The rapid development in wind power comes with new technical challenges. Reliable and accurate wind power forecast is of considerable significance to the electricity system’s daily dispatching and production. Traditional forecast methods usually utilize wind speed and turbine parameters as the model inputs. However, they are not sufficient to account for complex weather variability and the various wind turbine features in the real world. Inspired by the excellent performance of convolutional neural networks (CNN) in computer vision, we propose a novel approach to predicting short-term wind power by converting time series into images and exploit a CNN to analyze them. In our approach, we first propose two transformation methods to map wind speed and precipitation data time series into image matrices. After integrating multi-dimensional information and extracting features, we design a novel CNN framework to forecast 24-h wind turbine power. Our method is implemented on the Keras deep learning platform and tested on 10 sets of 3-year wind turbine data from Hangzhou, China. The superior performance of the proposed method is demonstrated through comparisons using state-of-the-art techniques in wind turbine power forecasting.

Large power transformer is one of the most important equipment in power system, while conventional methods of transformer vibration anomaly detection are inaccurate and complex. Based on the fast‐growing Internet of Energy (IoE), we put forward an improved transformer anomaly detection method that makes contributions in following ways: we first propose a new anomaly detection algorithm that combines time‐frequency domain analysis and artificial intelligence technology. Compared with the conventional modeling analysis, our method is simpler, more effective, and more adaptable. Then, we design a software‐hardware collaboration architecture and implement the algorithm on Xilinx Zynq‐7000 System on Chip (SoC) XC7Z010 development board, showing high accuracy of 98.12%. Finally, we apply the whole system to IoE environment.

Routing and Wavelength Assignment (RSA) is an important problem in optical transmission networks, it is responsible for allocating resources and establishing the light path. After the RSA algorithm is executed, various parameters can be evaluated in the network and the algorithm is suitable to evaluate optical network performance. However, traditional RWA algorithms generally only focus on parameters such as blocking rate and spectrum utilization and do not takes other network conditions such as network load into account. To solve the problem, we propose Multi-Dimensional Performance Indicators based Routing and Wavelength Assignment (MDPIRWA) algorithm for Optical Transmission Networks, the link-level is seen as an indicator in the routing process. In addition to calculating network blocking rate, service and load balancing are also considered in our algorithm. Simulation results show that MDPI-RWA reflects network performance more comprehensively, especially in high-security requirements scenes.