The fast growth of photovoltaic (PV) power generation raises the concern of grid instability due to its intermittent nature. Solar irradiance forecasting is becoming an effective way to support the power ramp rate control, mitigate power intermittency, and improve grid resilience. However, most previous research focuses on the predictor applied to the central PV farm but fails to fit the distributed PV system well. This article proposes a novel deep learning architecture, namely, group solar irradiance neural network, used for solar irradiance forecasting. The strategy adopts a convolutional graph neural network to mine distributed PVs’ graphs and identify the critical features. Meanwhile, the scheme includes a long-short-term memory recurrent neural network to capture the temporal correlations. The proposed solution shows an improved universality for model training and results in accurate and reliable predictions compared to other solutions. Furthermore, the learning architecture can be applied to the master–slave deployment scheme to reduce overall system cost. The proposed algorithm is tested with the data sourced from the U.S. National Renewable Energy Laboratory. The evaluation demonstrates the highest accuracy and best fitting for solar irradiance forecasting in comparison with other prediction methods.

Maximum power point tracking (MPPT) is essential in Photovoltaic (PV) systems, which has drawn significant research effort in the past. The operation is to adjust the power interfaces so that the operating characteristics of the consumption and the PV generator match at the ideal level in term of generation. A comprehensive review is essential to help readers understand the latest developments and inform research directions. Unlike the other review papers, this paper focuses on the operational principles of MPPT methods. Therefore, a different review angle is presented in this paper to provide a clear image of the technology of MPPT.

Dynamic performance of maximum power point tracking (MPPT) algorithms is important to ensure high power yield under practical operating conditions. In this paper, after reviewing three dynamic test procedures, including stepped oper- ation procedure, day-by-day operation procedure, and EN50530 dynamic test procedure, three typical MPPT algorithms such as the fixed-step-size perturb and observe (P&O), variable-step- size incremental conductance (VSSINC), and hybrid-step-size Beta method are evaluated experimentally under the EN 50530 dynamic test procedure. Two dynamic EN50530 test sequences are adopted for the performance evaluation to cover different irradiance changing conditions. The PV model for EN50530 dynamic test sequences is built and the effects of wrong-step changes by using three MPPT algorithms are analyzed systemat- ically. The experimental comparison of three MPPT algorithms in terms of the tracking routines, accumulated energy, and tracking efficiency is presented. The research shows that the 0.5% fixed- step-size P&O may fail to track the MPP due to the tracking drift while the beta algorithm exhibits the highest tracking efficiency under both dynamic sequences. The average tracking efficiency improvement of the beta algorithm compared with other two algorithms are experimentally measured as 24.2% and 18.8% respectively.

When the photovoltaic (PV) string is under the partial shading condition (PSC), the conventional maximum power point tracking (MPPT) techniques may fail to track the global maximum power point (GMPP). Although some global MPPT (GMPPT) techniques have been proposed, they may overlook the GMPP and fail to detect the PSC occurrence. Therefore, a novel GMPPT technique is proposed in this paper by modifying the conventional beta method. The proposed technique is more accurate than the previous techniques since it can guarantee that all the peaks in the β range and never overlook the GMPP. Furthermore, the proposed technique can inherently detect the PSC occurrence without setting any additional threshold parameters or periodical interruption, which is simpler and more effective. In order to verify the advantages of the proposed technique, a prototype with buck-boost converter was constructed. For a fair comparison, two popular GMPPT techniques were also implemented and tested in the same prototype under various scenarios. The performance improvement with the proposed technique for different PSCs has been validated by both simulation and experimental results.

Maximum power point tracking (MPPT) is essential for photovoltaic (PV) systems to ensure the highest power output of PV arrays under any environmental condition. Comparing to other techniques, the Beta method shows advantages in terms of tracking speed, steady-state performance, and simple implementation. However, the conventional Beta can further be improved by minimizing oscillations around the maximum power point under a steady state and an increasing tracking speed in response to rapid changing of irradiance or temperature. An improved Beta-parameter-based MPPT method is proposed in this paper to achieve the above-mentioned objectives. An adaptive scaling factor is introduced and utilized in the MPPT mechanism, which enhances the tracking speed and is easily applied for any PV power system. Furthermore, the proposed method can identify and maintain the middle point of the three-level perturbations, which eliminate the oscillations at a steady state. The control mechanism is not limited by specific operating conditions and illustrates superior performance over traditional methods with regards to transient response and steady-state performance, which contributes to effective solar power harvesting. Followed by theoretical analysis, the simulation and experimental evaluation validate the claimed advantages of the proposed MPPT solution.