Guest Editorial: Knowledge-Based Control and Optimization for Smart Energy Systems

Abstract

Stronger policies and raised climate goals leading into COP27 are driving the development of renewable energy to new records. Based on the analysis and forecasts of International Energy Agency, renewables are set to account for almost 95% of the increase in global power capacity through 2026. The rapid growth of renewables brings a lot of new challenges to the energy systems. Smart energy systems have been developed to meet the requirements of high-level penetration of renewable energy, distributed energy resources, multi-energy integration etc. In smart energy systems, the power generation process faces more internal and external uncertainties, the operating conditions are more complex, the requirements for reliability and flexibility are higher, and the characteristics of network collaboration are more significant. Therefore, knowledge-based control theories, control technologies and optimization methods are inspiring and promising to enhance the performance of smart energy systems.

In this perspective, the goal of this special issue is to provide a forum to exhibit recent developments in knowledge-based control and optimization theories, methodologies, techniques, and their applications to smart energy systems. There are in total thirteen papers accepted for publication in this Special Issue through careful peer reviews and revisions. Under the overarching theme of data-driven applications in power systems, the selected papers are broadly categorised into five topics. The summary of every topic is given as follows.

Monirul et al., in their paper “Adaptive state of charge estimation for lithium-ion batteries using feedback-based extended Kalman filter,” consider high-order equivalent circuit model (ECM) to capture the dynamic characteristics of lithium-ion batteries. The feedback-based extended Kalman filtering (FEKF) algorithm is established. The optimal simulation knowledge is adopted to improve the SOC estimation approach remarkably and provide a reference value. The nonlinear predicting and corrective techniques are applied to the experiment in the extended calculation process. The established high-order ECM utilizing the FEKF algorithm achieves superb performance from the lithium-ion battery pack.

Yang et al., in their paper “Self-paced learning LSTM based on intelligent optimization for robust wind power prediction,” propose a wind power prediction method that leverages an enhanced multi-objective sand cat swarm algorithm (MO-SCSO) and a self-paced long short-term memory network (spLSTM). The progressive advantage of selfpaced learning (SPL) is used to effectively solve the instability caused by noisy data during long short-term memory network (LSTM) training. The improved MO-SCSO is employed to iteratively optimize the hyperparameters of spLSTM. A combined MOSCSO-spLSTM model is constructed for wind power prediction, which is validated with the data of onshore wind farms in Austria and offshore wind farms in Denmark.

Fu et al., in their paper “Wind turbine load optimization control and verification based on wind speed estimator with time series broad learning system method,” design a wind turbine mechanical load optimization control strategy based on an accurate wind speed estimator with time series broad learning system method (BLSM). The OPEN-FAST is used to conduct a simulation comparison study on mechanical load characteristics of wind turbine before and after the implementation of the optimization control strategy. Field empirical mechanical load tests are performed on the wind turbine, which is configured with BLSM load optimization control technology. The findings indicate that the implementation of this control strategy can significantly mitigate the ultimate and fatigue loads of wind turbines.

Zhu et al., in their paper “Modeling and regulation of steam temperatures of a 1000 MW double-reheat boiler with long short-term memory,” to inhibit the steam temperature fluctuations, introduce the long short-term memory (LSTM) to model the dynamics of the steam temperatures of a 1000 MW double-reheat coal-fired boiler. An advanced controller is proposed by combining the LSTM-based dynamic model and the model predictive control architecture. The results demonstrate that the LSTM model can be used to capture the time delay, multivariable coupling and nonlinear dynamics of the steam temperatures on the studied double-reheat coal-fired boiler. The proposed controller also exhibits excellent performance in steam temperature regulation. The proposed method has good potential to stabilize steam temperatures during transient processes of wide-range load cycling, and finally improves the flexibility of the double-reheat ultra-supercritical unit.

Sun et al., in their paper “Research on partition control of direct air-cooling condenser based on multivariable Hammerstein CARMA model predictive control,” establish the relationship between mass flow rate and fan array speed under windy conditions. The model is grounded in multivariable Hammerstein controlled autoregressive moving average (H-CARMA) systems. An innovative extended stochastic gradient algorithm is introduced to estimate the model's unknown parameters. The recursive least square (RLS) is employed as a benchmark to verify the accuracy and efficiency of the approach. The model predictive controller (MPC) based on the differential evolution method (DE) is designed to derive the optimal control law. The experiment result shows that the dynamic characteristics of the system have been significantly improved and the fan power consumption is reduced.

Li et al., in their paper “Optimal classification tree for frequency security assessment of power systems with inverter-based resources reinforcement,” investigate the quantification problem of the frequency security levels of transmission systems under different inverter-based resources (IBRs) and their control parameter combinations. A novel system frequency dynamic model is proposed as a parametric optimization method, where the saturation of generators, energy storage systems, and renewable energy sources is incorporated as differential algebra equations (DAEs). This problem is further reformulated as a mixed-integer linear programming problem to generate a sufficient amount of data under different IBR integration and control parameters. The frequency security assessment problem is formulated as a data-driven multivariate classification problem, which is solved by the optimal classification tree (OCT) algorithm with better interptretionability. Numerical results indicate that the proposed system frequency dynamic model can capture the frequency dynamic under different IBR reinforcement plans and the OCT can realize accurate classification of the synthetic data regarding frequency security.

Qi et al., in their paper “Adaptive distributed MPC based load frequency control with dynamic virtual inertia of offshore wind farms,” employ the dynamic virtual inertia control (VIC) method to enhance frequency stability within the permitted operating states of OWFs. An adaptive distributed model predictive control (DMPC) method is proposed and applied to an interconnected power system. The dynamic VIC-based LFC model is derived and used to construct the predictive model of DMPC. To expand the adaptation of the analytical linearized model of OWFs in different operating points, the adaptive law is further designed to dynamically adjust the parameters of DMPC. The simulation results demonstrate the effectiveness of the proposed control method.

Tong et al., in their paper “A hybrid energy storage arrays group control strategy for wind power smoothing,” propose a coordinated control strategy through group consensus algorithm based on model predictive control (MPC) for hybrid energy storage array (HESA) to smooth wind power fluctuations. To allocate power commands to the FESS and BESS, the fluctuation of wind power output is extracted with different frequency domain characteristics as instructions by empirical mode decomposition (EMD) technology. A group consensus algorithm based on MPC is proposed to complete the adaptive power allocation of energy storage units. The actual wind farm data is used for the simulation to verify the effect of control strategy proposed in this paper.

Cai et al., in their paper “Anti-tropical cyclone yaw control of wind turbines based on knowledge learning and expert system,” analyse the characteristics of the wind field based on historical actual TC data and constructs a pseudo-Monte Carlo experiment. The experimental results are used to construct a knowledge base and an inference engine, and forms an expert system to guide the yaw control of wind turbines in nEWSP-TC. The simulation results show that the yaw error has different effects on the fatigue load of the wind turbine under different working conditions of nEWSP-TC, and the proposed improved yaw strategy can reduce the fatigue load of the wind turbine under the premise of limited power loss and improve safe operation capability of wind turbines under nEWSP-TC conditions.

Shi et al., in their paper “A high robust control scheme of grid-side converter for DFIG system,” propose a high robust control – second-order sliding-mode control (SOSMC) scheme to improve the DC-link voltage dynamic performance of the grid-side converter (GSC) for the doubly-fed induction generator (DFIG) system under the variable wind power generation and DC-link capacitance parameter disturbance. By using the nonlinear SOSMC controller, the DFIG system is robust to the disturbance of the wind speed and the parameter of DC-link capacitance. Compared with the conventional PI control scheme, the DFIG system with the proposed SOSMC scheme is much more robust, which has been verified in the MATLAB/Simulink platform.

Yu and Liu, in their paper “Flexible operation of a CHP-VPP considering the coordination of supply and demand based on a strengthened distributionally robust optimization,” propose for the nearly-zero carbon self-scheduling of a combined heat and power virtual power plant (CHP-VPP) over a coupled electric power network (EPN) and district heating network (DHN). A strengthened ambiguity sets based on moment information and Wasserstein metric is built to provide more accurate characterizations of the true probability distribution of uncertainties. In addition, a HOMIE model considering indoor activities and outside temperatures of each building is built to satisfy the comfortable indoor temperature. Linearization and duality theory are adopted and then a tailored column-and-constraint generation algorithm is developed to solve the problem. The validity and applicability of the strengthened DRO scheme are verified by an IEEE 33-bus EPN and 14-node DHN.

Nguyen et al., in their paper “Using EtherCAT technology to launch online automated guided vehicle (AGV)-manipulation with unity-based platform for smart warehouse management,” introduce an EtherCAT-based model of AGV-manipulation in the Unity platform for smart warehouse management. Theoretical computations in respect to the mechanical design are established to offer the proper parameters. The structure of TwinCAT HMI Server and the setting condition in Unity environment are mentioned. The software architecture is explained in detail. Several laboratory validations are completed in the same conditions.

Nan et al., in their paper “Smart line planning method for power transmission based on D3QN-PER algorithm,” propose a novel intelligent line planning method. It combines the duelling double deep Q network (D3QN) with the prioritized experience replay (PER) mechanism. Correlate the reward function with metrics such as line length, number of corner points, and geographical environmental data, which are pertinent to the construction costs of power transmission line. The D3QN algorithm is formulated by integrating double DQN and duelling DQN. The convergence efficiency of the algorithm is improved by using the PER mechanism for the problem of cost difference due to the different number of corner points in the planning path. Experiments using real maps are conducted to validate the feasibility of the algorithm.

Fang Fang is a Full Professor and the Vice President of North China Electric Power University, Beijing, China. He received the M.Sc. degree in control theory and engineering from North China Electric Power University (Baoding Campus), Baoding, China, in 2001, and the Ph.D. degree in thermal power engineering from North China Electric Power University, Beijing, China, in 2005. His research interests include cyber-physical systems, configuration and operation of integrated energy systems, and intelligent power generation technologies. He has published more than 60 highly level publications and worked as principal investigators for more than 30 research projects or industrial projects. He is an IET Fellow, the Chairman of the China Energy Research Society Technical Committee on Smart Power Generation, the founding Vice Chairman of the Chinese Society for Electrical Engineering Technical Committee on Offshore Wind Power, the founding Vice Chairman of China Electrotechnical Society Technical Committee on Energy Intelligence, and a Council Member of IEEE IES Technical Committee on Industrial Cyber-Physical Systems.

Yuanye Chen is a Lecturer at the School of Control and Computer Engineering, North China Electric Power University, Beijing, China. He received his B.Eng. and M.Eng. degrees in control science and engineering from Harbin Institute of Technology, Harbin, China, in 2010 and 2012, respectively, and the Ph.D. degree in mechanical engineering from University of Victoria, Victoria, Canada, in 2017. Visited City University of Hong Kong in 2016 and 2017.His research interests include networked control, distributed and cooperative control and their application to power and energy systems. He serves in the IEEE-IES Technical Committee on Industrial Cyber-Physical Systems. He also served as the IPC member and/or Associate Editor for academic conferences including IEEE ASCC, IEEE CCTA, IEEE IECON etc.

Mingxi Liu is an Associate Professor in the Department of Electrical and Computer Engineering at the University of Utah, Salt Lake City, USA. Before joining University of Utah, he was an NSERC Postdoc Fellow with Energy & Resources Group at University of California, Berkeley. He received his B.Eng. degree in control science and engineering from Harbin Institute of Technology, Harbin, China, in 2010, and the M. A. Sc. and Ph.D. degrees in mechanical engineering from University of Victoria, Victoria, Canada, in 2012 and 2016, respectively. He is a recipient of the 2022 NSF CAREER Award. His research focuses on building the pathway to a reliable integrated-decentralized power system, including developing new control, optimization, and machine learning theories and bridging them to the building blocks including smart buildings, vehicle-grid integration (VGI), microgrids, cyber-physical security, and grid-edge resources (GERs) integration. Dr. Liu serves on the editorial boards of IEEE Canadian Journal of Electrical and Computer Engineering, IEEE Open Journal of Industrial Electronics Society, and Advances in Applied Energy. He is an active reviewer for Proceedings of the IEEE, IEEE Transactions on Control Systems Technology, IEEE Transactions on Industrial Electronics, IEEE Transactions on Power Systems, IEEE Transactions on Smart Grid etc. He is a Member of IEEE. He serves in the IEEE-IES Technical Committee on Industrial Cyber-Physical Systems, IEEE-CSS Technical Committee on Smart Grid, and IEEE-CSS Technical Committee on Power Generations.

Huazhen Fang is an Associate Professor at the Department of Mechanical Engineering, the University of Kansas, Lawrence, USA. He received his bachelor's degree in Computer Science & Technology from Northwestern Polytechnic University, Xi'an, China in 2006, the M.Sc. in Mechanical Engineering from the University of Saskatchewan, Saskatoon, Canada in 2009, and the Ph.D. in Mechanical Engineering from the Department of Mechanical & Aerospace Engineering, University of California, San Diego, USA, in 2014. He received the Faculty Early Career Award from National Science Foundation in 2019.His research interest lies in system modelling, estimation, control design, machine learning, numerical optimization and their application to energy management, cooperative robotics and environmental observing. He has published more than 70 journal papers and conference proceedings. He currently serves as an Associate Editor for Information Sciences, IEEE Transactions on Industrial Electronics, IEEE Control Systems Letters, IEEE Open Journal of Control Systems, and IEEE Open Journal of the Industrial Electronics Society. He is also a member of the IEEE Control Systems Society Conference Editorial Board.