The efficient condition monitoring and accurate module defect detection in large-scale photovoltaic (PV) farms demand for novel inspection method and analysis tools. This paper presents a deep learning based solution for defect pattern recognition by the use of aerial images obtained from unmanned aerial vehicles (UAVs). The convolutional neural network (CNN) is used in the machine learning process to classify various forms of module defects. Such supervised learning process can extract a range of deep features of operating PV modules. It significantly improves the efficiency and accuracy of asset inspection and health assessment for large-scale PV farms in comparison with the conventional solutions. The proposed algorithmic solution is extensively evaluated from different aspects, and the numerical result clearly demonstrates its effectiveness for efficient defect detection of PV modules.

Condition monitoring and fault diagnosis of photovoltaic modules are essential to ensure the efficient and reliable operation of large-scale photovoltaic plants. This article presents an algorithmic solution for the rapid and sensitive detection of photovoltaic modules with multiple visible defects by an image analyzing apparatus mounted onto an unmanned aerial vehicle. The proposed solution is composed of three stages to efficiently and accurately analyze various forms of module defects. First, the Kirsch operator is employed to identify the anomalous regions, which can significantly reduce the computational complexity, and error rate. Afterward, a deep convolutional neural network is adopted to extract defect features. Finally, a multiple classification support vector machine is developed to facilitate the defects detection decision-making. The proposed solution is extensively evaluated by the comprehensive dataset collected from real-world solar photovoltaic plants. The experimental results clearly demonstrate the effectiveness of our solution for photovoltaic modules diagnosis with multiple visible defects.

Recently, the increasing integration of electric vehicles (EVs) has drawn great interest due to its flexible utilization; moreover, environmental concerns have caused an increase in the application of combined heat and power (CHP) units in multi-energy systems (MES). This paper develops an approach to coordinated scheduling of MES considering CHPs, uncertain EVs and battery degradation based on model predictive control (MPC), aimed at achieving the most economic energy scheduling. After exploiting the pattern of the drivers’ commuting behavior, the stochastic characteristics of available charging/discharging electric power of aggregated EVs in office or residential buildings are analyzed and represented by the scenarios with the help of scenario generation and reduction techniques. At each step of MPC optimization, the solution of a finite-horizon optimal control is achieved in which a suitable number of available EVs scenarios is considered, while the economic objective and operational constraints are included. The simulation results obtained are encouraging and indicate both the feasibility and the effectiveness of the proposed approach.

Defects detection with Electroluminescence (EL) image for photovoltaic (PV) module has become a standard test procedure during the process of production, installation, and operation of solar modules. There are some typical defects types, such as crack, finger interruption, that can be recognized with high accuracy. However, due to the complexity of EL images and the limitation of the dataset, it is hard to label all types of defects during the inspection process. The unknown or unlabeled create significant difficulties in the practical application of the automatic defects detection technique. To address the problem, we proposed an evolutionary algorithm combined with traditional image processing technology, deep learning, transfer learning, and deep clustering, which can recognize the unknown or unlabeled in the original dataset defects automatically along with the increasing of the dataset size. Specifically, we first propose a deep learning-based features extractor and defects classifier. Then, the unlabeled defects can be classified by the deep clustering algorithm and stored separately to update the original database without human intervention. When the number of unknown images reaches the preset values, transfer learning is introduced to train the classifier with the updated database. The fine-tuned model can detect new defects with high accuracy. Finally, numerical results confirm that the proposed solution can carry out efficient and accurate defect detection automatically using electroluminescence images.

Multi-objective robust state-feedback controller synthesis problems for linear discrete-time uncertain systems are addressed. Based on parameter-dependent Lyapunov functions, the G_l2 and GH₂ norm expressed in terms of LMI (Linear Matrix Inequality) characterizations are further generalized to cope with the robust analysis for convex polytopic uncertain system. Robust state-feedback controller synthesis conditions are also derived for this class of uncertain systems. Using the above results, multi-objective state-feedback controller synthesis procedures which involve the LMI optimization technique are developed and less conservative than the existing one. An illustrative example verified the validity of the approach.

In this paper, an adaptively constrained stochastic model predictive control (MPC) is proposed to achieve less-conservative coordination between energy storage units and uncertain renewable energy sources (RESs) in a microgrid (MG). Besides the economic objective of MG operation, the limits of state-of-charge (SOC) and discharging/charging power of the energy storage unit are formulated as chance constraints when accommodating uncertainties of RESs, considering mild violations of these constraints are allowed during long-term operation, and a closed-loop online update strategy is performed to adaptively tighten or relax constraints according to the actual deviation probability of violation level from the desired one as well as the current change rate of deviation probability. Numerical studies show that the proposed adaptively constrained stochastic MPC for MG optimal operation is much less conservative compared with the scenario optimization based robust MPC, and also presents a better convergence performance to the desired constraint violation level than other online update strategies.