Dr. Conor Lynch

Research Fellow & Group Lead

Dr Conor Lynch is a Research Fellow & Group Lead at the Nimbus research centre with interests including system modelling, machine learning, data analytics and Artificial Intelligence (AI) to optimally integrate and allocate renewable energy resources. He completed two level 8 honorary Bachelor of Engineering degrees in Structural Engineering and Sustainable Energy Technology at the Munster Technological University (formerly Cork Institute of Technology) in 2006 and 2011

In 2013, Conor was awarded the Irish Research Council for Science Engineering and Technology (IRCSET) Enterprise Partnership PhD Scholarship. Partnering with United Technologies Research Centre (UTRC), he concluded his PhD degree in model predictive control, focusing on Kalman Filtering optimisation techniques to optimally schedule the renewable energy contribution within a micro-grid in the Process, Energy and Transportation Department at Munster Technological University in 2016. During his PhD, he completed a term with the Applied Control Technology Consortium (ACTC) under the guidance of Prof Mike Grimble through the University of Strathclyde, Glasgow, Scotland. In that time, he studied System Modelling, Identi­fication and Parameter Estimation Methods for the Predictive Control for Linear and Nonlinear Systems.

In 2017, he was awarded the Bridge Network Technology Transfer Consortium Invention of the Year award for Engineering, ICT and Physical Sciences for his work on the Nimbus Energy Optimisation System (EOS) project. He now leads the AI, Machine Learning and Data Analytics team within Nimbus with expertise in the aforementioned applied to forecasting, predictive maintenance, anomaly detection, sentiment analysis, natural language processing (NLP), pattern recognition and data classi­fication. Additionally, he is a task participant of the International Energy Agency (IEA) Technology Collaboration Programme (TCP) for Task 36 – Forecasting for Wind Energy.

His research interests include: Optimisation, Micro-Grids, System Modelling, Machine Learning, Data Analytics and Artificial Intelligence for Forecasting and Predictive Control for the integration and allocation of renewable energy resources

E. Asghar, M. Hill, C. Lynch, “A Regularization-Based Long Short-Term Memory Architecture Design for Solar Irradiance Prediction”, 2nd International Conference on Electrical, Computer and Energy Technologies (ICECET), 20-22 July 2022, Prague, Czech Republic
 

R. Bain, C. Lynch, D. McDonnell, K. Witheephanich, “An XGBoost approach for industrial component degradation classification”, 2022, 33rd Irish Signals & Systems Conference (ISSC), Cork, Ireland, 9-10 June

C. O’Leary, C. Lynch, “An Evaluation of Machine Learning Approaches for Milk Volume Prediction in Ireland”, 2022, 33rd Irish Signals & Systems Conference (ISSC), Cork, Ireland, 9-10 June

Lynch C., O’Leary C., Sundareshan PGK., Akin Y., “Experimental Analysis of GBM to Expand the Time Horizon of Irish Electricity Price Forecasts”, Energies, 2021; 14(22):7587. https://doi.org/10.3390/en14227587
 
C. O’Leary, C. Lynch, R. Bain, G. Smith, D. Grimes, “A Comparison of Deep Learning vs Traditional Machine Learning for Electricity Price Forecasting”, ICICT 2021, 4th International Conference on Information and Computer Technologies, Kahului, Maui Island, Hawaii, United States, 11-14 March 2021. DOI: 10.1109/ICICT52872.2021.00009 – Awarded Best Conference Presentation Certificate
 

C. Lynch, C. O’Leary, G. Smith, R. Bain, J. Kehoe, A. Vakaloudis, R. Linger, “A review of open-source machine learning algorithms for Twitter text sentiment analysis and image classification”, WCCI 2020, IEEE World Conference on Computational Intelligence, Glasgow, Scotland, 19-24 July 2020. DOI: 10.1109/IJCNN48605.2020.9207544

C. Lynch, M. J. O’Mahony and R. A. Guinee, “Novel Kalman Filter Bank Methodology for Time-Series Prediction in Forecasting Applications” Proc. 2nd International Conference on Data-Driven Plasma Science (ICDDPS),  13 – 17 May 2019, Marseille, France.

C. Lynch, J. Kehoe, R. Bain, F. Zhang, J. Flynn, C. O’Leary, G. Smith, R. Linger, K. Fitzgibbon and F. Feijoo, “SVM-Based Day-Ahead Electricity Price Prediction Model for the Single Electricity Market in Ireland”, ISF 2019, 39th International Symposium on Forecasting, Thessaloniki, Greece, 16 -19 June 2019.

A. Baró Pérez, C. Lynch, A. L. Ferrer Hernández, I. B. Montejo and A.R. Rodríguez, 2018. “Kalman Filter bank post-processor methodology for the Weather Research and Forecasting Model wind speed grid model output correction”, International Journal of Sustainable Energy, vol. 38, issue 6, pp. 511–525.

C. Lynch, M. J. O’Mahony and R. A. Guinee. “Electrical Load Forecasting Using an Expanded Kalman Filter Bank Methodology.” 4th International Federation of Automatic Control (IFAC) Conference on Programmable Devices and Embedded Systems (PDES) 2016: Brno, Czech Republic, 5-7 October 2016. IFAC-Papers Online, vol. 49, no. 25, pp. 358–365, 2016.

C. Lynch, M. J. O’Mahony and R. A. Guinee, “24 Hour Step Ahead Wind Speed / Wind Power Prediction Using A Novel Kalman Filter Bank Prediction Estimator”, Proc. ASME 2015 Power Energy Conversion Conference. PowerEnergy2015,  28 June – 2 July 2015, San Diego, CA, 2015.

C. Lynch, M. J. O’Mahony, and R. A. Guinee, “A Novel 24 Kalman Filter Bank Estimator for Solar Irradiance Prediction for PV Power Generation”, Proc. 42nd IEEE Photovoltaic Specialists Conference (PVSC), 14 – 19 June, New Orleans, LA, 2015.

C. Lynch, M. J. O’Mahony, and R. A. Guinee, “Accurate Day Ahead Temperature Prediction Using A 24 Kalman Filter Estimator”, Proc. IEEE 2015 PRIME Conference. 29 June – 2 July, Glasgow, UK, 2015.

C. Lynch, M. J. O’Mahony and T. Scully, 2014. “Simplified Method to Derive the Kalman Filter Covariance Matrices to Predict Wind Speeds from a NWP Model”, Energy Procedia, 62, pp. 676–685

Analog Devices International – AI solution to detect and segment wafer map anomalies
 
PlayerStat Data – Object detection and recognition for soccer analysis
 
O-PENS – Optimise Predict Energy System – microgrid optimisation project
 
 

STEP4 – Short Term Electricity Price Forecaster

Clarke Analytics – AI Trustworthiness 

Predictive Control Systems (PCS) – Energy system modelling and optimisation

 

SteriTrack – Development of a direct part marking (DPM) scanner for the healthcare sector