Artificial neural network-polar coordinated fuzzy controller based maximum power point tracking control under partially shaded conditions

The one of main causes of reducing energy yield of photovoltaic systems is partially shaded conditions. Although the conventional maximum power point tracking (MPPT) control algorithms operate well under uniform insolation, they do not operate well in non-uniform insolation. The non-uniform conditions cause multiple local maximum power points on the power?voltage curve. The conventional MPPT methods cannot distinguish between the global and local peaks. Since the global maximum power point (MPP) may change within a large voltage window and also its position depends on shading patterns, it is very difficult to recognise the global operating point under partially shaded conditions. In this paper, a novel MPPT system is proposed for partially shaded PV array using artificial neural network (ANN) and fuzzy logic with polar information controller. The ANN with three layer feed-forward is trained once for several partially shaded conditions to determine the global MPP voltage. The fuzzy logic with polar information controller uses the global MPP voltage as a reference voltage to generate the required control signal for the power converter. Another objective of this study is to determine the estimated maximum power and energy generation of PV system through the same ANN structure. The effectiveness of the proposed method is demonstrated under the experimental real-time simulation technique based dSPACE real-time interface system for different interconnected PV arrays such as series-parallel, bridge link and total cross tied configurations.     

A genetic algorithm optimized ANN-based MPPT algorithm for a stand-alone PV system with induction motor drive

Artificial neural network (ANN) based maximum power point tracking (MPPT) algorithm makes use of the advantages of ANNs such as noise rejection capability and not requiring any prior knowledge of the physical parameters relating to PV system. This paper proposes a genetic algorithm (GA) optimized ANN-based MPPT algorithm implemented in a stand-alone PV system with direct-coupled induction motor drive. The major objective of this design is to eliminate dc–dc converter and its accompanying losses. Implementing off-line ANN in DSP needs optimization of ANN structure to obtain an ideal size. GA optimization was used in this study to determine neuron numbers in multi-layer perceptron neural network. Another objective of this work is to prevent the necessity of the trade-off between the tracking speed and the oscillations around the maximum power point. Hence, varying step size is used in MPPT algorithm and PI-controller is adopted for simple implementation. Simulation and experimental results have been used to demonstrate effectiveness of the proposed method.     

Improvement in artificial neural network-based estimation of grid connected photovoltaic power output

This paper presents a method to improve the accuracy of artificial neural network (ANN)–based estimation of photovoltaic (PV) power output by introducing two more inputs, solar zenith angle and solar azimuth angle, in addition to the most widely used environmental information, plane-of-array irradiance and module temperature. Solar zenith angle and solar azimuth angle define the solar position in the sky; hence, the loss of modeling accuracy due to impacts of solar angle-of-incidence and solar spectrum is reduced or eliminated. The observed data from two sites where local climates are significantly different is used to train and test the proposed network. The good performance of the proposed network is verified by comparing with existing ANN model, algebraic model, and polynomial regression model which use environmental information only of plane-of-array irradiance and module temperature. Our results show that the proposed ANN model greatly improves the accuracy of estimation in the long term under various weather conditions. It is also demonstrated that the improvement in estimating outdoor PV power output by adding solar zenith angle and azimuth angle as inputs is useful for other data-driven methods like support vector machine regression and Gaussian process regression.     

Improved artificial neural network method for predicting photovoltaic output performance

To ensure the safety and stability of power grids with photovoltaic (PV) generation integration, it is necessary to predict the output performance of PV modules under varying operating conditions. In this paper, an improved artificial neural network (ANN) method is proposed to predict the electrical characteristics of a PV module by combining several neural networks under different environmental conditions. To study the dependence of the output performance on the solar irradiance and temperature, the proposed neural network model is composed of four neural networks, it called multi- neural network (MANN). Each neural network consists of three layers, in which the input is solar radiation, and the module temperature and output are five physical parameters of the single diode model. The experimental data were divided into four groups and used for training the neural networks. The electrical properties of PV modules, including I–V curves, P– V curves, and normalized root mean square error, were obtained and discussed. The effectiveness and accuracy of this method is verified by the experimental data for different types of PV modules. Compared with the traditional single-ANN (SANN) method, the proposed method shows better accuracy under different operating conditions.     

A new approach in MPPT for photovoltaic array based on Extremum Seeking Control under uniform and non-uniform irradiances

This work presents a Maximum Power Point Tracking (MPPT) based on analyzing the output characteristics of PV array under uniform irradiance and partial shading conditions. In order to carry out MPPT in PV panels, under partial shading conditions a method based on Extremum Seeking Control (ESC) is introduced. In contrast with classic ESC, in this method the double of dithering signal frequency is not used, consequently PV output power has a ripple of a lower frequency. Also the drop which occurs when MPPT system starts to operate in classic ESC method is minimized in this paper. The ESC approach for MPPT in this paper uses a series combination of a Low Pass Filter (LPF) and a High Pass Filter (HPF). These two filters act as a Band Pass Filter (BPF) and let a specific frequency of input power which includes the derivative of PV with respect to its voltage pass through. Finally, the system does not operate in local optimal points for efficient point will be global. The algorithm adds partial shadow judging conditions in ESC method. The system runs the variable step ESC method to realize MPPT when photovoltaic array is under uniform irradiance. Under Partial Shading Condition (PSC), the control method can eliminate the interference of local maximum power point (MPP) to make 23 the PV array running at global MPP. In addition, unlike other methods, the proposed MPPT operates on the global MPPs. The proposed MPP tracker does not add any extra complexity compared to the classical ones. However, it increases significantly the efficiency of the PV installation under PSC. We will show that under uniform irradiance, the proposed MPPT leads to faster performances than classical approaches.     

Adaptive neuro-fuzzy inference system-based maximum power point tracking of solar PV modules for fast varying solar radiations

This paper analyses the operation of an adaptive neuro-fuzzy inference system (ANFIS)-based maximum power point tracking (MPPT) for solar photovoltaic (SPV) energy generation system. The MPPT works on the principle of adjusting the voltage of the SPV modules by changing the duty ratio of the boost converter. The duty ratio of the boost converter is calculated for a given solar irradiance and temperature condition by a closed-loop control scheme. The ANFIS is trained to generate maximum power corresponding to the given solar irradiance level and temperature. The response of the ANFIS-based control system is highly precise and offers an extremely fast response. The response time is seen as nearly 1 ms for fast varying cell temperature and 6 ms for fast varying solar irradiance. The simulation is done for fast-changing solar irradiance and temperature conditions. The response of the proposed controller is also presented.     

A novel photovoltaic maximum power point tracking technique based on grasshopper optimized fuzzy logic approach

The maximum power point tracking (MPPT) in the PV system has become complex due to the stochastic nature of the load, intermittency in solar irradiance and ambient temperature. To address this problem, a novel Grasshopper optimized fuzzy logic control (FLC) approach based MPPT technique is proposed in this paper. In this proposed MPPT, grasshopper optimization is used to tune the membership functions (MFs) of FLC to handle all uncertainties caused by variable irradiances and temperatures. The performance of the proposed grasshopper optimized FLC based MPPT is studied under rapidly changing irradiance and temperature. The proposed MPPT overcomes the limitations such as slow convergence speed, steady-state oscillations, lower tracking efficiency as encountered in conventional methods viz. perturb & observed (P&O) and FLC techniques. The feasibility of the proposed MPPT is validated through experimentation. The effectiveness of the proposed scheme is compared with P&O and also with FLC MPPT.     

A photovoltaic powered electrolysis converter system with maximum power point tracking control

One of the main problems for renewable and other innovative energy sources is the storage of energy for sustainability. This study focuses on two different scenarios to benefit from solar energy more efficiently. Photovoltaic (PV) energy is converted to the desired voltage level using a buck converter for generating hydrogen with electrolysis process. A maximum power point tracking (MPPT) algorithm is used to benefit from the photovoltaic sources more efficiently. The basic electrolysis load for hydrogen production needs low voltage and high current and controlled sensitively to supply these conditions. The photovoltaic powered buck converter for electrolysis load was simulated in MATLAB/Simulink software using a perturb and observe (P and O) MPPT algorithm and PI controller. The simulation results show that in normal, short circuit and open circuit working conditions the PV and load voltages are stabilized. The efficiency of the proposed system is reached more than 90% for high irradiance levels.     

Relevance vector-machine-based solar cell model

This paper proposes an advanced machine learning method, relevance vector machines (RVMs), to model photovoltaic (PV) cells with a few measured data, over a range of expected operating conditions. RVMs are established on a Bayesian formulation which results in usage of less number of relevance vectors leading to much more sparse representation than the support vector machine. The RVM model can be used to predict short-circuit current and open-circuit voltage and thereby maximum power point for any unknown temperature and irradiation. Coordinate translation technique is used to plot the nonlinear I–V characteristics of PV cells. The proposed method matches the measured data more accurately than the pure neural network model and the neuro-fuzzy model.     

Resiliency oriented control of a smart microgrid with photovoltaic modules

The resiliency of a standalone microgrid is of considerable issue because the available regulation measures and capabilities are limited. Given this background, this paper presented a new mathematical model for a detailed photovoltaic (PV) module and the application of new control techniques for efficient energy extraction. The PV module employs a single-stage conversion method to integrate it with the utility grid. For extraction the maximum power from PV and integrate it to power grid, a three-phase voltage source converter is used. For obtaining the maximum power at a particular irradiance a maximum power point tracking (MPPT) scheme is used. The fuzzy logic control and adaptive network-based fuzzy inference system are proposed for direct current (DC) link voltage control. The proposed model and control scheme are validated through a comparison with the standard power-voltage and current–voltage charts for a PV module. Simulation results demonstrate that the system stability can be maintained with the power grid and in the island mode, in contrast with the MPPT.     

Short term solar irradiance forecasting using a mixed wavelet neural network

In modern smart grids and deregulated electricity markets, accurate forecasting of solar irradiance is critical for determining the total energy generated by PV systems. We propose a mixed wavelet neural network (WNN) in this paper for short-term solar irradiance forecasting, with initial application in tropical Singapore. The key advantage of using wavelet transform (WT) based methods is the high signal compression ability of wavelets, making them suitable for modeling of nonstationary environmental parameters with high information content, such as short timescale solar irradiance. In this WNN, a combination of the commonly known Morlet and Mexican hat wavelets is used as the activation function for hidden-layer neurons of a feed forward artificial neural network (ANN). To demonstrate the effectiveness of the proposed approach, hourly predictions of solar irradiance, which is an aggregate sum of irradiance value observed using 25 sensors across Singapore, are considered. The forecasted results show that WNN delivers better prediction skill when compared with other forecasting techniques.     

两类离网光伏控制器外特性比较分析

对串联PWM型和软开关MPPT型离网光伏控制器的外特性进行了比较分析,给出了两类光伏控制器在不同阶段的电压输出波形。由于对峰值电压的受控特性不同,造成串联PWM控制器比软开关MPPT控制器的蓄电池寿命短。通过仿真得到两类光伏控制器输出功率随蓄电池电压、日照强度和温度的变化曲线。在标准条件下软开关MPPT型控制器比串联PWM型控制器的输出功率平均多26%。随着日照强度的增加或随着温度的降低,两种控制器外特性的差别更大。     

Input output feedback linearization control and variable step size MPPT algorithm of a grid-connected photovoltaic inverter

In this paper, the power factor of a grid-connected photovoltaic inverter is controlled using the input output Feedback Linearization Control (FLC) technique. This technique transforms the nonlinear state model of the inverter in the d–q reference frame into two equivalent linear subsystems, and then applies a pole placement linear control loops on this subsystem in order to separately control the grid power factor and the dc link voltage of the inverter. Maximum Power Point Tracker (MPPT) that allows extraction of maximum available power from the photovoltaic (PV) array has been included. This MPPT is based on variable step size incremental conductance method. Compared with conventional fixed step size method, the variable step MPPT improves the speed and the accuracy of the tracking.     

Highly efficient maximum power point tracking using DC–DC coupled inductor single-ended primary inductance converter for photovoltaic power systems

Solar photovoltaics (PVs) have nonlinear voltage–current characteristics, with a distinct maximum power point (MPP) depending on factors such as solar irradiance and operating temperature. To extract maximum power from the PV array at any environmental condition, DC–DC converters are usually used as MPP trackers. This paper presents the performance analysis of a coupled inductor single-ended primary inductance converter for maximum power point tracking (MPPT) in a PV system. A detailed model of the system has been designed and developed in MATLAB/Simulink. The performance evaluation has been conducted on the basis of stability, current ripple reduction and efficiency at different operating conditions. Simulation results show considerable ripple reduction in the input and output currents of the converter. Both the MPPT and converter efficiencies are significantly improved. The obtained simulation results validate the effectiveness and suitability of the converter model in MPPT and show reasonable agreement with the theoretical analysis.     

Study of hourly and daily solar irradiation forecast using diagonal recurrent wavelet neural networks

An accurate forecast of solar irradiation is required for various solar energy applications and environmental impact analyses in recent years. Comparatively, various irradiation forecast models based on artificial neural networks (ANN) perform much better in accuracy than many conventional prediction models. However, the forecast precision of most existing ANN based forecast models has not been satisfactory to researchers and engineers so far, and the generalization capability of these networks needs further improving. Combining the prominent dynamic properties of a recurrent neural network (RNN) with the enhanced ability of a wavelet neural network (WNN) in mapping nonlinear functions, a diagonal recurrent wavelet neural network (DRWNN) is newly established in this paper to perform fine forecasting of hourly and daily global solar irradiance. Some additional steps, e.g. applying historical information of cloud cover to sample data sets and the cloud cover from the weather forecast to network input, are adopted to help enhance the forecast precision. Besides, a specially scheduled two phase training algorithm is adopted. As examples, both hourly and daily irradiance forecasts are completed using sample data sets in Shanghai and Macau, and comparisons between irradiation models show that the DRWNN models are definitely more accurate.     

Polar coordinated fuzzy controller based real-time maximum-power point control of photovoltaic system

It is crucial to improve the photovoltaic (PV) system efficiency and to develop the reliability of PV generation control systems. There are two ways to increase the efficiency of PV power generation system. The first is to develop materials offering high conversion efficiency at low cost. The second is to operate PV systems optimally. However, the PV system can be optimally operated only at a specific output voltage and its output power fluctuates under intermittent weather conditions. Moreover, it is very difficult to test the performance of a maximum-power point tracking (MPPT) controller under the same weather condition during the development process and also the field testing is costly and time consuming. This paper presents a novel real-time simulation technique of PV generation system by using dSPACE real-time interface system. The proposed system includes Artificial Neural Network (ANN) and fuzzy logic controller scheme using polar information. This type of fuzzy logic rules is implemented for the first time to operate the PV module at optimum operating point. ANN is utilized to determine the optimum operating voltage for monocrystalline silicon, thin-film cadmium telluride and triple junction amorphous silicon solar cells. The verification of availability and stability of the proposed system through the real-time simulator shows that the proposed system can respond accurately for different scenarios and different solar cell technologies.     

Brushless DC motor drives supplied by PV power system based on Z-source inverter and FL-IC MPPT controller

This paper discusses operation performance of a water pumping system consist of a brushless dc (BLDC) motor coupled a centrifugal pump and accompanying a Z-source inverter (ZSI) fed by a photovoltaic (PV) array, to be improved. Despite conventional double-stage power converters, this paper proposes utilizing a single-stage ZSI to extract the maximum power of the PV array and supply the BLDC motor simultaneously. Utilizing the ZSI provides some inherent advantages such as high efficiency and low cost, which is very promising for PV systems due to its novel voltage buck/boost capability. In addition, in order to precisely perform the maximum power point tracking (MPPT) of the PV array the fuzzy logic-incremental conductance (FL-IC) MPPT scheme is proposed. The proposed FL-IC MPPT scheme provides enough modification to the conventional IC method to enjoy an appropriate variable step size MPPT control signal for the ZSI. Moreover, direct torque control (DTC) is found more effective in comparison with hysteresis current control with current shaping to drive the BLDC motor, because it benefits from faster torque response, reduced torque ripple, less sensitivity to parameters variations, and simple implementation. In the mean time, due to the frequently variations of the PV power generation; delivered mechanical power to the centrifugal pump is variable. Thus, the BLDC motor should be driven with variable reference speed. In order to improve the speed transient response of the BLDC motor and enhance the energy saving aspect of the system, it should enjoy a high quality dynamic response characteristic. Therefore, to realize these purposes, particle swarm optimization (PSO) has been proposed to regulate the proportional-integral-derivative (PID) parameters of the BLDC motor speed controller. The system configuration, operation principle and control methods are presented in detail. Finally, the proposed system was simulated in different operation conditions of the PV array by computer simulations and the effectiveness of the proposed control strategies has been validated by comparative studies and simulation results.     

Enhancement of grid-connected photovoltaic system using ANFIS-GA under different circumstances

In recent years, many different techniques are applied in order to draw maximum power from photovoltaic (PV) modules for changing solar irradiance and temperature conditions. Generally, the output power generation of the PV system depends on the intermittent solar insolation, cell temperature, efficiency of the PV panel and its output voltage level. Consequently, it is essential to track the generated power of the PV system and utilize the collected solar energy optimally. The aim of this paper is to simulate and control a grid-connected PV source by using an adaptive neuro-fuzzy inference system (ANFIS) and genetic algorithm (GA) controller. The data are optimized by GA and then, these optimum values are used in network training. The simulation results indicate that the ANFIS-GA controller can meet the need of load easily with less fluctuation around the maximum power point (MPP) and can increase the convergence speed to achieve the MPP rather than the conventional method. Moreover, to control both line voltage and current, a grid side P/Q controller has been applied. A dynamic modeling, control and simulation study of the PV system is performed with the Matlab/Simulink program.     

Neural network observers for on-line tracking of synchronousgenerator parameters

This paper presents a methodology for implementing artificial neural network (ANN) observers in estimating and tracking synchronous generator parameters from time-domain online disturbance measurements. Data for training the neural network observers are obtained through offline simulations of a synchronous generator operating in a one-machine-infinite-bus environment. Nominal values of parameters are used in the machine model. After training, the ANN observer is tested with simulated online measurements to provide estimates of unmeasurable rotor body currents and in tracking simulated changes in machine parameters     

An improved maximum power point tracking method for photovoltaic systems

In most of the maximum power point tracking (MPPT) methods described currently in the literature, the optimal operation point of the photovoltaic (PV) systems is estimated by linear approximations. However these approximations can lead to less than optimal operating conditions and hence reduce considerably the performances of the PV system. This paper proposes a new approach to determine the maximum power point (MPP) based on measurements of the open-circuit voltage of the PV modules, and a nonlinear expression for the optimal operating voltage is developed based on this open-circuit voltage. The approach is thus a combination of the nonlinear and perturbation and observation (P&O) methods. The experimental results show that the approach improves clearly the tracking efficiency of the maximum power available at the output of the PV modules. The new method reduces the oscillations around the MPP, and increases the average efficiency of the MPPT obtained. The new MPPT method will deliver more power to any generic load or energy storage media.