Abstract
Learning efficient predictive models in dynamic environments requires taking into account the continuous changing nature of phenomena generating the data streams, known in machine learning as “concept drift”. Such changes may affect models’ effectiveness over time, requiring permanent updates of parameters and structure to maintain performance. Several supervised machine learning methods have been developed to be adapted to learn in dynamic and non-stationary environments. One of the most well-known and efficient learning methods is neural networks. This paper focuses on the different neural networks developed to build learning models able to adapt to concept drifts on streaming data. Their performance will be studied and compared using meaningful criteria. Their limits to address the challenges related to the problem of the improvement of electrical grid flexibility in presence of distributed Wind–PV renewable energy resources within the context of energy transition will be highlighted. Finally, the study provides a self-adaptive scheme based on the use of neural networks to overcome these limitations and tackle these challenges.
Similar content being viewed by others
References
Alippi C, Roveri M (2008) Just-in-time adaptive classifiers: part I: detecting nonstationary changes. IEEE Trans Neural Netw 19(7):1145–1153
Aljundi R, Lin M, Goujaud B, Bengio Y (2019) Online continual learning with no task boundaries. CoRR arXiv:1903.08671
Babcock B, Babu S, Datar M, Motwani R, Widom J (2002) Models and issues in data stream systems. In: Proceedings of the 21st ACM SIGMOD-SIGACT-SIGART symposium on principles of database systems, pp 1–16
Bakakeu J, Tolksdorf S, Bauer J, Klos HH, Peschke J, Fehrle A, Eberlein W, Bürner J, Brossog M, Jahn L, Franke J (2018) An artificial intelligence approach for online optimization of flexible manufacturing systems. In: Energy efficiency in strategy of sustainable production IV. Applied Mechanics and Materials, vol 882, pp 96–108
Bessa RJ, da Costa Miranda V, da Gama JMP (2009) Entropy and correntropy against minimum square error in offline and online three-day ahead wind power forecasting. IEEE Trans Power Syst 24:1657–1666
Bifet A, Kirkby R (2009) Data stream mining a practical approach. Citeseerx, Oxford
Bouchachia A (2011) Incremental learning with multi-level adaptation. Neurocomputing 74:1785–1799
Budiman A, Fanany MI, Basaruddin C (2016) Adaptive convolutional ELM for concept drift handling in online stream data. CoRR
Cavalcante RC, Oliveira ALI (2015) An approach to handle concept drift in financial time series based on extreme learning machines and explicit drift detection. In: IJCNN. IEEE, New York, pp 1–8
Chen C, Nagananda KG, Xiong G, Kishore S, Snyder LV (2013a) A communication-based appliance scheduling scheme for consumer-premise energy management systems. IEEE Trans Smart Grid 4:56–65
Chen X, Wei T, Hu S (2013b) Uncertainty-aware household appliance scheduling considering dynamic electricity pricing in smart home. IEEE Trans Smart Grid 4:1–10
Craven M, Shavlik JW (1997) Understanding time-series networks: a case study in rule extraction. Int J Neural Syst 8(4):373–384
Dai Q (2013) A competitive ensemble pruning approach based on cross-validation technique. Know Based Syst 37:394–414
de Almeida A, Fonseca P, Bandeirinha R, Fernandes T, Araújo R, Nunes U (2006) Residential monitoring to decrease energy use and carbon emissions in Europe. https://remodece.isr.uc.pt/downloads/REMODECE_PublishableReport_Nov2008_FINAL.pdf
Denholma P, Hand M (2011) Grid flexibility and storage required to achieve very high penetration of variable renewable electricity. Energy Policy 39:1817–1830
Dong Y, Japkowicz N (2016) Advances in artificial intelligence, vol 9673, Chap Threaded ensembles of supervised and unsupervised neural networks for stream learning, pp 304–315
Doudkin A, Marushko Y (2017) Ensembles of neural network for telemetry multivariate time series forecasting. In: International conference on pattern recognition and information processing, communications in computer and information science, pp 53–62
Duda P, Jaworski M, Rutkowski L (2018) Convergent time-varying regression models for data streams: tracking concept drift by the recursive Parzen-based generalized regression neural networks. Int J Neural Syst 28:1750 (048–1–23)
Elwell R, Polikar R (2009a) Incremental learning in nonstationary environments with controlled forgetting. In: 2009 international joint conference on neural networks, pp 771–778
Elwell R, Polikar R (2009b) Incremental learning of variable rate concept drift. In: MCS ’09: Proceedings of the 8th international workshop on multiple classifier systems, pp 142–151. https://doi.org/10.1007/978-3-642-02326-2_15
Elwell R, Polikar R (2011) Incremental learning of concept drift in nonstationary environments. IEEE Trans Neural Netw 22(10):1517–1531
Erol-Kantarci M, Mouftah HT (2011) Wireless sensor networks for cost-efficient residential energy management in the smart grid. IEEE Trans Smart Grid 2:314–325
Ferdaus MM, Pratama M, Anavatti SG, Garratt MA (2019) Online identification of a rotary wing unmanned aerial vehicle from data streams. Appl Soft Comput 76:313–325
Fong S, Fang C, Tian N, Wong R, Yap BW (2016) Big data applications and use cases. Chap self-adaptive parameters optimization for incremental classification in big data using neural network, pp 175–196
Gama J, Pedersen RU (2007) Learning from data streams. Chap Predictive learning in sensor networks, pp 143–164
Gama J, Medas P, Castillo G, Rodrigues P (2004) Learning with drift detection. In: Advances in artificial intelligence-SBIA 2004. Springer, Berlin, pp 286–295
Gama J, Rodrigues PP, Sebastiao R (2009) Evaluating algorithms that learn from data streams. In: Proceedings of the 2009 ACM symposium on applied computing, pp 1496–1500
Gama J, Zliobaite I, Bifet A, Pechenizkiy M, Bouchachia A (2014) A survey on concept drift adaptation. ACM Comput Surv 46(4):44:1–44:37
Ganesan VA, Divi S, Moudhgalya NB, Sriharsha U, Vijayaraghavan V (2019) Forecasting food sales in a multiplex using dynamic artificial neural networks. In: Proceedings of the 2019 computer vision conference (CVC), advances in intelligent systems and computing, vol 944, pp 69–80. https://link.springer.com/chapter/10.1007/978-3-030-17798-0_8
Ghazikhani A, Monsefi R, Yazdi HS (2013a) Ensemble of online neural networks for non-stationary and imbalanced data streams. Neurocomputing 122:535–544
Ghazikhani A, Monsefi R, Yazdi HS (2013b) Online cost-sensitive neural network classifiers for non-stationary and imbalanced data streams. Neural Comput Appl 23:1283–1295
Ghazikhani A, Monsefi R, Yazdi HS (2014) Online neural network model for non-stationary and imbalanced data stream classification. Int J Mach Learn Cybern 5(1):51–62
Grachten M, Chacón CEC (2017) Strategies for conceptual change in convolutional neural networks. CoRR arXiv:1711.01634
Gu S, Tan Y, He X (2013) Recentness biased learning for time series forecasting. Inf Sci 237:29–38
Guo L, Wu HC, Zhang H, Xia T, Mehraeen S (2015) Robust optimization for home-load scheduling under price uncertainty in smart grids. In: International conference on computing, networking and communications (ICNC), pp 487–493
Hammami Z, Mouelhi W, Ben Said L (2017) On-line self-adaptive framework for tailoring a neural-agent learning model addressing dynamic real-time scheduling problems. J Manuf Syst 45:97–108
Han D, Giraud-Carrier C, Li S (2015) Efficient mining of high-speed uncertain data streams. Appl Intell 43(4):773–785
Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: a new learning scheme of feedforward neural networks. In: Proceedings of the international joint conference on neural networks, pp 985–990
Jesse R, Albert B, Geoff H, Bernhard P (2012) Scalable and efficient multi-label classification for evolving data streams. Mach Learn 88(1–2):243–272. https://doi.org/10.1007/s10994-012-5279-6
Karnick M, Ahiskali M, Muhlbaier MD, Polikar R (2008a) Learning concept drift in nonstationary environments using an ensemble of classifiers based approach. In: 2008 IEEE international joint conference on neural networks (IEEE world congress on computational intelligence), pp 345–3462
Karnick M, Muhlbaier MD, Polikar R (2008b) Incremental learning in non-stationary environments with concept drift using a multiple classifier based approach. In: 2008 19th international conference on pattern recognition. IEEE, New York
Khamassi I, Sayed-Mouchaweh M, Hammami M, Ghedira K (2015) Self-adaptive windowing approach for handling complex concept drift. Cogn Comput 7(6):772–790
Ksieniewicz P, Woźniak M, Cyganek B, Kasprzak A, Walkowiak K (2019) Data stream classification using active learned neural networks. Neurocomputing 353:74–82
Kubat M, Widmer G (1995) Adapting to drift in continuous domains (extended abstract). In: Machine learning: ECML-95, pp 307–310
Leite D, Ballini R, Costa P, Gomide F (2012) Evolving fuzzy granular modeling from nonstationary fuzzy data streams. Evol Syst 3(2):65–79
Leite D, Costa P, Gomide F (2013) Evolving granular neural networks from fuzzy data streams. Neural Netw 38:1–16
Liu D, Wu Y, Jiang H (2016) FP-ELM: an online sequential learning algorithm for dealing with concept drift. Neurocomputing 207:322–334
Lobo JL, Laña I, Ser JD, Bilbao MN, Kasabov N (2018a) Evolving spiking neural networks for online learning over drifting data streams. Neural Netw 108:1–19
Lobo JL, Ser JD, Bilbao ILMN, Kasabov N (2018b) Drift detection over non-stationary data streams using evolving spiking neural networks. In: International symposium on intelligent and distributed computing, intelligent distributed computing XII, pp 82–94
Lu N, Zhang G, Lu J (2014) Concept drift detection via competence models. Artif Intell 209:11–28
Lu R, Hong SH (2019) Incentive-based demand response for smart grid with reinforcement learning and deep neural network. Appl Energy 236:937–949
Maloof MA, Michalski RS (2004) Incremental learning with partial instance memory. Artif Intell 154(1–2):95–126
Martinez-Rego D, Perez-Sanchez B, Fontenla-Romero O, Alonso-Betanzos A (2011) A robust incremental learning method for non-stationary environments. Neurocomputing 74(11):1800–1808
Mirza B, Lin Z (2016) Meta-cognitive online sequential extreme learning machine for imbalanced and concept-drifting data classification. Neural Netw 80:79–94
Mirza B, Lin Z, Liu N (2015) Ensemble of subset online sequential extreme learning machine for class imbalance and concept drift. Neurocomputing 149:316–329
Missaoui R, Joumaaa H, Ploixa S, Bacha S (2014) Managing energy smart homes according to energy prices: analysis of a building energy management system. Energy Build 71:155–167
Muhlbaier MD, Topalis A, Polikar R (2009) Learn++.NC: combining ensemble of classifiers with dynamically weighted consult-and-vote for efficient incremental learning of new classes. IEEE Trans Neural Netw 20:152–168
Multiple (2018a) “Digitalization of the electricity system and customer participation” description and recommendations of technologies, use cases and cybersecurity. European Technology and Innovation Platforms (ETIP) Smart Networks for Energy Transition (SNET), Workgroup-4 “Digitalization of the Energy System and Customer Participation”. https://www.etip-snet.eu/wp-content/uploads/2018/10/ETIP-SNET-Position-Paper-on-Digitalisation-FINAL-1.pdf
Multiple (2018b) Eia (2018). Annual energy outlook 2018 with projections to 2050. Technical report, US Energy Information Administration. https://www.eia.gov/outlooks/aeo/pdf/AEO2018.pdf
Pallonetto F, De-Rosa M, Milano F, Finn DP (2019) Demand response algorithms for smart-grid ready residential buildings using machine learning models. Appl Energy 239:1265–1282
Pratama M, Wang D (2019) Deep stacked stochastic configuration networks for lifelong learning of non-stationary data streams. Inf Sci 495:150–174
Pratama M, Lu J, Lughofer E, Zhang G, Er MJ (2017) An incremental learning of concept drifts using evolving type-2 recurrent fuzzy neural networks. IEEE Trans Fuzzy Syst 25:1175–1192
Pratama M, Pedrycz W, Webb GI (2018) An incremental construction of deep neuro fuzzy system for continual learning of non-stationary data streams. CoRR, pp 1–13. arXiv:1808.08517
Qayyum FA, Naeem M, Khwaja AS, Anpalagan A, Guan L, Venkatesh B (2015) Appliance scheduling optimization in smart home networks. IEEE Access 3:2176–2190
Rai P, III HD, Venkatasubramanian S (2009) Streamed learning: one-pass SVMS. In: Proceeding IJCAI’09 proceedings of the 21st international joint conference on artifical intelligence, pp 1211–1216
Rajput P, Rajput K, Shaikh MZ, Chowdhry BS, Aamir M (2012) Home energy management within smart grid via WSN. In: IEEE international multi topic conference, vol 2, pp 23–26
Rasheed MB, Javaid N, Ahmad A, Jamil M, Khan ZA, Qasim U, Alrajeh N (2016) Energy optimization in smart homes using customer preference and dynamic pricing. Energies 9:1–25
Rutkowski L, Jaworski M, Duda P (2020a) Stream data mining: algorithms and their probabilistic properties. Chap Probabilistic neural networks for the streaming data classification, pp 245–277
Rutkowski L, Jaworski M, Duda P (2020b) Stream data mining: algorithms and their probabilistic properties. Chap Nonparametric regression models for data streams based on the generalized regression neural networks, pp 173–244
Rutkowski L, Jaworski M, Duda P (2020c) Stream data mining: algorithms and their probabilistic properties. Chap General non-parametric learning procedure for tracking concept, Drift, pp 155–172
Sakti S, Pankaj M, Vishnu T, Narendhar G, Lovekesh V, Puneet A, Gautam S (2018) Online anomaly detection with concept drift adaptation using recurrent neural networks. In: Proceedings of the ACM India joint international conference on data science and management of data, CoDS-COMAD’18. ACM, New York, pp 78–87
Salem H, Sayed-Mouchaweh M, Ben Hassine A (2016) A review on machine learning and data mining techniques for residential energy smart management. In: 2016 15th IEEE international conference on machine learning and applications (ICMLA), pp 1074–1076
Silva B, Marques N, Panosso G (2012) Applying neural networks for concept drift detection in financial markets. In: CEUR workshop proceedings, vol 960, pp 43–47
Soares S, Araujo R (2015a) An adaptive ensemble of on-line extreme learning machines with variable forgetting factor for dynamic system prediction. Neurocomputing 171:693–707
Soares S, Araujo R (2015b) A dynamic and on-line ensemble regression for changing environments. Expert Syst Appl 42:2935–2948
Telec Z, Trawinski B, Lasota T, Trawinski G (2014) Evaluation of neural network ensemble approach to predict from a data stream. In: 6th International conference on computational collective intelligence. Technologies and applications, pp 472–482
Ullah A, Muhammad K, Haq IU, Baik SW (2019) Action recognition using optimized deep autoencoder and cnn for surveillance data streams of non-stationary environments. Fut Gener Comput Syst 96:386–397
Yamauchi K (2011) Incremental model selection and ensemble prediction under virtual concept drifting environments. Evol Syst 2:249–260
Yu H, Webb GI (2019) Adaptive online extreme learning machine by regulating forgetting factor by concept drift map. Neurocomputing 343:141–153
Yu K, Davaasambuu B, Nguyenand NH, Nguyen Q, Mohammad A, Sato T (2016) Cost-efficient residential energy management scheme for information-centric networking based home network in smart grid. Int J Comput Netw Commun 8:25–42
Zarkowski M (2015) Adaptive online neural network for face identification with concept drift. In: Intelligent systems’ 2014, pp 703–712
Zhang D, Papageorgiou LG, Samsatli NJ, Shah N (2011) Optimal scheduling of smart homes energy consumption with microgrid. In: ENERGY 2011: The 1st international conference on smart grids, green communications and IT energy-aware technologies, pp 70–75
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Hammami, Z., Sayed-Mouchaweh, M., Mouelhi, W. et al. Neural networks for online learning of non-stationary data streams: a review and application for smart grids flexibility improvement. Artif Intell Rev 53, 6111–6154 (2020). https://doi.org/10.1007/s10462-020-09844-3
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10462-020-09844-3