Maximum Power Point Tracking Based on Reinforcement Learning Using Evolutionary Optimization Algorithms

Intelligent MPPT for photovoltaic panels using a novel fuzzy logic and artificial neural networks based on evolutionary algorithms

Due to the Randomness and fluctuation of the photovoltaic (PV) system, Maximum Power Point Tracking (MPPT) algorithm is employed to ensure the maximum power extraction from PV arrays, when it is connected to the grid. The previous studies have indicated that the MPPT algorithm is one of the main causes of interharmonics emission in PV systems. The MPPT algorithm parameters such as perturbation step size inevitably have a strong impact on the interharmonics in the current injected to the grid. In general, a smaller MPPT perturbation step size will reduce the interharmonics emission level, but it will result in poor tracking performance of the MPPT algorithm. Thus, there is a trade-off between the MPPT efficiency and the interharmonics emission in PV system. In this paper, an interharmonics suppression scheme with variable step size MPPT algorithm was proposed. In the suppression scheme, two voltage values near by the MPPT voltage and two tracking step size are preset. When the dc-link voltage of PV is between the two preset voltage values, it means that the PV power near its MPP and the smaller perturbation step size implemented in the MPPT algorithm. Otherwise, the bigger perturbation step size is employed. It can greatly reduce interharmonics emission level and maintain the MPPT efficiency. Simulations have been carried out to verify the effectiveness of the suppression scheme.

This paper focuses on the intelligent techniques used for tracking the maximum power point of the solar photovoltaic (SPV) system for varying environmental conditions. The most widely used perturb and observe (P&O) maximum power point tracking (MPPT) technique is discussed briefly for the comparison with the intelligent techniques. The paper proposes control technique for the SPV system by using fuzzy logic controller (FLC)-based MPPT algorithm and the optimisation of its various parameters by genetic algorithm (GA). The performance of the FLC optimised with GA is compared with the P&O and the fuzzy-based MPPT technique. MATLAB/simulink software is used to design the different stages of the MPPT controllers. Simulation results reported that GA optimised FLC perform much better than the P&O and fuzzy logic-based MPPT controllers.

Solar photovoltaic (PV) system contributes a significant role in meeting power requirements and helps the decentralization of power generation and distribution. The output of the individual photovoltaic module depends on local temperature and irradiance. Since the variation of these parameters depends on the environmental factors, it is difficult to obtain maximum power in all instances. The maximum power point tracking (MPPT) technique is used for tracking the maximum power available at a particular instant. This paper presents the maximum power extraction from a photovoltaic system using Artificial Intelligence (AI) techniques. AI based methods provide a fast dynamic response with high accuracy and mitigate the effects of partial shading. A comparative study is performed for various AI based MPPT techniques such as Fuzzy, Artificial Neural Network (ANN), and Adaptive Neuro Fuzzy Inference System (ANFIS). PV module output is interfaced with the resistive load through the Z-Source inverter (ZSI). The ZSI boost the input voltage and provides an AC output voltage. The AI based MPPT techniques have been investigated with conventional Z-source Inverter (ZSI) and Switched Inductor Z-Source inverter (SL-ZSI). A simple boost control technique is employed to control, both conventional and SL Z-source inverter. The performance of the system is verified using MATLAB Simulink.

Artificial neural networks (ANN) and evolutionary algorithms are two relatively young research areas that were subject to a steadily growing interest during the past years. This paper examines the use of different evolutionary algorithms, imperialist competitive algorithm (ICA), genetic algorithm (GA), ICA-GA and recursive ICA-GA (R-ICA-GA) to train a classification problem on a multi layer perceptron (MLP) neural network. All of named evolutionary training algorithms are compared together in this paper. The first goal of the paper is to apply new evolutionary optimization algorithms ICA-GA and R-ICA-GA for training the ANN and the second goal of the paper is to compare different evolutionary algorithms. It is shown that the ICA-GA has the best performance, in number of epochs, compared to the other algorithms. For this purpose, learning algorithms are applied on six known datasets (WINE, PIMA, WDBC, IRIS, SONAR and GLASS) which are used for classification problems.

A hybrid maximum power point tracking for partially shaded photovoltaic systems in the tropics

For problems involving uncertainties in design variables and parameters, a bi-objective evolutionary algorithm (EA) based approach to design optimization using evidence theory is proposed and implemented in this paper. In addition to a functional objective, a plausibility measure of failure of constraint satisfaction is minimized. Despite some interests in classical optimization literature, this is the first attempt to use evidence theory with an EA. Due to EA's flexibility in modifying its operators, nonrequirement of any gradient, its ability to handle multiple conflicting objectives, and ease of parallelization, evidence-based design optimization using an EA is promising. Results on a test problem and two engineering design problems show that the modified evolutionary multi-objective optimization algorithm is capable of finding a widely distributed trade-off frontier showing different optimal solutions corresponding to different levels of plausibility failure limits. Furthermore, a single-objective evidence-based EA is found to produce better optimal solutions than a previously reported classical optimization algorithm. Furthermore, the use of a graphical processing unit (GPU) based parallel computing platform demonstrates EA's performance enhancement around 160–700 times in implementing plausibility computations. Handling uncertainties of different types are getting increasingly popular in applied optimization studies and this EA based study is promising to be applied in real-world design optimization problems.

In this paper, a solar photovoltaic (PV) array powered scalar control of the induction motor (IM) drive for the water pumping application is presented. This control scheme involves the standalone operation of the IM drives. Solar PV array has nonlinear I- V characteristics, it requires additional control technique for Maximum Power Point (MPP) tracking. The efficiency is improved with the help MPP tracking (MPPT) technique which extracts maximum power available to the PV array. Perturb and observe (P&O) control technique offers simple control, ease of implementation and low cost is utilized along with DC/DC converter. This Stage extracts maximum power available from the PV array and fed power to the next stage of the DC/AC converter. The switching of DC/AC converter is generated with the help of open-loop V/F control of IM. The performance of the system is examined with the help of MATLAB/Simulink and corresponding results are present to support the suitability of the control scheme.

PV irrigation systems have begun to be used intensively today, as energy needs increase. In Partially Shaded Conditions (PSC), the efficiency of the PV system decreases significantly, and traditional Maximum Power Point Tracking (MPPT) algorithms become insufficient. On the other hand, traditional MPPT algorithms require sensors to measure the current and voltage of the PV system. In this study, a sensorless hybrid MPPT algorithm is proposed to reduce system costs and enable operation without the need for PV system data. A simulation study was conducted in the MATLAB/Simulink environment to examine the PV system. The proposed algorithm has been tested under four different PSC scenarios. PV system power, motor speed, and currents were examined under each condition. The high maximum power tracking performance of the proposed algorithm is demonstrated through simulation results. In the steady state, the lowest MPPT efficiency was 95.66%, whereas the highest MPPT efficiency was 99.9%. The MPPT algorithm completed in less than 2 seconds, with the first stage taking 1.3 seconds to reach most of the maximum PV system power. The second stage of the MPPT algorithm was used to achieve maximum power in a narrower area.

In recent decades, evolutionary optimisation algorithms have been used successfully for a wide variety of water resources engineering problems and their applications are still increasing. In this research work, a hybrid harmony search algorithm, ‘Non‐dominated Sorting Harmony Search’ algorithm is developed and compared with two state‐of‐the‐art multi‐objective evolutionary algorithms – the non‐dominated sorting genetic algorithm (NSGA)‐IIand multi‐objective particle swarm optimisation (MOPSO) algorithms – for assigning optimal rehabilitation plans for sewer pipe networks. The algorithms considered were validated using some standard test functions reported in the literature and compared with each other in terms of several metrics. These algorithms were then linked to theSWMM‐EPAhydraulic model and applied to a storm sewer pipe network case study in Seoul, South Korea, to obtain the best rehabilitation plans for pipe replacements. The results showed that the algorithms considered have different behaviours in solving the benchmark tests and rehabilitation problem. The proposed hybrid multi‐objective harmony search algorithm provides better optimal solutions in terms of different metrics and clearly outperforms the other two algorithms for the rehabilitation of the storm sewer pipe networks.

The escalating demands and increasing awareness for the environment, resulted in deployment of Photovoltaic (PV) system as a viable option. PV system are widely installed for numerous applications. However, the challenges in tracking the maximum power with intermittent atmospheric condition and varying load is significant. Maximum Power Point Tracking (MPPT) algorithms are employed and based on their convergence speed, control of external variations and oscillation, the output power efficiency, and other significant factors viz. the algorithm complexity and implementation cost, novel MPPT approach are preferable than the conventional approach. This paper presents an artificial intelligence-based optimization controller for MPPT in a PV system under varying load and irradiance conditions. Comparative analysis of Artificial Neural Network (ANN) and Particle Swarm Optimization (PSO) based MPPT is simulated and analysed. The PV system consisting of PV array and boost converter with MPPT controller feeds the DC load. The power conversion and panel efficiency are the significant factors to determine the effectiveness of tracking maximum power point. The simulation results show the performance of these controllers on the PV panel output power and the load side output power under changing loads and irradiance. In addition, the comparison of PV panel efficiency of ANN and PSO based MPPT techniques w.r.t changing loads is carried out. Based on the above analysis, PSO based MPPT algorithm marginally outperforms the ANN based MPPT algorithm. Further, the implementation of hybrid MPPT (ANN &PSO) for higher accuracy and tracking capability can be carried out as future work.

A maximum power point tracking (MPPT) DC/DC converter for a photovoltaic (PV) system is an important component in a PV system. The converter is used to convert the value of DC voltage produced by PV panels to a value accepted by the inverter for on-grid, or battery for off-grid system. In addition, the MPPT is used to extract and maintain the solar PV to its maximum power in all conditions. However, the values of components used in literature of MPPT DC/DC converter for a specific PV module cannot be applied for different capacity. Although sets of equations are given in literature to determine the values of inductor and capacitor used in the circuit, the calculated values do not produce the desired output in most cases because of unclear explanation. The validation of input parameters of the converter is also not properly presented for different solar irradiance and temperature. The efficiency of the converter is still low. Hence, this paper presents step-by-step process on how to design a MPPT DC/DC boost converter in MATLAB/Simulink environment. The incremental conductance method is used as MPPT algorithm to control the duty cycle of the converter. Then, a thorough analysis is done by simulating the developed model under different solar irradiance and temperature. Simulation results are then compared with the theoretical values from I-V and P-V curves of the selected PV modules. The results show that the proposed MPPT DC/DC converter is able to extract maximum power from PV modules and the output power produced by the converter also indicates that the converter has a high efficiency at 99.7% in all selected values of solar irradiance and temperature.

Energy crises and the growth of the energy demand have increased the interest in utilizing unconventional power sources. Thus, renewable energy sources have become a topic of interest to mitigate rising energy concerns and cope with increased electricity demand. With remarkable merits including cleanness and abundance, photovoltaic (PV) solar energy systems are a key to solving these issues. The employed inverters should effectively utilize the maximum available power from the PV solar system and transfer this power to the utility grid without posing any further limitations. However, the unequal power generation of different PV systems caused by partial shading (PS) and other PV panel degradation factors leads to a reduction in generation capacity. One of the relatively new solutions to mitigate the mismatch concerns between the PV modules and sub-modules is to extract the maximum power of each sub-module individually. The main objective of this paper is to present a comprehensive review of such PV grid-connected inverters topologies associated with sub-module connection and control. It will classify the PV grid-tied inverters in accordance with the level where the maximum power point tracking (MPPT) system is implemented. A special focus has been placed on sub-module microinverters (MI) in terms of circuit topologies, conversion efficiency, and controller design. This paper provides a comprehensive analysis of employing the distributed MPPT (DMPPT) approach to maximize the power generation of PV systems by mitigating the mismatch issues inside the PV module. The circuit topology, PV system configuration, and MPPT algorithms used for applying DMPPT solutions in PV SMs are discussed in detail in this study.

One of the main problems with a solar photovoltaic (PV) system is the partial shading condition (PSC).This results in a significant reduction of the output power of a solar PV system.This paper mainly aims at proposing and validating a novel optimization technique namely the Genetic Algorithm (GA) for Maximum Power Point Tracking (MPPT) in case of PSC.In this study, an experimental examination utilizing a PV emulator highlights the effect of PSC on PV system performance.PSC was found to result in a 37% decrease in maximum power, a 38% decrease in fill factor, and a 60% decrease in efficiency.Metaheuristic techniques for P-V curves with several peaks can be used to track the maximum power point (MPP).GA is based on a metaheuristic methodology that has been applied to solve optimization problems in a variety of systems, such as PV systems with MPPT.With a convergence time of less than 2 ms, the suggested system can track the global MPP with 99% tracking efficiency.This demonstrates the improvement in tracking time and accuracy over traditional MPPT techniques.Additionally, the suggested system can also accomplish steady operation in dynamically changing environmental conditions and reduce the oscillations around MPP.

"Photovoltaic panel maximum power point tracker". As the name implied, it is a photovoltaic system that uses the photovoltaic array as a source of electrical power supply and since every photovoltaic (PV) array has an optimum operating point, called the maximum power point, which varies depending on cell temperature, the insolation level and array voltage. A maximum power point tracker (MPPT) is needed to operate the PV array at its maximum power point. The objective of this paper is to build MPPT to charge a 12-volts lead acid battery by using a (TBP1275) 74 - watts PV panel. A technique for efficiency extracting the maximum output power from a solar panel under varying meteorological conditions is presented. The methodology is based on connecting a pulse width modulated dc/dc SEPIC converter, which is controlled by a micro controller based unit. The main difference between the method used in the proposed MPPT systems and other technique used in the past is that PV array output power is used to directly control the dc/dc converter thus reducing the complexity of the system. The resulting system has high efficiency, low cost and can be easily modified. This approach ensured maximum power transfer under all conditions by using micro controller for calculation. The tracking capability of the proposed technique has been verified experimentally with a 74 W solar panel at different insolation levels.