Abstract: A deep learning-based method for fusing multi-source urban energy data and a storage medium are provided to perform data fusion on multi-source urban energy data found in big data and perform multi-scale and multimodal information fusion by using a cross-modal transformer, thereby implementing cross-modal mutual fusion of multi-source heterogeneous types of data to obtain a fused feature for prediction of a quantity of energy that will be used in the future and a quantity of energy that needs to be produced. The present disclosure proposes a multi-scale cooperative multimodal transformer architecture to enhance an effect of representation learned from an unaligned multimodal sequence. Not only there is a higher degree of correlation in multi-source urban energy data fusion, but also a system becomes more lightweight.

Abstract: According to a transformer-architecture-based method and system for IoT for and smart control of urban integrated energy, urban integrated energy IoT information acquired by a terminal from different areas is output to a server after being standardized into a sequence signal, where energy demand prediction is performed through learning of a deep learning network configured on the server, a smart control network is configured and built by using the deep learning network, real-time prediction processing is performed on the urban integrated energy IoT information acquired in real time, and a result is uploaded to a workstation for reviewing. Based on the transformer architecture, the deep learning network is combined with a fast Fourier transform algorithm and inverse transform on a sequence, and an FFT-Attention mechanism is proposed. Compared with a conventional transformer architecture, frequency domain information of a sequence is given more emphasis.

Abstract: A method for generating adversarial examples for a Graph Neural Network (GNN) model. The method includes: determining vulnerable features of target nodes in a graph based on querying the GNN model, wherein the graph comprising nodes including the target nodes and edges, each of the edges connecting two of the nodes; grouping the target nodes into a plurality of clusters according to the vulnerable features of the target nodes; and obtaining the adversarial examples based on the plurality of clusters.

Abstract: A construction method and system for asset value models in a digital twin engine includes: measuring the level of business importance based on a business model of building energy consumption assets, and constructing a first asset value model according to the business importance; establishing a correlation between the assets and productivity, and constructing a second asset value model according to productivity loss caused by the assets; and calculating the energy use efficiency of a building according to optimal decision variables, predicting the degradation index of the assets through the energy use efficiency, the first asset value model and the second asset value model, and generating a maintenance solution of the assets. The disclosed has ingenious conception and excellent effect, and realizes the accurate evaluation of the asset value by establishing the correlation between the assets and different businesses and different efficiency, generating the optimal and most accurate asset maintenance solution.

Abstract: An SVM-based secure access method for wireless terminals. Step 1, establish a wireless network security model based on the communication scenarios of the wireless terminal and the wireless base station; establish the channel feature vectors based on the wireless network security model and the frames received by the wireless base station; Step 2, use the pre-trained SVM model to examine the channel feature vectors of the frames, determining whether the frames are legitimate signals; Step 3, determine whether the wireless terminal with at least one frame sent is a legitimate terminal based on whether at least one of the frames sent is a legitimate signal. The frames sent by the wireless terminals that access the wireless base station are examined to effectively determine legitimate terminals by improving the SVM parameter combination optimization method of differential evolution and the differential evolution method with an adaptive improvement of the control parameters.

Abstract: An SVM-based secure access method for wireless terminals. Step 1, establish a wireless network security model based on the communication scenarios of the wireless terminal and the wireless base station; establish the channel feature vectors based on the wireless network security model and the frames received by the wireless base station; Step 2, use the pre-trained SVM model to examine the channel feature vectors of the frames, determining whether the frames are legitimate signals; Step 3, determine whether the wireless terminal with at least one frame sent is a legitimate terminal based on whether at least one of the frames sent is a legitimate signal. The frames sent by the wireless terminals that access the wireless base station are examined to effectively determine legitimate terminals by improving the SVM parameter combination optimization method of differential evolution and the differential evolution method with an adaptive improvement of the control parameters.

Abstract: A selection method for a strong wind region composite insulator based on a intrinsic frequency, and a composite insulator are provided. When a selection is made among a plurality of composite insulators according to the selection method, a intrinsic frequency of a composite insulator to be selected is measured first; if the composite insulator is an unequal-diameter umbrella, the intrinsic frequency of a large umbrella skirt in the composite insulator is measured; if the composite insulator is an equal-diameter umbrella, the intrinsic frequency of any umbrella skirt in the composite insulator is measured; and then a composite insulator is selected according to the intrinsic frequency, wherein the composite insulator whose intrinsic frequency is greater than or equal to 45 Hz is selected. The composite insulator is a composite insulator having corresponding structure parameters.

Abstract: A selection method for a strong wind region composite insulator based on structure parameters, and a composite insulator are disclosed. When a selection is made among a plurality of composite insulators according to the selection method, structure parameters of the composite insulators are measured first, and then the selection is made according to certain ranges of the parameters, a selected composite insulator is tested, and it is found that it may withstand strong wind climate environments where the highest wind speed reaches 50 m/s. The composite insulator is a composite insulator having corresponding structure parameters. The selection method is easy to operate and implement. When the composite insulator is applied to a strong wind region where the highest wind speed reaches 50 m/s, the problem of violent oscillation of umbrella skirts or tear of the umbrella skirts does not occur, and the composite insulator may still operate reliably.