{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T17:44:03Z","timestamp":1783964643536,"version":"3.55.0"},"reference-count":32,"publisher":"SAGE Publications","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IDA"],"published-print":{"date-parts":[[2021,3,4]]},"abstract":"<jats:p>The energy load data in the micro-energy network are a time series with sequential and nonlinear characteristics. This paper proposes a model based on the encode-decode architecture and ConvLSTM for multi-scale prediction of multi-energy loads in the micro-energy network. We apply ConvLSTM, LSTM, attention mechanism and multi-task learning concepts to construct a model specifically for processing the energy load forecasting of the micro-energy network. In this paper, ConvLSTM is used to encode the input time series. The attention mechanism is used to assign different weights to the features, which are subsequently decoded by the decoder LSTM layer. Finally, the fully connected layer interprets the output. This model is applied to forecast the multi-energy load data of the micro-energy network in a certain area of Northwest China. The test results prove that our model is convergent, and the evaluation index value of the model is better than that of the multi-task FC-LSTM and the single-task FC-LSTM. In particular, the application of the attention mechanism makes the model converge faster and with higher precision.<\/jats:p>","DOI":"10.3233\/ida-194969","type":"journal-article","created":{"date-parts":[[2021,3,9]],"date-time":"2021-03-09T12:45:26Z","timestamp":1615293926000},"page":"359-382","source":"Crossref","is-referenced-by-count":19,"title":["Multi-task prediction model based on ConvLSTM and encoder-decoder"],"prefix":"10.1177","volume":"25","author":[{"given":"Tao","family":"Luo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xudong","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueliang","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","reference":[{"key":"10.3233\/IDA-194969_ref2","unstructured":"I. Sutskever, O. Vinyals and Q.V. Le, Sequence to Sequence Learning with Neural Networks [C], in: NIPS. MIT Press, 2014."},{"issue":"3","key":"10.3233\/IDA-194969_ref3","first-page":"698","article-title":"Multi-task learning based on deep architecture for various types of load forecasting in regional energy system integration [J]","volume":"42","author":"Jiaqi","year":"2018","journal-title":"Power System Technology"},{"key":"10.3233\/IDA-194969_ref4","doi-asserted-by":"crossref","unstructured":"A.Y. Saber and A.K.M.R. Alam, Short term load forecasting using multiple linear regression for big data [C], in: IEEE Symposium Series on Computational Intelligence (SSCI), 2017.","DOI":"10.1109\/SSCI.2017.8285261"},{"key":"10.3233\/IDA-194969_ref5","doi-asserted-by":"crossref","first-page":"877","DOI":"10.1016\/j.energy.2014.07.064","article-title":"Heating, cooling, and electrical load forecasting for a large-scale district energy system [J]","volume":"74","author":"Powell","year":"2014","journal-title":"Energy"},{"key":"10.3233\/IDA-194969_ref7","unstructured":"L. Pengfei, Q. Xipeng and H. Xuanjing, Recurrent neural network for text classification with multi-task learning, in: International Joint Conference on Artificial Intelligence, 2016, pp. 2873\u20132879."},{"key":"10.3233\/IDA-194969_ref8","unstructured":"L. Pengfei, Q. Xipeng and H. Xuanjing, Adversarial multi-task learning for text classification, in: Meeting of the Association for Computational Linguistics, Vol. 1, 2017, pp. 1\u201310."},{"key":"10.3233\/IDA-194969_ref9","doi-asserted-by":"crossref","unstructured":"L. Yunpeng, H. Di, B. Junpeng et al., Multi-step ahead time series forecasting for different data patterns based on LSTM recurrent neural network [J], in: Proceedings \u2013 2017 14th Web Information Systems and Applications Conference, WISA 2017.","DOI":"10.1109\/WISA.2017.25"},{"key":"10.3233\/IDA-194969_ref10","doi-asserted-by":"crossref","unstructured":"F.A. Gers, D. Eck and J. Schmidhuber, Applying LSTM to Time Series Predictable through Time-Window Approaches [C], in: International Conference on Artificial Neural Networks, Springer, Berlin, Heidelberg, 2001.","DOI":"10.1007\/3-540-44668-0_93"},{"key":"10.3233\/IDA-194969_ref11","doi-asserted-by":"crossref","unstructured":"R.B. Girshick, J. Donahue, T. Darrell and J. Malik, Rich feature hierarchies for accurate object detection and semantic segmentation, in: Computer Vision and Pattern Recognition, 2014, pp. 580\u2013587. arXiv:1311.2524 [cs.CV].","DOI":"10.1109\/CVPR.2014.81"},{"key":"10.3233\/IDA-194969_ref12","doi-asserted-by":"crossref","unstructured":"J. Long, E. Shelhamer and T. Darrell, Fully convolutional networks for semantic segmentation, in: Computer Vision and Pattern Recognition, 2015, pp. 3431\u20133440.","DOI":"10.1109\/CVPR.2015.7298965"},{"issue":"11","key":"10.3233\/IDA-194969_ref13","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1023\/A:1007379606734","article-title":"Multitask learning [J]","volume":"28","author":"Caruana","year":"1997","journal-title":"Machine Learning"},{"issue":"8","key":"10.3233\/IDA-194969_ref14","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory [J]","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Computation"},{"key":"10.3233\/IDA-194969_ref15","doi-asserted-by":"crossref","unstructured":"G. Balikas, S. Moura and M.R. Amini, Multitask learning for fine-grained twitter sentiment analysis in: Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieva, 2017, pp. 1005\u20131008.","DOI":"10.1145\/3077136.3080702"},{"key":"10.3233\/IDA-194969_ref16","doi-asserted-by":"crossref","unstructured":"R. Collobert and J. Weston, A unified architecture for natural language processing: deep neural networks with multitask learning, in: International Conference on Machine Learning, 2008, pp. 160\u2013167.","DOI":"10.1145\/1390156.1390177"},{"key":"10.3233\/IDA-194969_ref17","unstructured":"L. Pengfei, Q. Xipeng and H. Xuanjing, Deep multi-task learning with shared memory, in: Conference on Empirical Methods in Natural Language Processing, 2016."},{"key":"10.3233\/IDA-194969_ref18","unstructured":"L. Pengfei, Q. Xipeng and H. Xuanjing, Recurrent neural network for text classification with multi-task learning, in: International Joint Conference on Artificial Intelligence, 2016, pp. 2873\u20132879."},{"key":"10.3233\/IDA-194969_ref20","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1016\/j.apenergy.2018.11.063","article-title":"Hybrid forecasting model based on long short term memory network and deep learning neural network for wind signal [J]","volume":"236","author":"Yong","year":"2019","journal-title":"Applied Energy"},{"key":"10.3233\/IDA-194969_ref21","unstructured":"H. Kaiming, Z. Xiangyu, R. Shaoqing and S. Jian, Deep residual learning for image recognition, in: Computer Vision and Pattern Recognition, 2015, pp. 770\u2013778."},{"key":"10.3233\/IDA-194969_ref22","doi-asserted-by":"crossref","unstructured":"H. Kaiming, Z. Xiangyu, R. Shaoqing and S. Jian, Identity mappings in deep residual networks, in: European Conference on Computer Vision, 2016, pp. 630\u2013645.","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"10.3233\/IDA-194969_ref23","doi-asserted-by":"crossref","unstructured":"Y. Bengio, N. Boulanger-Lewandowski and R. Pascanu, Advances in optimizing recurrent networks, in: International Conference on Acoustics, Speech, and Signal Processing, 2013, pp. 8624\u20138628.","DOI":"10.1109\/ICASSP.2013.6639349"},{"key":"10.3233\/IDA-194969_ref24","doi-asserted-by":"crossref","unstructured":"L. Deng, M. Seltzer, D. Yu, A. Acero, A. Mohamed and G. Hinton, Binary coding of speech spectrograms using a deep autoencoder, in: Conference of the International Speech Communication Association, 2010, pp. 1692\u20131695.","DOI":"10.21437\/Interspeech.2010-487"},{"key":"10.3233\/IDA-194969_ref25","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1016\/j.eswa.2016.10.065","article-title":"Improving sentiment analysis via sentence type classification using BiLSTM-CRF and CNN","volume":"72","author":"Tao","year":"2017","journal-title":"Expert Systems with Application"},{"key":"10.3233\/IDA-194969_ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2017.02.030"},{"key":"10.3233\/IDA-194969_ref27","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1016\/j.procs.2014.05.296","article-title":"Sentiment classification based on AS-LDA model","volume":"31","author":"Jiguang","year":"2014","journal-title":"Procedia Computer Science"},{"key":"10.3233\/IDA-194969_ref28","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1016\/j.neucom.2016.01.110","article-title":"Topic-related Chinese message sentiment analysis","volume":"210","author":"Chong","year":"2016","journal-title":"Neurocomputing"},{"key":"10.3233\/IDA-194969_ref32","unstructured":"B. Jimmy, M. Volodymyr and K. Koray, Multiple object recognition with visual attention, in: International Conference on Learning Representations, 2015."},{"key":"10.3233\/IDA-194969_ref33","unstructured":"L. Pengfei, Q. Xipeng and H. Xuanjing, Deep multi-task learning with shared memory, in: Conference on Empirical Methods in Natural Language Processing, 2016."},{"issue":"8","key":"10.3233\/IDA-194969_ref35","first-page":"131","article-title":"Short-term load forecasting method based on CNN-LSTM hybrid neural network model","volume":"43","author":"JiXiang","year":"2019","journal-title":"Automation of Electric Power Systems"},{"issue":"1","key":"10.3233\/IDA-194969_ref36","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proceedings of the IEEE"},{"key":"10.3233\/IDA-194969_ref38","doi-asserted-by":"crossref","unstructured":"D.E. Rumelhart, G.E. Hinton and R.J. Williams, Learning representations by back-propagating errors, Nature 23 (1986).","DOI":"10.21236\/ADA164453"},{"issue":"7","key":"10.3233\/IDA-194969_ref39","doi-asserted-by":"crossref","first-page":"2220","DOI":"10.3390\/s18072220","article-title":"A deep CNN-LSTM model for particulate matter (PM2.5) forecasting in smart cities [J]","volume":"18","author":"Chiou-Jye","year":"2018","journal-title":"Sensors"},{"key":"10.3233\/IDA-194969_ref40","doi-asserted-by":"publisher","first-page":"1508","DOI":"10.3745\/JIPS.02.0104","article-title":"CNN-LSTM coupled model for prediction of waterworks operation data","volume":"14","author":"Cao","year":"2018","journal-title":"Journal of Information Processing Systems"}],"container-title":["Intelligent Data Analysis"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/IDA-194969","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:18:57Z","timestamp":1777454337000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/IDA-194969"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,4]]},"references-count":32,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.3233\/ida-194969","relation":{},"ISSN":["1088-467X","1571-4128"],"issn-type":[{"value":"1088-467X","type":"print"},{"value":"1571-4128","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,4]]}}}