Data-Driven Trajectory Prediction of Grid Power Frequency Based on Neural Models

Frequency in power systems is a real-time information that shows the balance between generation and demand. Good system frequency observation is vital for system security and protection. This paper analyses the system frequency response following disturbances and proposes a data-driven approach for predicting it by using machine learning techniques like Nonlinear Auto-regressive (NAR) Neural Networks (NN) and Long Short Term Memory (LSTM) networks from simulated and measured Phasor Measurement Unit (PMU) data. The proposed method uses a horizon-window that reconstructs the frequency input time-series data in order to predict the frequency features such as Nadir. Simulated scenarios are based on the gradual inertia reduction by including non-synchronous generation into the Nordic 32 test system, whereas the PMU collected data is taken from different locations in the Nordic Power System (NPS). Several horizon-windows are experimented in order to observe an adequate margin of prediction. Scenarios considering noisy signals are also evaluated in order to provide a robustness index of predictability. Results show the proper performance of the method and the adequate level of prediction based on the Root Mean Squared Error (RMSE) index.

[1]  Dirk Witthaut,et al.  Non-Gaussian power grid frequency fluctuations characterized by Lévy-stable laws and superstatistics , 2018, Nature Energy.

[2]  Liu Liu,et al.  An Analytical Model for Frequency Nadir Prediction Following a Major Disturbance , 2020, IEEE Transactions on Power Systems.

[3]  Ram Rajagopal,et al.  AR-Net: A simple Auto-Regressive Neural Network for time-series , 2019, ArXiv.

[4]  C. Bergmeir,et al.  Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directions , 2019, International Journal of Forecasting.

[5]  Mehrdad Ghandhari,et al.  Non-synchronous generation impact on power systems coherency , 2016 .

[6]  Jianfeng Yan,et al.  Digital twin and its application to power grid online analysis , 2019, CSEE Journal of Power and Energy Systems.

[7]  Radu-Emil Precup,et al.  Hybrid data-driven fuzzy active disturbance rejection control for tower crane systems , 2020, Eur. J. Control.

[8]  Yoh-Han Pao,et al.  Prediction of power system frequency response after generator outages using neural nets , 1993 .

[9]  Rob J. Hyndman,et al.  A note on the validity of cross-validation for evaluating autoregressive time series prediction , 2018, Comput. Stat. Data Anal..

[10]  Federico Delfino,et al.  Data-Driven Photovoltaic Power Production Nowcasting and Forecasting for Polygeneration Microgrids , 2018, IEEE Systems Journal.

[11]  Jie Tian,et al.  Synchronised ambient data-driven electromechanical oscillation modes extraction for interconnected power systems using the output-only observer/Kalman filter identification method , 2020 .

[12]  Chaker El Amrani,et al.  Sequence to Sequence Weather Forecasting with Long Short-Term Memory Recurrent Neural Networks , 2016 .

[13]  F. Gonzalez-Longatt,et al.  Short-term Kinetic Energy Forecast using a Structural Time Series Model: Study Case of Nordic Power System , 2020, 2020 International Conference on Smart Systems and Technologies (SST).

[14]  Yan Xu,et al.  Data-Driven Load Frequency Control for Stochastic Power Systems: A Deep Reinforcement Learning Method With Continuous Action Search , 2019, IEEE Transactions on Power Systems.

[15]  Yingnan Pan,et al.  Event-Triggered Adaptive Fuzzy Control for Stochastic Nonlinear Systems With Unmeasured States and Unknown Backlash-Like Hysteresis , 2021, IEEE transactions on fuzzy systems.

[16]  Federico Milano,et al.  Robust Frequency Divider for Power System Online Monitoring and Control , 2018, IEEE Transactions on Power Systems.

[17]  Kwang Y. Lee,et al.  An Ensemble Framework for Day-Ahead Forecast of PV Output Power in Smart Grids , 2018, IEEE Transactions on Industrial Informatics.

[18]  Peng Lu,et al.  Correlation-Constrained and Sparsity-Controlled Vector Autoregressive Model for Spatio-Temporal Wind Power Forecasting , 2018, IEEE Transactions on Power Systems.

[19]  D. Dolinar,et al.  Correlation-based estimation of area's frequency response characteristic during large disturbances , 2016, 2016 IEEE International Energy Conference (ENERGYCON).

[20]  Chongqing Kang,et al.  Impact of High Renewable Penetration on the Power System Operation Mode: A Data-Driven Approach , 2020, IEEE Transactions on Power Systems.

[21]  Xianfu Chen,et al.  Deep Learning with Long Short-Term Memory for Time Series Prediction , 2018, IEEE Communications Magazine.

[22]  Guoqiang Peter Zhang,et al.  Trend Time–Series Modeling and Forecasting With Neural Networks , 2008, IEEE Transactions on Neural Networks.

[23]  Steven Porretta,et al.  Calculation of power systems inertia and frequency response , 2018, 2018 IEEE Texas Power and Energy Conference (TPEC).

[24]  Ting Zhou,et al.  Tailings Pond Risk Prediction Using Long Short-Term Memory Networks , 2019, IEEE Access.

[25]  Tao Yu,et al.  A new generation of AI: A review and perspective on machine learning technologies applied to smart energy and electric power systems , 2019, International Journal of Energy Research.

[26]  Swades De,et al.  Dynamic Prediction of Powerline Frequency for Wide Area Monitoring and Control , 2018, IEEE Transactions on Industrial Informatics.

[27]  Vijay Vittal,et al.  Forecast-Based Anticipatory Frequency Control in Power Systems , 2018, IEEE Transactions on Power Systems.

[28]  Jürgen Schmidhuber,et al.  LSTM: A Search Space Odyssey , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[29]  Ayşe Soy Temür,et al.  PREDICTING HOUSING SALES IN TURKEY USING ARIMA, LSTM AND HYBRID MODELS , 2019, Journal of Business Economics and Management.

[30]  Qi Wang,et al.  Integrating Model-Driven and Data-Driven Methods for Power System Frequency Stability Assessment and Control , 2019, IEEE Transactions on Power Systems.

[31]  Jun Yi,et al.  An Integrated Model-Driven and Data-Driven Method for On-Line Prediction of Transient Stability of Power System With Wind Power Generation , 2020, IEEE Access.

[32]  Zijun Zhang,et al.  Short-Horizon Prediction of Wind Power: A Data-Driven Approach , 2010, IEEE Transactions on Energy Conversion.

[33]  Wenhu Tang,et al.  Deep Learning for Daily Peak Load Forecasting–A Novel Gated Recurrent Neural Network Combining Dynamic Time Warping , 2019, IEEE Access.

[34]  Peiyuan Chen,et al.  Frequency evaluation of the Nordic power system using PMU measurements , 2017 .

[35]  Rafael Mihalic,et al.  A novel approach to underfrequency load shedding , 2011 .

[36]  Yilu Liu,et al.  Fast and Accurate Frequency Response Estimation for Large Power System Disturbances Using Second Derivative of Frequency Data , 2020, IEEE Transactions on Power Systems.

[37]  A. Mellit,et al.  Day-Ahead Photovoltaic Forecasting: A Comparison of the Most Effective Techniques , 2019, Energies.

[38]  Gang Wang,et al.  Real-Time Power System State Estimation and Forecasting via Deep Unrolled Neural Networks , 2018, IEEE Transactions on Signal Processing.

[39]  Vijay K. Sood,et al.  Impact of non-synchronous generation on transmission oscillations paths , 2018, 2018 IEEE Texas Power and Energy Conference (TPEC).

[40]  D.P. Chassin,et al.  Estimation of WECC system inertia using observed frequency transients , 2004, IEEE Transactions on Power Systems.

[41]  Mao Yang,et al.  Research on Ultra-Short-Term Wind Power Prediction Considering Source Relevance , 2020, IEEE Access.

[42]  Yang Zhang,et al.  Dynamic Optimization Long Short-Term Memory Model Based on Data Preprocessing for Short-Term Traffic Flow Prediction , 2020, IEEE Access.

[43]  Yier Jin,et al.  A Survey of Machine Learning Methods for Detecting False Data Injection Attacks in Power Systems , 2020, IET Smart Grid.

[44]  Thyago P. Carvalho,et al.  A systematic literature review of machine learning methods applied to predictive maintenance , 2019, Comput. Ind. Eng..

[45]  Paolo Frankl,et al.  Energy System Debate: What Lies Ahead for the Future [In My View] , 2019, IEEE Power and Energy Magazine.

[46]  Raj Aggarwal,et al.  Artificial neural networks in power systems. III. Examples of applications in power systems , 1998 .