Data Analytics to Support Operational Distribution Network Monitoring

The operation of distribution networks has become more challenging in recent years with increasing levels of embedded generation and other low carbon technologies pushing these towards their design limits. To identify the nature and extent of these challenges, network operators are deploying monitoring equipment on low voltage feeders, leading to new insights into fault behaviour and usage characterisation. With this heightened level of observability comes the additional challenge of finding models that translate raw data streams into outputs on which operational decisions can be based or supported. In this paper, operational low voltage substation and feeder monitoring data from a UK distribution network is used to identify fault occurrence relations to localised meteorological data, characterise the localised network sensitivities of demand dynamics and infer the effects of embedded generation not visible to the network operator. These case studies are then used to show how additional operational context can be provided to the network operator through the application of analytics.

[1]  Philip M. Long,et al.  Predicting Electricity Distribution Feeder Failures Using Machine Learning Susceptibility Analysis , 2006, AAAI.

[2]  B. Don Russell,et al.  Reliability improvement of distribution feeders through real-time, intelligent monitoring , 2009, 2009 IEEE Power & Energy Society General Meeting.

[3]  Akshya Swain,et al.  Classification of power quality events using wavelet packet transform and extreme learning machine , 2016, 2016 IEEE 2nd Annual Southern Power Electronics Conference (SPEC).

[4]  Cleverson L. S. Pinto,et al.  A new approach for event classification and novelty detection in power distribution networks , 2013, 2013 IEEE Power & Energy Society General Meeting.

[5]  Emma M. Stewart,et al.  Synchrophasor data analytics in distribution grids , 2017, 2017 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT).

[6]  Mladen Kezunovic,et al.  Improving smart grid operation with new Hierarchically Coordinated Protection approach , 2012 .

[7]  David M. Laverty,et al.  Real-Time Multiple Event Detection and Classification Using Moving Window PCA , 2016, IEEE Transactions on Smart Grid.

[8]  Aldo Dagnino,et al.  Forecasting Fault Events in Power Distribution Grids Using Machine Learning , 2012, SEKE.

[9]  J. F. G. Cobben,et al.  Power quality data evaluation in distribution networks based on data mining techniques , 2013, 2013 12th International Conference on Environment and Electrical Engineering.

[10]  Alejandro Navarro-Espinosa,et al.  Representative residential LV feeders: A case study for the North West of England , 2016, 2016 IEEE Power and Energy Society General Meeting (PESGM).

[11]  David M. J. Tax,et al.  Novelty detection and multi-class classification in power distribution voltage waveforms , 2016, Expert Syst. Appl..

[12]  M. KEZUNOVIC,et al.  Hierarchically Coordinated Protection : An Integrated Concept of Corrective , Predictive , and Inherently Adaptive Protection , 2015 .

[13]  D. Sutanto,et al.  Analyzing Harmonic Monitoring Data Using Supervised and Unsupervised Learning , 2009, IEEE Transactions on Power Delivery.

[14]  S. Shen,et al.  The statistical analysis of compositional data , 1983 .

[15]  Yong Liu,et al.  Wide-area measurement system development at the distribution level: An FNET/GridEye example , 2016, 2016 IEEE Power and Energy Society General Meeting (PESGM).

[16]  B. Don Russell,et al.  Waveform analytics-based improvements in situational awareness, feeder visibility, and operational efficiency , 2014, 2014 IEEE PES T&D Conference and Exposition.