Power Quality Improvement in Grid Connected Distribution Systems using Artificial Intelligence based Controller

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.

This paper presents the hysteresis controller, based scheme for distribution static compensator (DSTATCOM) for analysis of faults, line-line fault, line to ground fault, single line to ground fault for power quality improvement. DSTATCOM is used for power quality improvement. It provides the deficient reactive power in the distribution system. Conventionally hysteresis controller uses proportional and integral (PI) controller. In this paper, artificial neural network (ANN) and adaptive neuro fuzzy inference system (ANFIS) based DSTATCOM controllers are implemented for the analysis of different faults. This paper also provides the comparison of different faults for ANN and ANFIS based DSTATCOM with the help sequence analyzer. Sequence analyzer is used for the positive, negative and zero sequence analysis of three phase signal. Per unit study of the output voltage is carried out to compare the results of the different faults based on ANN and ANFIS controller. The simulation results show the improved results for the voltage profiles with ANFIS controller. The simulation of the proposed model is done with the help of MATLAB/Simulink software.

These days the Power Quality has become the key issue in electrical distribution power systems. The power quality gets deteriorated due to the extensive use of non-linear loads and power electronic devices like solid-state switching devices which injects the current harmonics in the distribution systems. These harmonics leads to increase in power loss in transmission and distribution network. This paper shows a comparison of Adaptive Neuro Fuzzy Inference System (ANFIS) with Instantaneous Reactive Power Theory (IRPT) and Artificial Neural Network (ANN) for a three phase Distribution Static Compensator (DSTATCOM). This is used for compensation of power loss, current harmonics and reactive power compensation. These control methods are executed with MATLAB Simulink 2018a. The simulation results obtained demonstrates that ANFIS performs better than ANN and IRPT in terms of Total Harmonic Distortion, peak overshoot, settling time, convergence rate and the settling time of dc link voltage.

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.

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.

An attenuation relationship model belonging to a region with a high earthquake hazard is important. It is used for engineering studies to know how the peak ground acceleration (PGA) value depends on the distance where there are no stations. This study used earthquakes with magnitudes greater than 4 that IzmirNET recorded between 2009 and 2017 to determine the PGA through an artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS), which are widely applied in engineering seismology studies. For this purpose, 2925 records from 62 earthquakes were analysed in the ANN and ANFIS applications. Magnitude, focal depth, hypocentral distance (Rhyp), and site conditions comprise the inputs, and PGA values are the outputs. Using the Karaburun earthquake, we compared the ANN and ANFIS models using different ground motion prediction equations (GMPE) and the appropriate criteria. We determined the proximate values to PGA values measured at IzmirNET stations of the Karaburun earthquake, which was M = 6.2 in 2017, were used to test the ANN and ANFIS. The results were examined and indicated that the ANN and ANFIS are good candidates for obtaining PGA values for future earthquakes in the studied area. In addition, the PGA values of subsequent earthquakes can be calculated more quickly without any preliminary evaluation using an ANN and ANFIS.

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.

Analysis of adsorption isotherms of Ag+, Co+2, and Cu+2 onto zeolites using computational intelligence models

Brushless DC (BLDC) motors are the most popular motors used by the industry because they are easy to control. BLDC motors are generally controlled by artificial controls such as Fuzzy Logic Controller (FLC), Artificial Neural Network (ANN), and Adaptive Neuro-Fuzzy Inference System (ANFIS). However, the performance of the BLDC control system in previous studies was compared separately with their respective parameters, making it difficult to evaluate comprehensively. Therefore, in order to investigate the characteristic performance of Fuzzy, ANN, and ANFIS, this article provides a comparison of these artificial controls. Two scenarios of the dynamic tests are conducted to investigate control performance under constant torque-various speed and constant speed-various torque. By dynamic testing, characteristics of Fuzzy, ANN, and ANFIS can be observed as real applications. The testing parameters are: Settling Time, Overshoot and Overdamp (in the graph and average value), and then statistic performance are: Integral Square Error (ISE), Integral Absolute Error (IAE), Integral Time Absolute Error (ITAE), and Mean Absolute Error (MAE). The test result in scenario 1 showed that the ANN has a better performance compared to other controllers with the MAE, IAE, ITAE, and ISE value of 31.3003; 105.6280; 208.0630; and 5,7289 e4, respectively. However, in scenario 2, ANN only has a better performance compared to other controllers on just a few parameters. In scenario 2, ANN is indeed able to maintain speed but it has a more ripple value than ANFIS. Even so, the ripple that occurs in ANN does not have too much value compared to the setpoint. Therefore, the MAE value of the ANN is smaller than the ANFIS (18.8937 of ANN and 28.4685 of ANFIS).

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

The proposed work deals with the implementation of a control approach for an active power transfer between solar photovoltaic (PV) array and grid/ load alongwith power quality improvement by eliminating harmonics and compensating reactive power required by the load in the distribution system. The PV array is directly connected across the DC link of a voltage source converter (VSC). The power is transferred to the grid/ load through VSC, which performs the function of distribution static compensator (DSTATCOM) by injecting compensating currents in the proposed system. The PV array is operated at maximum power by employing the usage of perturb and observe (P&O) maximum power point tracking (MPPT) approach in order to extract the available maximum power from the solar PV array. A feed-forward term for the solar PV array power, is incorporated for the enhancement of dynamic response. The prominence of the control algorithm lies in the efficient switching of VSC, by generating reference grid currents, which are obtained through indirect current control technique. The recursive digital filter is utilized for processing the load currents and extracting the active power component of the load currents. Therefore, the active power component of load currents obtained, are used for generating the reference grid currents in the proposed system. A prototype of the system is developed in the laboratory and its performance is studied for varying loads, changing solar insolation, and voltage swell and voltage sag conditions.

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).

Due to the increasing need for intelligent systems, the adaptive neuro-fuzzy inference system (ANFIS) has recently attracted the attention of researchers in various scientific and engineering areas. The purpose of this work is to present the modeling of a photovoltaic power supply (PVPS) system using an ANFIS. For the modeling of the PVPS system, it is required to find suitable models for its different components (ANFIS PV-generator, ANFIS battery and ANFIS regulator) under variable climatic conditions. A database of measured weather data (global radiation, temperature and humidity) and electrical signals (photovoltaic, battery and regulator voltage and current) of a PVPS system installed in Tahifet (south of Algeria) has been recorded for the period from 1992 to 1997 using a data acquisition system. These data have been used for the modeling and simulation of the PVPS system. The ANFIS for the PV-generator, battery and regulator have been trained by using 10 signals recorded from the different components of the PVPS system. Each signal is represented by 365*5 values (complete 5-years). A set of data for 4-years have been used for the training of the ANFIS and data for 1-year has been used for the testing of the ANFIS. In this way, the ANFIS was trained to accept and handle a number of unusual cases. The comparison between actual and estimated values obtained from the ANFIS gave satisfactory results. The correlation coefficient between measured values and those estimated by the ANFIS gave good prediction accuracy of 98%. In addition, test results show that the ANFIS performed better than the artificial neural networks (ANN). Predicted electrical signals by the ANFIS can be used for several applications in PV systems.

Evaluation of ANN and ANFIS modeling ability in the prediction of AISI 1050 steel machining performance

Modern utility systems are being heavily strained by rising energy consumption and dynamic load variations, which have an impact on the quality and reliability of the supply. Harmonic injection and reactive power imbalance are caused by the widespread divergence. Power quality (PQ) issues are mostly caused by renewable energy powered by power electronic converters that are integrated into the utility grid, despite the fact that a range of industries require high-quality power to function properly at all times. Several solutions have been created, but continuing efforts and newly improved solutions are needed to solve these problems by operating according to various international standards. Distributed Static Compensator (DSTATCOM) was created in the proposed model to enhance PQ in a standard bus system. A standard bus system using the DSTATCOM model was initially developed. A real-time dataset was gathered while applying various PQ disturbance conditions. A deep learning controller was created using this generated dataset, which examined the bus voltages to generate the DSTATCOM pulse signal. Two case studies, the IEEE 13 bus and the IEEE 33 bus system, were used to analyze the proposed work. Performance of the proposed deep learning controller was verified in various situations, including interruption, swell, harmonics, and sag. The outcome of THD in the IEEE 13 bus is 0.09% at the sag period, 0.08% at the swell period, 0.01% at the interruption period, and in the IEEE 33 bus was 1.99% at the sag period, 0.44% at the swell period, and 0.01% at the interruption period. Also, the effectiveness of the proposed deep learning controller was examined and contrasted with current methods like K-Nearest Neighbor (KNN) and Feed Forward Neural Network (FFNN). The validated results show that the suggested method provides an efficient mitigation mechanism, making it suitable for all cases involving PQ issues.