Artificial Intelligence-Aided Model Predictive Control for a Grid-Tied Wind-Hydrogen-Fuel Cell System

Integrating renewable energy into power grids is seen in increase in recent years since these energy sources are sustainable and clean. However, the integration brings about considerable technical challenges associated with fluctuations and uncertainties of the energy availability whilst maintaining the stability of smart grids. The prediction of renewable energy generation is key to achieve optimal power dispatch in renewable-intensive smart grids. However, uncertain interruption and prediction errors will make an optimal decision more challenging. Model predictive control (MPC) is an effective way to overcome the discrepancies between the prediction and the real-world system through a closed-loop correction over iteration process. This study develops an improved MPC scheme used with a hybrid energy storage system for optimal power dispatch in a smart grid. This hybrid renewable energy system consists of a wind farm, a hydrogen/oxygen storage system and several fuel cells (FCs). In this study, particle swarm optimization (PSO) with a back propagation (BP) artificial neural network is developed to predict the wind energy availability by using measured data. Then, a genetic algorithm (GA) is combined with a state space model (SSM) to achieve the MPC control. A dataset of 24-hour ahead predictive generation is calibrated from the measured data and is defined for optimal power flow between the grid, the wind farm and the storage subsystem so as to balance the supply and load. The optimization target is to achieve a minimal energy exchange between the power grid and the hybrid renewable energy storage system. Based on actual measured data, the test results have shown that the proposed methodology can maximize the local usage of wind power whilst minimizing the power exchange with the grid. An optimal power dispatch strategy is proved to be effective to meet the demand and efficiency with dynamic control of the FCs. The usage of the intermittent wind power is increased from 45% to 90% in the four test studies. Therefore, this work can minimize the impact of fluctuating renewable energy on the power grid and enhance uptakes of FC-based energy systems. This is particularly economic and relevant to the remote and under-developed regions where their power networks are weak and vulnerable.

[1]  Zhe Chen,et al.  Optimizing investments in coupled offshore wind -electrolytic hydrogen storage systems in Denmark , 2017 .

[2]  Hernán De Battista,et al.  Evaluation of hydrogen production capabilities of a grid-assisted wind-H2 system , 2011 .

[3]  Robert S. Balog,et al.  Model Predictive Control of PV Sources in a Smart DC Distribution System: Maximum Power Point Tracking and Droop Control , 2014, IEEE Transactions on Energy Conversion.

[4]  Hongwen Li,et al.  Speed Ripple Minimization of Permanent Magnet Synchronous Motor Based on Model Predictive and Iterative Learning Controls , 2019, IEEE Access.

[5]  Jing Zhang,et al.  An improved probabilistic load flow simulation method considering correlated stochastic variables , 2019 .

[6]  Farhad Aghili,et al.  Quadratically Constrained Quadratic-Programming Based Control of Legged Robots Subject to Nonlinear Friction Cone and Switching Constraints , 2017, IEEE/ASME Transactions on Mechatronics.

[7]  Chao Chen,et al.  Energy management of hybrid electric vehicles: A review of energy optimization of fuel cell hybrid power system based on genetic algorithm , 2020, Energy Conversion and Management.

[8]  Kok Kiong Tan,et al.  Development of a Genetic-Algorithm-Based Nonlinear Model Predictive Control Scheme on Velocity and Steering of Autonomous Vehicles , 2016, IEEE Transactions on Industrial Electronics.

[9]  S. Kahla,et al.  Fuzzy-PSO controller design for maximum power point tracking in photovoltaic system , 2017 .

[10]  M. M. Ardehali,et al.  Optimization of autonomous combined heat and power system including PVT, WT, storages, and electric heat utilizing novel evolutionary particle swarm optimization algorithm , 2018 .

[11]  Yun Deng,et al.  Prediction model of PSO-BP neural network on coliform amount in special food , 2019, Saudi journal of biological sciences.

[12]  Yixuan Zhang,et al.  Comparison of BP, PSO-BP and statistical models for predicting daily global solar radiation in arid Northwest China , 2019, Comput. Electron. Agric..

[13]  Guillaume Sandou,et al.  LabVIEW Perturbed Particle Swarm Optimization Based Approach for Model Predictive Control Tuning , 2016 .

[14]  P. Enevoldsen,et al.  The past, present and potential of hydrogen as a multifunctional storage application for wind power , 2019, Renewable and Sustainable Energy Reviews.

[15]  Hoay Beng Gooi,et al.  A Hybrid Firefly-Swarm Optimized Fractional Order Interval Type-2 Fuzzy PID-PSS for Transient Stability Improvement , 2019, IEEE Transactions on Industry Applications.

[16]  Moulay Rachid Douiri.  Particle swarm optimized neuro-fuzzy system for photovoltaic power forecasting model , 2019, Solar Energy.

[17]  N. Aziz,et al.  MIMO Neural Wiener Based Model Predictive Control (NWMPC) For MTBE Reactive Distillation Using Simulated Annealing-Particle Swarm optimization (SA-PSO) , 2015 .

[18]  Feng Cao,et al.  Investigations on optimal discharge pressure in CO2 heat pumps using the GMDH and PSO-BP type neural network—Part A: Theoretical modeling , 2019, International Journal of Refrigeration.

[19]  Jacek Kluska,et al.  PID-Like Adaptive Fuzzy Controller Design Based on Absolute Stability Criterion , 2020, IEEE Transactions on Fuzzy Systems.

[20]  Subhashish Bhattacharya,et al.  Rule-Based Control of Battery Energy Storage for Dispatching Intermittent Renewable Sources , 2010, IEEE Transactions on Sustainable Energy.

[21]  Su Whan Sung,et al.  Dynamic Behavior of Linear Processes , 2009 .

[22]  Ming-Tzu Ho,et al.  Robust Second-Order Controller Synthesis for Model Matching of Interval Plants and Its Application to Servo Motor Control , 2012, IEEE Transactions on Control Systems Technology.

[23]  M. A. Abido,et al.  A novel multi-objective hybrid particle swarm and salp optimization algorithm for technical-economical-environmental operation in power systems , 2020 .

[24]  Ronald G. Harley,et al.  Model Predictive and Genetic Algorithm-Based Optimization of Residential Temperature Control in the Presence of Time-Varying Electricity Prices , 2011, IEEE Transactions on Industry Applications.

[25]  Lei Chen,et al.  Equivalence of Three Quadratic Approximation Methods of Stability Boundaries of Nonlinear Dynamic Systems , 2010, IEEE Transactions on Automatic Control.

[26]  Xu Dan,et al.  Robust model predictive control for greenhouse temperature based on particle swarm optimization , 2018, Information Processing in Agriculture.

[27]  Mahmoud F. Elmorshedy,et al.  Residential Community Load Management Based on Optimal Design of Standalone HRES With Model Predictive Control , 2020, IEEE Access.

[28]  Hongwen He,et al.  Rule-based plug-in hybrid school bus energy management control strategy simulation , 2015, 2015 10th Asian Control Conference (ASCC).

[29]  Fan Zhang,et al.  GPU-based model predictive control for continuous casting spray cooling control system using particle swarm optimization , 2019, Control Engineering Practice.

[30]  Saeid Nahavandi,et al.  Multiobjective and Interactive Genetic Algorithms for Weight Tuning of a Model Predictive Control-Based Motion Cueing Algorithm , 2019, IEEE Transactions on Cybernetics.

[31]  Lei Guo,et al.  PID controller design for output PDFs of stochastic systems using linear matrix inequalities , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[32]  Nadeem Javaid,et al.  Towards Efficient Energy Management of Smart Buildings Exploiting Heuristic Optimization with Real Time and Critical Peak Pricing Schemes , 2017 .

[33]  Bangyin Liu,et al.  Online 24-h solar power forecasting based on weather type classification using artificial neural network , 2011 .

[34]  Benjamin K. Sovacool,et al.  Integrating power systems for remote island energy supply: Lessons from Mykines, Faroe Islands , 2016 .

[35]  L. Hontoria,et al.  Estimation of the energy of a PV generator using artificial neural network , 2009 .

[36]  Eamon McKeogh,et al.  The role of hydrogen in high wind energy penetration electricity systems: The Irish case , 2004 .

[37]  Jinghan Cui,et al.  Deep-Neural-Network-Based Economic Model Predictive Control for Ultrasupercritical Power Plant , 2020, IEEE Transactions on Industrial Informatics.

[38]  Romeo Ortega,et al.  Energy Shaping of Mechanical Systems via PID Control and Extension to Constant Speed Tracking , 2016, IEEE Transactions on Automatic Control.

[39]  Numan Sabit Cetin,et al.  Artificial neural networks for controlling wind–PV power systems: A review , 2014 .

[40]  Bo Liu,et al.  Economic study of a large-scale renewable hydrogen application utilizing surplus renewable energy and natural gas pipeline transportation in China , 2020 .

[41]  Amin Masoumi,et al.  Application of neural network and weighted improved PSO for uncertainty modeling and optimal allocating of renewable energies along with battery energy storage , 2020, Appl. Soft Comput..

[42]  Jianbin Qiu,et al.  A Combined Adaptive Neural Network and Nonlinear Model Predictive Control for Multirate Networked Industrial Process Control , 2016, IEEE Transactions on Neural Networks and Learning Systems.