Real-Time Identification of Power Fluctuations Based on LSTM Recurrent Neural Network: A Case Study on Singapore Power System

Fast and stochastic power fluctuations caused by renewable energy sources and flexible loads have significantly deteriorated the frequency performance of modern power systems. Power system frequency control aims to achieve real-time power balance between generations and loads. In practice, it is much more difficult to exactly acquire the values of unbalance power in both transmission and distribution systems, especially when there is a high penetration level of renewable energies. This paper explores a deep learning approach to identify active power fluctuations in real-time, which is based on a long short-term memory recurrent neural network. The developed method provides a more accurate and faster estimation of the value of power fluctuations from the real-time measured frequency signal. The identified power fluctuations can serve as control reference so that the system frequency can be better maintained by automatic generation control, as well as emerging frequency control elements, such as energy storage system. A detailed model of Singapore power system integrated with distributed energy storage systems is used to verify the proposed method and to compare with various classical methods. The simulation results clearly demonstrate the necessity for power fluctuation identification, and the advantages of the proposed method.

[1]  Yang Mi,et al.  Frequency Control of an Isolated Micro-Grid Using Double Sliding Mode Controllers and Disturbance Observer , 2018, IEEE Transactions on Smart Grid.

[2]  Martin Wattenberg,et al.  Visualizing Dataflow Graphs of Deep Learning Models in TensorFlow , 2018, IEEE Transactions on Visualization and Computer Graphics.

[3]  Zhou Quan,et al.  RBF Neural Network and ANFIS-Based Short-Term Load Forecasting Approach in Real-Time Price Environment , 2008, IEEE Transactions on Power Systems.

[4]  Zhiqiang Ge,et al.  Deep Learning of Semisupervised Process Data With Hierarchical Extreme Learning Machine and Soft Sensor Application , 2018, IEEE Transactions on Industrial Electronics.

[5]  Hieu Minh Trinh,et al.  Load Frequency Control of Power Systems With Electric Vehicles and Diverse Transmission Links Using Distributed Functional Observers , 2016, IEEE Transactions on Smart Grid.

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

[7]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[8]  Yuan Zhang,et al.  Short-Term Residential Load Forecasting Based on LSTM Recurrent Neural Network , 2019, IEEE Transactions on Smart Grid.

[9]  Wen Tan,et al.  Unified Tuning of PID Load Frequency Controller for Power Systems via IMC , 2010, IEEE Transactions on Power Systems.

[10]  Yu Wang,et al.  System frequency regulation in Singapore using distributed energy storage systems , 2017, 2017 Asian Conference on Energy, Power and Transportation Electrification (ACEPT).

[11]  Mohamed Menaa,et al.  LFC enhancement concerning large wind power integration using new optimised PID controller and RFBs , 2016 .

[12]  Fei Shen,et al.  Machine Health Monitoring Using Local Feature-Based Gated Recurrent Unit Networks , 2018, IEEE Transactions on Industrial Electronics.

[13]  Jianhui Wang,et al.  A Unified Control Scheme Based on a Disturbance Observer for Seamless Transition Operation of Inverter-Interfaced Distributed Generation , 2018, IEEE Transactions on Smart Grid.

[14]  Yu Kurita,et al.  Control of storage batteries using a disturbance observer in load frequency control for large wind power penetration , 2015, 2015 IEEE Power & Energy Society General Meeting.

[15]  Yuanli Cai,et al.  A Fuzzy Model Predictive Control Based Upon Adaptive Neural Network Disturbance Observer for a Constrained Hypersonic Vehicle , 2018, IEEE Access.

[16]  Yan Xu,et al.  A Robust Load Frequency Control Scheme for Power Systems Based on Second-Order Sliding Mode and Extended Disturbance Observer , 2018, IEEE Transactions on Industrial Informatics.

[17]  Jürgen Schmidhuber,et al.  Learning to forget: continual prediction with LSTM , 1999 .

[18]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[19]  Alberto Bemporad,et al.  Combined Design of Disturbance Model and Observer for Offset-Free Model Predictive Control , 2007, IEEE Transactions on Automatic Control.

[20]  Jie Liu,et al.  Robust Deadbeat Predictive Power Control With a Discrete-Time Disturbance Observer for PWM Rectifiers Under Unbalanced Grid Conditions , 2019, IEEE Transactions on Power Electronics.

[21]  H. B. Gooi,et al.  Strait Ahead: Toward a Sustainable, Economic, and Secure Electricity Supply in Singapore , 2012, IEEE Power and Energy Magazine.

[22]  Changyin Sun,et al.  An Event-Triggered Approach for Load Frequency Control With Supplementary ADP , 2017, IEEE Transactions on Power Systems.

[23]  David J. Hill,et al.  Intelligent Time-Adaptive Transient Stability Assessment System , 2016, IEEE Transactions on Power Systems.

[24]  D. K. Sambariya,et al.  A robust PID controller for load frequency control of single area re-heat thermal power plant using elephant herding optimization techniques , 2017, 2017 International Conference on Information, Communication, Instrumentation and Control (ICICIC).

[25]  Yi Zhang,et al.  Coordinated Distributed MPC for Load Frequency Control of Power System With Wind Farms , 2017, IEEE Transactions on Industrial Electronics.

[26]  Hao Yu,et al.  Advantages of Radial Basis Function Networks for Dynamic System Design , 2011, IEEE Transactions on Industrial Electronics.