The existing techniques for detecting defects in photovoltaic (PV) components have some drawbacks, such as few samples, low detection accuracy, and poor real-time performance. This paper presents a cloud-edge collaborative technique for detecting the defects in PV components, based on transfer learning. The proposed cloud model is based on the YOLO v3-tiny algorithm. To increase the detection effect of small targets, we produced a third prediction layer by fusing the shallow feature information with the stitching layer in the second detection scale and introducing a residual module to achieve improvement of the YOLO v3-tiny algorithm. In order to further increase the ability of the network model to extract target features, the residual module was introduced in the YOLO v3-tiny backbone network to increase network depth and learning ability. Finally, through the model’s transfer learning and edge collaboration, the adaptability of the defect-detection algorithm to personalized applications and real-time defect detection was enhanced. The experimental results showed that the average accuracy and recall rates of the improved YOLO v3-tiny for detecting defects in PV components were 95.5% and 93.7%, respectively. The time-consumption of single panoramic image detection is 6.3 ms, whereas the consumption of the model’s memory is 64 MB. After cloud-edge learning migration, the training time for a local sample model was improved by 66%, and the accuracy reached 99.78%.

Existing photovoltaic (PV) power prediction methods suffer from insufficient data samples, poor model generalization ability, and the inability to share power data. In this paper, a hybrid prediction model based on federated learning (FL) is proposed. To improve communication efficiency and model generalization ability, FL is introduced to combine data from multiple locations without sharing to collaboratively train the prediction model. Furthermore, a hybrid LSTM-BPNN prediction model is designed to improve the accuracy of predictions. LSTM is used to extract important features from the time-series data, and BPNN maps the extracted high-dimensional features to the low-dimensional space and outputs the predicted values. Experiments show that the minimum MAPE of the hybrid prediction model constructed in this paper can reach 1.2%, and the prediction effect is improved by 30% compared with the traditional model. Under the FL mode, the trained prediction model not only improves the prediction accuracy by more than 20% but also has excellent generalization ability in multiple scenarios.

With the increasing marketization of electricity, residential users are gradually participating in various businesses of power utility companies, and there are more and more interactive adjustments between load, source, and grid. However, the participation of large-scale users has also brought challenges to the grid companies in carrying out demand-side dispatching work. The user load response is uneven, and users’ behavioral characteristics are highly differentiated. It is necessary to consider the differences in users’ electricity consumption demand in the design of the peak–valley load time-sharing incentives, and to adopt a more flexible incentive form. In this context, this paper first establishes a comprehensive clustering method integrating k-means and self-organizing networks (SONs) for the two-step clustering and a BP neural network for reverse adjustment and correction. Then, a time-varying incentive optimization for interactive demand response based on two-step clustering is introduced. Furthermore, based on the different clustering results of customers, the peak–valley load time-sharing incentives are formulated. The proposed method is validated through case studies, where the results indicate that our method can effectively improve the users’ load characteristics and reduce the users’ electricity costs compared to the existing methods.

With the gradual deepening of power-related research and the expansion of power data volume, power data-oriented research and applications have fully entered the era of big data and cloud storage. The huge amount of heterogeneous data samples also bring a huge impact on traditional data processing methods. Therefore, let each virtual power plant participate in the electricity market externally as a unified power plant, and build a blockchain structure of multiple virtual power plants in the form of a slice. The structured data such as the basic information of the account is stored in the enterprise database in a relational data model and managed through an identity verification policy. The mechanism of off-chain negotiation and on-chain settlement is used to manage the transaction data. The management mechanism is further improved by combining an encryption scheme and a security evaluation method. After the practical test of the management mechanism, the time consumed for one and two parallel operations reaches 23 seconds and 8 seconds, and 4 seconds and 9 seconds or less for three and four times, respectively. In the case of nine users’ data distortion, the root means the square value of the blockchain data management mechanism is only 0.82, which is significantly less than 1. It shows that the blockchain-based data management mechanism, as a new generation of power data management means, can not only effectively integrate the power grid information data and relieve the pressure of the power grid system, but also avoid data leakage and strengthen power security.