Neural networks for online learning of non-stationary data streams: a review and application for smart grids flexibility improvement

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.

[1]  Hussein T. Mouftah,et al.  Wireless Sensor Networks for Cost-Efficient Residential Energy Management in the Smart Grid , 2011, IEEE Transactions on Smart Grid.

[2]  Robi Polikar,et al.  Incremental Learning of Concept Drift in Nonstationary Environments , 2011, IEEE Transactions on Neural Networks.

[3]  Javier Del Ser,et al.  Evolving Spiking Neural Networks for online learning over drifting data streams , 2018, Neural Networks.

[4]  Geoffrey I. Webb,et al.  Adaptive online extreme learning machine by regulating forgetting factor by concept drift map , 2019, Neurocomputing.

[5]  Gerhard Widmer,et al.  Adapting to Drift in Continuous Domains (Extended Abstract) , 1995, ECML.

[6]  Yue Dong,et al.  Threaded Ensembles of Supervised and Unsupervised Neural Networks for Stream Learning , 2016, Canadian Conference on AI.

[7]  Robi Polikar,et al.  Incremental Learning of Variable Rate Concept Drift , 2009, MCS.

[8]  Hadi Sadoghi Yazdi,et al.  Online cost-sensitive neural network classifiers for non-stationary and imbalanced data streams , 2012, Neural Computing and Applications.

[9]  João Gama,et al.  Evaluating algorithms that learn from data streams , 2009, SAC '09.

[10]  Paul Denholm,et al.  Grid flexibility and storage required to achieve very high penetration of variable renewable electricity , 2011 .

[11]  João Gama,et al.  A survey on concept drift adaptation , 2014, ACM Comput. Surv..

[12]  Seung Ho Hong,et al.  Incentive-based demand response for smart grid with reinforcement learning and deep neural network , 2019, Applied Energy.

[13]  EnergyInformationAdministration.  Annual Energy Outlook 2008 With Projections to 2030 , 2008 .

[14]  Hadi Sadoghi Yazdi,et al.  Ensemble of online neural networks for non-stationary and imbalanced data streams , 2013, Neurocomputing.

[15]  Ying Tan,et al.  Recentness biased learning for time series forecasting , 2013, Inf. Sci..

[16]  Guang-Bin Huang,et al.  Extreme learning machine: a new learning scheme of feedforward neural networks , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[17]  Abdelhamid Bouchachia,et al.  Incremental learning with multi-level adaptation , 2011, Neurocomputing.

[18]  Gang Xiong,et al.  A Communication-Based Appliance Scheduling Scheme for Consumer-Premise Energy Management Systems , 2013, IEEE Transactions on Smart Grid.

[19]  Michal Wozniak,et al.  Data stream classification using active learned neural networks , 2019, Neurocomputing.

[20]  Federico Milano,et al.  Demand response algorithms for smart-grid ready residential buildings using machine learning models , 2019, Applied Energy.

[21]  Yauheni Marushko,et al.  Ensembles of Neural Network for Telemetry Multivariate Time Series Forecasting , 2016, ICPR 2016.

[22]  Rui Araújo,et al.  An adaptive ensemble of on-line Extreme Learning Machines with variable forgetting factor for dynamic system prediction , 2016, Neurocomputing.

[23]  Mateusz Zarkowski.  Adaptive Online Neural Network for Face Identification with Concept Drift , 2014, IEEE Conf. on Intelligent Systems.

[24]  Alagan Anpalagan,et al.  Appliance Scheduling Optimization in Smart Home Networks , 2015, IEEE Access.

[25]  Javier Del Ser,et al.  Drift Detection over Non-stationary Data Streams Using Evolving Spiking Neural Networks , 2018, IDC.

[26]  Jude W. Shavlik,et al.  Understanding Time-Series Networks: A Case Study in Rule Extraction , 1997, Int. J. Neural Syst..

[27]  Leszek Rutkowski,et al.  Probabilistic Neural Networks for the Streaming Data Classification , 2020 .

[28]  Ryszard S. Michalski,et al.  Incremental learning with partial instance memory , 2002, Artif. Intell..

[29]  Carlos Eduardo Cancino Chacón,et al.  Strategies for Conceptual Change in Convolutional Neural Networks , 2017, ArXiv.

[30]  Mohamad Ivan Fanany,et al.  Adaptive Convolutional ELM For Concept Drift Handling in Online Stream Data , 2016, ArXiv.

[31]  Adriano Lorena Inácio de Oliveira,et al.  An approach to handle concept drift in financial time series based on Extreme Learning Machines and explicit Drift Detection , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[32]  REMODECE Brochure.  Residential Monitoring to Decrease Energy Use and Carbon Emissions in Europe , 2019 .

[33]  Takuro Sato,et al.  COST -EFFICIENT RESIDENTIAL ENERGY MANAGEMENT SCHEME FOR INFORMATION -CENTRIC NETWORKING BASED HOME NETWORK IN SMART GRID , 2016 .

[34]  Lazaros G. Papageorgiou,et al.  Optimal Scheduling of Smart Homes Energy Consumption with Microgrid , 2011 .

[35]  João Gama,et al.  Learning from Data Streams , 2009, Encyclopedia of Data Warehousing and Mining.

[36]  Mahardhika Pratama,et al.  Online identification of a rotary wing Unmanned Aerial Vehicle from data streams , 2019, Appl. Soft Comput..

[37]  Sung Wook Baik,et al.  Action recognition using optimized deep autoencoder and CNN for surveillance data streams of non-stationary environments , 2019, Future Gener. Comput. Syst..

[38]  Amparo Alonso-Betanzos,et al.  A robust incremental learning method for non-stationary environments , 2011, Neurocomputing.

[39]  Jörg Franke,et al.  Energy efficiency in strategy of sustainable production , 2015 .

[40]  Yoshua Bengio,et al.  Online continual learning with no task boundaries , 2019, ArXiv.

[41]  Moamar Sayed Mouchaweh,et al.  A Review on Machine Learning and Data Mining Techniques for Residential Energy Smart Management , 2016, 2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA).

[42]  Lamjed Ben Said,et al.  On-line self-adaptive framework for tailoring a neural-agent learning model addressing dynamic real-time scheduling problems , 2017 .

[43]  Christophe G. Giraud-Carrier,et al.  Efficient mining of high-speed uncertain data streams , 2015, Applied Intelligence.

[44]  Tongquan Wei,et al.  Uncertainty-Aware Household Appliance Scheduling Considering Dynamic Electricity Pricing in Smart Home , 2013, IEEE Transactions on Smart Grid.

[45]  Robi Polikar,et al.  Learning concept drift in nonstationary environments using an ensemble of classifiers based approach , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[46]  Mahardhika Pratama,et al.  An Incremental Learning of Concept Drifts Using Evolving Type-2 Recurrent Fuzzy Neural Networks , 2017, IEEE Transactions on Fuzzy Systems.

[47]  Robi Polikar,et al.  Incremental learning in non-stationary environments with concept drift using a multiple classifier based approach , 2008, 2008 19th International Conference on Pattern Recognition.

[48]  Daniel F. Leite,et al.  Evolving fuzzy granular modeling from nonstationary fuzzy data streams , 2012, Evol. Syst..

[49]  Leszek Rutkowski,et al.  Stream Data Mining: Algorithms and Their Probabilistic Properties , 2019, Studies in Big Data.

[50]  Nadeem Javaid,et al.  Energy Optimization in Smart Homes Using Customer Preference and Dynamic Pricing , 2016 .

[51]  João Gama,et al.  Learning with Drift Detection , 2004, SBIA.

[52]  Koichiro Yamauchi.  Incremental model selection and ensemble prediction under virtual concept drifting environments , 2011, Evol. Syst..

[53]  Zhiping Lin,et al.  Meta-cognitive online sequential extreme learning machine for imbalanced and concept-drifting data classification , 2016, Neural Networks.

[54]  Tian Xia,et al.  Robust optimization for home-load scheduling under price uncertainty in smart grids , 2015, 2015 International Conference on Computing, Networking and Communications (ICNC).

[55]  Robi Polikar,et al.  Learn$^{++}$ .NC: Combining Ensemble of Classifiers With Dynamically Weighted Consult-and-Vote for Efficient Incremental Learning of New Classes , 2009, IEEE Transactions on Neural Networks.

[56]  Suresh Venkatasubramanian,et al.  Streamed Learning: One-Pass SVMs , 2009, IJCAI.

[57]  Geoff Holmes,et al.  Scalable and efficient multi-label classification for evolving data streams , 2012, Machine Learning.

[58]  Leszek Rutkowski,et al.  Nonparametric Regression Models for Data Streams Based on the Generalized Regression Neural Networks , 2019, Studies in Big Data.

[59]  Stéphane Ploix,et al.  Managing Energy Smart Homes according to Energy Prices: Analysis of a Building Energy Management System , 2014 .

[60]  Albert Bifet,et al.  DATA STREAM MINING A Practical Approach , 2009 .

[61]  Patrick C. K. Hung,et al.  Big Data Applications and Use Cases , 2016, International Series on Computer Entertainment and Media Technology.

[62]  Leszek Rutkowski,et al.  General Non-parametric Learning Procedure for Tracking Concept Drift , 2019, Studies in Big Data.

[63]  Nithish B. Moudhgalya,et al.  Forecasting Food Sales in a Multiplex Using Dynamic Artificial Neural Networks , 2019, Advances in Intelligent Systems and Computing.

[64]  Hadi Sadoghi Yazdi,et al.  Online neural network model for non-stationary and imbalanced data stream classification , 2014, Int. J. Mach. Learn. Cybern..

[65]  Rui Araújo,et al.  A dynamic and on-line ensemble regression for changing environments , 2015, Expert Syst. Appl..

[66]  Robi Polikar,et al.  Incremental learning in nonstationary environments with controlled forgetting , 2009, 2009 International Joint Conference on Neural Networks.

[67]  Nan Liu,et al.  Ensemble of subset online sequential extreme learning machine for class imbalance and concept drift , 2015, Neurocomputing.

[68]  Khaled Ghédira,et al.  Self-Adaptive Windowing Approach for Handling Complex Concept Drift , 2015, Cognitive Computation.

[69]  V. Miranda,et al.  Entropy and Correntropy Against Minimum Square Error in Offline and Online Three-Day Ahead Wind Power Forecasting , 2009, IEEE Transactions on Power Systems.

[70]  Cesare Alippi,et al.  Just-in-Time Adaptive Classifiers—Part I: Detecting Nonstationary Changes , 2008, IEEE Transactions on Neural Networks.

[71]  He Jiang,et al.  FP-ELM: An online sequential learning algorithm for dealing with concept drift , 2016, Neurocomputing.

[72]  Mohamad Ivan Fanany,et al.  Adaptive Online Sequential ELM for Concept Drift Tackling , 2016, Comput. Intell. Neurosci..

[73]  Ning Lu,et al.  Concept drift detection via competence models , 2014, Artif. Intell..

[74]  Bhawani Shankar Chowdhry,et al.  5 Home Energy Management within Smart Grid via WSN , 2012 .

[75]  Dianhui Wang,et al.  Deep stacked stochastic configuration networks for lifelong learning of non-stationary data streams , 2019, Inf. Sci..

[76]  Qun Dai,et al.  A competitive ensemble pruning approach based on cross-validation technique , 2013, Knowl. Based Syst..

[77]  Lovekesh Vig,et al.  Online anomaly detection with concept drift adaptation using recurrent neural networks , 2018, COMAD/CODS.

[78]  Zbigniew Telec,et al.  Evaluation of Neural Network Ensemble Approach to Predict from a Data Stream , 2014, ICCCI.

[79]  Johannes Bürner,et al.  An Artificial Intelligence Approach for Online Optimization of Flexible Manufacturing Systems , 2018, Applied Mechanics and Materials.

[80]  Daniel F. Leite,et al.  Evolving granular neural networks from fuzzy data streams , 2013, Neural Networks.

[81]  Jennifer Widom,et al.  Models and issues in data stream systems , 2002, PODS.

[82]  Nuno C. Marques.  Applying Neural Networks for Concept Drift Detection in Financial Markets (Proceedings Ubiquitous Data Miningorkshop, in conjunction with ECAI 2012.) , 2012 .

[83]  Piotr Duda,et al.  Convergent Time-Varying Regression Models for Data Streams: Tracking Concept Drift by the Recursive Parzen-Based Generalized Regression Neural Networks , 2017, Int. J. Neural Syst..

[84]  Witold Pedrycz,et al.  An Incremental Construction of Deep Neuro Fuzzy System for Continual Learning of Nonstationary Data Streams , 2018, IEEE Transactions on Fuzzy Systems.