Deep-Learning-Based Controller for Parallel DSTATCOM to Improve Power Quality in Distribution System

Large penetration of PV in a microgrid connected distribution system impacts the weak utility distribution system by creating various power quality (PQ) problems such as voltage sag or swell, unbalance, harmonics and DC current injection etc. These power quality (PQ) issues and they are broadly classified as current related PQ issues and voltage related PQ issues. The current related issues are mitigated by one of the custom power device connected in parallel namely distribution static compensator (DSTATCOM), by operating in current controlled mode (CCM). The dynamic voltage restorer (DVR) is another custom power device (CPD) for mitigating voltage related PQ problems. It is reported in literature that, a suitable modification of a DSTATCOM can achieve the capability to compensate voltage disturbances also. A multiple functions of DSTATCOM is thus achieved by operating the device so as to mitigate the current and voltage related PQ issues. Thus a multi-functional control strategy allow DSTATCOM to compensate voltage and current related PQ problems. This paper presents a hybrid DSTATCOM which can be used in highly PV penetrated distribution system to control the voltage and current related PQ issues. The topology uses a suitably designed foreign inductor, connected between the grid and load. A dynamic reference load voltage generation algorithm using instantaneous symmetric component theory (ISCT) is presented. The simulation is done with real time voltage level using MATLAB/SIMULINK.

Renewable energy integration into the modern power grid introduces challenges of power quality, current and voltage harmonics, and reactive power imbalances. The extensive use of smart appliances and increasing electric vehicle load across residential, industrial, transportation, and commercial sectors have led to increasing current quality problems in the electrical power system. Grid-connected distributed static compensator (DSTATCOM) integrated with hybrid renewable energy including solar photovoltaic (PV) and wind energy is an efficient futuristic approach to enhance power quality and optimize energy management. This paper presents a novel adaptive control, variable step size least mean square algorithm with ℓ0 norm constraint for the interlinking converter to regulate power requirements and mitigate current quality issues in the grid. This overall system utilizing controller ensures rapid and reliable power supply from PV and wind to the load and utility grid during the period of generation and works as a DSTATCOM during the low or no generation phase, enhancing power reliability. To extract peak power output from dynamically changing conditions, the gray wolf optimization is implemented with a PV and wind energy system. The highly lagging and non-linear loads are considered in this work. Analysis of total harmonic distortion in both the grid current and point of common coupling voltage shows it to be within operational limits and maintains adherence to established power quality regulations.

Integrations of renewable energy (RE) sources like wind energy and solar energy to utility grid affects quality of electrical power. Utility operators have to ensure a good quality power supply and their services to retain the existing consumers or attract the new consumers. An effective system for monitoring and improvement of power quality (PQ) can help to achieve this task. The improvement of PQ can be achieved by using the distribution static compensator (DSTATCOM) in utility grid. This research work presents a control design using synchronous reference frame (SRF) theory to provide efficient control to the DSTATCOM for PQ improvement in utility grid in the presence of solar PV energy. A capacitor and battery bank is used as the DC bus in the design of DSTATCOM. The DSTATCOM has been implemented for improvement of PQ with solar PV energy during various operational events. The events considered include the tripping/reclosing of feeder, switching ON/OFF of capacitor bank, switching ON/OFF of inductive-resistive (LR) load. Proposed study is carried out using MATLAB/Simulink software with the help of an IEEE-13 bus test system. Proposed study is performed using a test system comprising of voltage source and load integrated on point of common coupling (PCC).

Proportional and Integral (PI) controllers are usually accustomed for the control operation of Distribution Static Compensator (DSTATCOM) for the distribution system. However, since the system is very nonlinear and subject to numerous disturbances, the PI controlled DSTATCOM cannot offer optimum performance for various operation points. Additional controllers like the Instant Power Theory (IPT) supported fuzzy logic approach is needed for the DSTATCOM to supply adequate dynamic current control and to enhance power quality and stability of the distribution system. This paper presents the planning of fuzzy logic Controllers (FLC) of a DSTATCOM for improving power quality for a distribution system. The IPT based FLC for the DSTATCOM is used for improving the power quality and the dynamic performance of a distribution system is compared with a DSTATCOM controlled IPT based PI controller. The performances of the DSTATCOM controllers are evaluated throughout grid-side currents with linear and non-linear loads of the distribution system. Simulation results show that the DSTATCOM with IPT based FLC will improve the power quality by reducing reactive currents and harmonic currents with higher system dynamic performance than the DSTATCOM with IPT based standard PI controller.

This paper proposes an intelligent control strategy based on the adaptive neuro-fuzzy inference system (ANFIS) to enhance power quality in wind energy systems connected to weak grids. Weak grids, characterized by high impedance and low short-circuit ratios, suffer from voltage fluctuations, harmonic distortions, and reactive power imbalances when integrating wind energy. Conventional control methods, such as proportional-integral and fuzzy logic controllers, lack real-time adaptability, limiting their effectiveness in weak grid scenarios. The proposed ANFIS-based synchronous reference frame (SRF) control for a distribution static compensator (DSTATCOM) introduces an intelligent learning mechanism that dynamically adjusts reactive power compensation, harmonic mitigation, and voltage stabilization based on grid conditions. Unlike traditional approaches, the ANFIS-SRF controller leverages self-adaptive tuning and non-linear decision-making capabilities, ensuring superior system performance. The obtained simulations validate the effectiveness of the proposed method, demonstrating that grid voltage total harmonic distortion is reduced from 11.26 to 9.83% under non-linear load conditions and from 4.97 to 2.64% in mixed-load scenarios, maintaining compliance with IEEE 1547 and IEEE 519-2014 standards. Additionally, the power factor is significantly improved, reaching values above 0.98, while the proposed controller successfully maintains grid voltage and current stability under varying wind conditions. These numerical findings assures that the ANFIS-SRF-controlled DSTATCOM outperforms traditional control methods in ensuring reliable and efficient wind energy integration into weak grids. This study contributes to intelligent grid control applications by providing a self-learning, real-time adaptive solution that enhances grid stability, power quality, and renewable energy penetration.

A Distribution static compensator (DSTATCOM) has become a potential choice in alleviating power quality(PQ) issues in distribution network with non-linear loads. DSTATCOM essentially maintains the PCC voltage and inverter DC link voltage by using two AC and DC PI controllers. Conventionally the computation of these gain values of PI controllers are done based on the model based or trial and error method. This paper presents comparitive study of optimisation based approach for obtaining the k p and k i values of the pi controller. Particle swarm optimization(PSO) and Ant colony optimization(ACO) based PI controller tuning is used in DSTATCOM for improved dynamic response and also the power quality improvement. The DSTATCOM is modeled and simulated in MATLAB/SIMULINK. The optimization techinques based PI controller tuning have been compared with conventional approach and thier performances are verified.

Power quality improvement in distribution network using DSTATCOM with battery energy storage system

In this paper a new control algorithm has been proposed to control the power flow of the utility grid which has been penetrated by renewable energy sources (RES). The proposed control algorithm ensures utility grid to undergo minimum power changes. The hybrid energy storage system consisting of high power density element such as super capacitor and high energy density element such as battery storage has been used to compensate the residual power. The proposed control algorithm has been implemented to the distribution static compensator (DSTATCOM) to achieve multiple goals, such as integrating photo voltaic (PV) to the utility grid, compensating the reactive power and current related power quality issues and the power flow balancing. The balancing of the energy flows and current related power quality issues have been compensated using a DSTATCOM. The proposed configuration of the system has been implemented in MATLAB/Simulink and the corresponding simulation results are being presented in the manuscript.

The rapid integration of distributed generation sources and power electronic converters in modern smart grids has introduced significant power quality (PQ) challenges, including increased harmonic distortion, voltage instability, and power losses. Existing optimization techniques struggle with slow convergence, suboptimal tuning of control parameters, and limited PQ enhancement. To deal with these problems, this research proposes a novel Lightning Search Optimization–Quantum Neural Network (LSO-QNN) approach for optimizing the Distribution Static Compensator (DSTATCOM)-based Proportional–Integral–Derivative (PID) controller to enhance PQ in grid-connected renewable energy systems. The novelty of this work lies in the hybridization of LSO with QNN, which enables adaptive and dynamic tuning of PID controller gains, ensuring faster convergence, enhanced harmonic suppression, and improved voltage stability compared to conventional methods. Simulation findings indicates that the proposed LSO-QNN approach achieves a voltage Total Harmonic Distortion (THD) of 0.38% and Current THD of 3.4%, significantly outperforming Particle Swarm Optimization (PSO) (6.4%), Heap-Based Optimizer (HBO) (4.5%), and Nomadic People Optimizer (NPO) (5.5%). Moreover, it improves voltage stability (1.1s) and reduces computation time (34 ms), achieving an overall efficiency of 99.3%. These findings establish the superiority of LSO-QNN over traditional optimization techniques, making it a highly effective and practical solution for real-world PQ enhancement in smart grids.

An increasing growth of non-linear load in the three-phase four-wire distribution system, results in various power quality problems in the distribution system. Custom power devices (CPD) have been evolved to solve the power quality problems in the distribution system. Among the various custom power devices, Distribution Static Compensator (DSTATCOM) is one of the effective solutions for solving the power quality problems. This paper reveals about Distribution static compensator (DSTATCOM) for balancing of source currents, harmonic mitigation and neutral current compensation in three-phase four-wire distribution system. A synchronous reference frame (SRF) theory is projected for the control of DSTATCOM. Four-leg voltage source converter (VSC) with a dc capacitor is used as four-wire DSTATCOM. Here DSTATCOM is operated in load compensation mode. The first three-legs are used for balancing of source current and harmonic mitigation and the fourth leg is used for neutral current compensation. The compensation performance of DSTATCOM using the proposed control strategy is demonstrated using simulation results obtained from MATLAB/SIMULINK.

Reactive power compensation is an important aspect in the control of distribution systems. Reactive current in addition to increasing the distribution system losses, introduces various power quality problems like, harmonics, voltage sag, swell and poor load power factor. These power quality issues result in the malfunction of sensitive equipments. A Distribution Static Compensator (DSTATCOM) proves to be a viable solution for the mitigation of such power quality issues. The aim of this paper is to compare an optimized PI and a Fuzzy controlled DSTATCOM for reactive power compensation and harmonic mitigation. Here the PI controllers are first optimized by using error minimization criteria through Genetic algorithms and then replaced by a Fuzzy controller. Through various simulations it is concluded that the transient response of fuzzy controllers is better than the optimized PI controllersKeywords: Decoupled Current Control, Distribution Static Compensator (DSTATCOM), Fuzzy Logic Controllers, Genetic Algorithms, Integral Square Error (ISE), Power Quality

The renewable energy sources are intermittent in nature with high availability-based uncertainties. These resources when integrated to the utility grid significantly hinder the grid power quality (PQ). This article deals with PQ issues arising in the topology including the grid connected renewable energy generating system, which is a combination of wind turbine (WT) driving the synchronous generator (SG) and solar photovoltaic (PV) array and control strategies to improve the same. The solar PV array is associated at the dc link eliminating the dc–dc converter stage via a common dc link. The variable revolutions per minute (RPM) operation is achieved by the back to back connected grid side VSC (GVSC) and the machine side voltage source converter (MVSC). The GVSC is controlled by using the nonlinear harmonic observer (NHO) control. It provides robust implementation at various perturbations faced practically, i.e., discontinuous jump of frequency, phase, and amplitude. The fundamental load current component is effectively extracted. The NHO control is deployed within the framework to allow the system to dynamically adapt to the changes in the operating environment while maintaining the PQ of the utility grid. A special attention is paid to the condition when the power generated by the solar PV array is zero (during night operation) and the GVSC acts in the distribution static compensator (DSTATCOM) mode fulfilling the reactive power requirement. The regulation of MVSC is achieved by the vector control. Independent optimal power extraction techniques are featured for both wind and solar PV array. Test conditions are realized on the laboratory developed prototype and test results are acquired for PQ, loss of supply from solar PV array, effects of randomness of the wind speed, and solar insolation along with load alterations.

The decay of power quality is one of the principal issues of electrical distribution systems. One of the main reasons for this is the use of non-linear devices like the switching devices and the power electronics converters. Non-linearity leads to detrimental effects on the utility of the power supply, system efficiency, reduction in power factor, etc. The reactive power is increased due to the reduction in power factor and it does not have any contribution in the transfer of energy, hence its compensation is needed. In this paper, the Artificial Neural Network (ANN) and Adaptive Neuro Fuzzy Inference System (ANFIS) based control methods for a Three-Phase Distribution Static Compensator (DSTATCOM) are proposed. This is used for compensation of the reactive power along with the current related power quality issues that include harmonics. These control methods are simulated in the MATLAB environment with the help of the SIMULINK toolbox. The simulation results suitably demonstrate the performance of these methods and it is found that source current waveforms with lesser distortion are achieved with ANFIS as compared to ANN.

Distribution static compensator (DSTATCOM) is a shunt compensation device that is generally used to solve power quality problems in distribution systems. In an all-electric ship power system, power quality issues arise due to high-energy demand loads such as pulse loads. This paper presents the application of a DSTATCOM to improve the power quality in a ship power system during and after pulse loads. The control strategy of the DSTATCOM plays an important role in maintaining the voltage at the point of common coupling. A novel adaptive control strategy for the DSTATCOM based on artificial immune system (AIS) is presented in this paper. The optimal parameters of the controller are first obtained by using the particle swarm optimization algorithm. This provides a sort of innate immunity (robustness) to common system disturbances. For unknown and random system disturbances, the controller parameters are modified online, thus providing adaptive immunity to the control system. The performance of the DSTATCOM and the AIS-based adaptive control strategy is first investigated in MATLAB-/Simulink-based simulation platform. It is verified through a real-time ship power system implementation on a real-time digital simulator and the control algorithm on a digital signal processor.

In this study, model predictive control (MPC) of the three‐phase split capacitor (TPSC) distribution static compensator (DSTATCOM) using VlseKriterijumska Optimizacija I Kompromisno Resenje (VIKOR) method is proposed. Power quality improvement using MPC involves the selection of switching state which minimises the difference between reference and actual DSTATCOM currents. However, the limitation of MPC is higher switching frequency and limitation of TPSC DSTATCOM is voltage divergence of dc‐link capacitors. To alleviate these problems, one constraint is to suppress the voltage divergence and the other is to reduce the switching frequency is included in the cost function using weighting factors. Optimal selection of switching state for minimisation of a multi‐constraint cost function is depending on the weighting factor; however, its tuning is a challenging task. In this study, the simplification of weighting factor tuning is achieved using the VIKOR method and it further selects the optimal switching state based on a specific measure of closeness to the ideal solution and multi‐criteria ranking index. The advantages of the proposed work are compensation of power quality issues, balance the dc‐link voltages, switching frequency reduction of inverter and simplification of weighting factor tuning. Finally, the proposed work is evaluated using simulation and experimental studies.