Dynamic Line Rating Using Numerical Weather Predictions and Machine Learning: A Case Study

In this paper, a dynamic line-rating experiment is presented in which four machine-learning algorithms (generalized linear models, multivariate adaptive regression splines, random forests and quantile random forests) are used in conjunction with numerical weather predictions to model and predict the ampacity up to 27 h ahead in two conductor lines located in Northern Ireland. The results are evaluated against reference models and show a significant improvement in performance for point and probabilistic forecasts. The usefulness of probabilistic forecasts in this field is shown through the computation of a safety-margin forecast which can be used to avoid risk situations. With respect to the state of the art, the main contributions of this paper are an in depth look at explanatory variables and their relation to ampacity, the use of machine learning with numerical weather predictions to model ampacity, the development of a probabilistic forecast from standard point forecasts, and a favorable comparison to standard reference models. These results are directly applicable to protect and monitor transmission and distribution infrastructures, especially if renewable energy sources and/or distributed power generation systems are present.

[1]  Jean-Louis Lilien,et al.  LARGE PENETRATION OF DISTRIBUTED PRODUCTIONS: DYNAMIC LINE RATING AND FLEXIBLE GENERATION, A MUST REGARDING INVESTMENT STRATEGY AND NETWORK RELIABILITY. , 2012 .

[2]  Tony Yip,et al.  Dynamic line rating protection for wind farm connections , 2009 .

[3]  Albert Moser,et al.  Probabilistic ampacity forecasting for overhead lines using weather forecast ensembles , 2013 .

[4]  A. K. Deb,et al.  Prediction of overhead transmission line ampacity by stochastic and deterministic models , 1988 .

[5]  Parsons Brinckerhoff,et al.  DYNAMIC THERMAL RATINGS : THE STATE OF THE ART , 2011 .

[6]  S. D. Foss,et al.  Effect of variability in weather conditions on conductor temperature and the dynamic rating of transmission lines , 1988 .

[7]  William A. Chisholm,et al.  Key Considerations for the Selection of Dynamic Thermal Line Rating Systems , 2015, IEEE Transactions on Power Delivery.

[8]  Ramesh Rayudu,et al.  Dynamic rating of transmission lines-a New Zealand experience , 2000, 2000 IEEE Power Engineering Society Winter Meeting. Conference Proceedings (Cat. No.00CH37077).

[9]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[10]  M.W. Davis,et al.  A new thermal rating approach: The real time thermal rating system for strategic overhead conductor transmission lines -- Part I: General description and justification of the real time thermal rating system , 1977, IEEE Transactions on Power Apparatus and Systems.

[11]  Michael Negnevitsky,et al.  Expert system application for the loading capability assessment of transmission lines , 1995 .

[12]  Rafael Lopez,et al.  Enhancing distributed generation penetration in smart grids through dynamic ratings , 2013, 2013 IEEE Grenoble Conference.

[13]  S. D. Foss,et al.  Dynamic line rating in the operating environment , 1990 .

[14]  S. D. Foss,et al.  Evaluation of an overhead line forecast rating algorithm , 1991 .

[15]  Jean-Louis Lilien,et al.  Dynamic line rating and ampacity forecasting as the keys to optimise power line assets with the integration of res. The European project Twenties Demonstration inside Central Western Europe , 2013 .

[16]  George K. Karagiannidis,et al.  Big Data Analytics for Dynamic Energy Management in Smart Grids , 2015, Big Data Res..

[17]  E. Siwy.  Risk Analysis in Dynamic Thermal Overhead Line Rating , 2006, 2006 International Conference on Probabilistic Methods Applied to Power Systems.

[18]  Andrea Michiorri,et al.  Forecasting real-time ratings for electricity distribution networks using weather forecast data , 2009 .

[19]  Sheng Gehao,et al.  Research for dynamic increasing transmission capacity , 2008, 2008 International Conference on Condition Monitoring and Diagnosis.

[20]  Nicolai Meinshausen,et al.  Quantile Regression Forests , 2006, J. Mach. Learn. Res..

[21]  Fulli Gianluca,et al.  Distributed Power Generation in Europe: Technical Issues for Further Integration , 2008 .

[22]  D. J. Morrow,et al.  Modelling and prediction techniques for dynamic overhead line rating , 2012, 2012 IEEE Power and Energy Society General Meeting.

[23]  P. McCullagh,et al.  Generalized Linear Models , 1984 .

[24]  J. Freidman,et al.  Multivariate adaptive regression splines , 1991 .

[25]  Lasantha Meegahapola,et al.  Comparative analysis of dynamic line rating models and feasibility to minimise energy losses in wind rich power networks , 2013 .

[26]  Richard J. Cook,et al.  Generalized Linear Model , 2014 .

[27]  David Morrow,et al.  Experimentally validated partial least squares model for dynamic line rating , 2014 .

[28]  Jeremy Colandairaj,et al.  Equipment and methodology for the planning and implementation of dynamic line ratings on overhead transmission circuits , 2010, 2010 Modern Electric Power Systems.

[29]  Jeremy Colandairaj,et al.  Application of Dynamic Line Rating to Defer Transmission Network Reinforcement due to Wind Generation , 2012 .

[30]  Jin-O Kim,et al.  Prediction of Dynamic Line Rating Based on Assessment Risk by Time Series Weather Model , 2006, 2006 International Conference on Probabilistic Methods Applied to Power Systems.

[31]  S. P. Basu,et al.  Design, installation, and field experience with an overhead transmission dynamic line rating system , 1996, Proceedings of 1996 Transmission and Distribution Conference and Exposition.