Data-Driven Based Method for Power System Time-Varying Composite Load Modeling

Fast and accurate load parameters identification has great impact on the power systems operation and stability analysis. This paper proposes a novel transfer reinforcement learning based method to identify composite ZIP and induction motor (IM) load models. An imitation learning process is firstly introduced to improve the exploitation and exploration process. The transfer learning process is then employed to overcome the challenge of time consuming optimization when dealing with new tasks. An Associative memory is designed to realize demension reduction and knowledge learning and transfer between different optimization tasks. Agents can exploit the optimal knowledge from source tasks to accelerate search rate and improve solution accuracy. The greedy rule is adopted to balance global search and local search. Convergency analysis shows that the proposed method can converge to the global optimal solution with probability 1. The performance of the proposed ITQ appraoch have been validated on 68-bus system. Simulation results in multi-test cases verify that the proposed method has superior convergence rate and stability.

[1]  Roland P. Malhamé,et al.  Convergence characteristics of a maximum likelihood load model identification scheme , 1992, Autom..

[2]  Ying Zhang,et al.  Deep Learning-Based Time-Varying Parameter Identification for System-Wide Load Modeling , 2019, IEEE Transactions on Smart Grid.

[3]  Dongbo Zhao,et al.  Load Modeling—A Review , 2018, IEEE Transactions on Smart Grid.

[4]  Tao Yu,et al.  Lifelong Learning for Complementary Generation Control of Interconnected Power Grids With High-Penetration Renewables and EVs , 2018, IEEE Transactions on Power Systems.

[5]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[6]  V. Ajjarapu,et al.  A Novel Parameter Identification Approach via Hybrid Learning for Aggregate Load Modeling , 2009, IEEE Transactions on Power Systems.

[7]  Jin Ma,et al.  A Real Application of Measurement-Based Load Modeling in Large-Scale Power Grids and its Validation , 2009, IEEE Transactions on Power Systems.

[8]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[9]  Yunping Chen,et al.  The load modeling and parameters identification for voltage stability analysis , 2002, Proceedings. International Conference on Power System Technology.

[10]  Kumars Rouzbehi,et al.  Nonlinear Power System Load Identification Using Local Model Networks , 2013, IEEE Transactions on Power Systems.

[11]  Jinyu Wen,et al.  Power system load modeling by learning based on system measurements , 2003 .

[12]  Bo Yang,et al.  Accelerating bio-inspired optimizer with transfer reinforcement learning for reactive power optimization , 2017, Knowl. Based Syst..

[13]  Jeonghoon Shin,et al.  Fast and reliable estimation of composite load model parameters using analytical similarity of parameter sensitivity , 2016 .

[14]  Andrew Lewis,et al.  Grey Wolf Optimizer , 2014, Adv. Eng. Softw..

[15]  David J. Hill,et al.  Nonlinear dynamic load models with recovery for voltage stability studies , 1993 .

[16]  H. Mannila,et al.  Computing Discrete Fréchet Distance ∗ , 1994 .

[17]  K. H. Tseng,et al.  Load Model Effects on Distance Relay Settings , 2002, IEEE Power Engineering Review.

[18]  C.A. Canizares,et al.  On the parameter estimation and modeling of aggregate power system loads , 2004, IEEE Transactions on Power Systems.

[19]  Andrew Lewis,et al.  The Whale Optimization Algorithm , 2016, Adv. Eng. Softw..

[20]  Chong Wang,et al.  Robust Time-Varying Parameter Identification for Composite Load Modeling , 2019, IEEE Transactions on Smart Grid.

[21]  F. S. van der Merwe,et al.  Induction motor parameter estimation through an output error technique , 1994 .

[22]  I. Hiskens Nonlinear dynamic model evaluation from disturbance measurements , 2002, 2002 IEEE Power Engineering Society Winter Meeting. Conference Proceedings (Cat. No.02CH37309).

[23]  C. W. Taylor,et al.  Standard load models for power flow and dynamic performance simulation , 1995 .

[24]  P. Regulski,et al.  Estimation of Composite Load Model Parameters Using an Improved Particle Swarm Optimization Method , 2015, IEEE Transactions on Power Delivery.