK (2022) STGHTN: spatial-temporal gated hybrid transformer network for traffic flow forecasting. Appl Intell. https://doi.org/10.1007/s10489-022-04122-x
Liu G, Guo JB (2019) Bidirectional LSTM with attention mechanism and convolutional layer for text classification. Neurocomputing 337:325–338
Niu ZY, Zhong GQ, Yu H (2021) A review on the attention mechanism of deep learning. Neurocomputing 452:48–62
Wang SX, Wang X, Wang SM, Wang D (2019) Bi-directional long short-term memory method based on attention mechanism and rolling update for short-term load forecasting. Int J Electr Power Energy Syst 109:470–479
Huang Y, Huang Z, Yu JH, Dai XH, Li YY (2022) Short-term load forecasting based on IPSO-DBiLSTM network with variational mode decomposition and attention mechanism. Appl Intell. https://doi.org/10.1007/s10489-022-04174-z
Lin J, Ma J, Zhu JG, Cui Y (2022) Short-term load forecasting based on LSTM networks considering attention mechanism. Int J Electr Power Energy Syst 137:107818
Zhang H, Yan J, Liu YQ, Gao YQ, Han S, Li L (2021) Multi-source and temporal attention network for probabilistic wind power prediction. IEEE Trans Sustain Energy 12(4):2205–2218
Huang ST, Wang DL, Wu XH, Tang A (2019) Dsanet: dual self-attention network for multivariate time series forecasting. In the 28th ACM international conference on information and knowledge management, November 3–7, Beijing, China, pp 2129–2132
Zhang WY, Chen Q, Yan JY, Zhang S, Xu JY (2021) A novel asynchronous deep reinforcement learning model with adaptive early forecasting method and reward incentive mechanism for short-term load forecasting. Energy 236:121492
Rafi SH, Deeba SR, Hossain E (2021) A short-term load forecasting method using integrated CNN and LSTM network. IEEE Access 9:32436–32448