Accurate short-term electric load forecasting is significant for the smart grid. It can reduce electric power consumption and ensure the balance between power supply and demand. In this paper, the Stacked Denoising Auto-Encoder (SDAE) is adopted for short-term load forecasting using four factors: historical loads, somatosensory temperature, relative humidity, and daily average loads. The daily average loads act as the baseline in final forecasting tasks. Firstly, the Denoising Auto-Encoder (DAE) is pre-trained. In the symmetric DAE, there are three layers: the input layer, the hidden layer, and the output layer where the hidden layer is the symmetric axis. The input layer and the hidden layer construct the encoding part while the hidden layer and the output layer construct the decoding part. After that, all DAEs are stacked together for fine-tuning. In addition, in the encoding part of each DAE, the weight values and hidden layer values are combined with the original input layer values to establish an SDAE network for load forecasting. Compared with the traditional Back Propagation (BP) neural network and Auto-Encoder, the prediction error decreases from 3.66% and 6.16% to 2.88%. Therefore, the SDAE-based model performs well compared with traditional methods as a new method for short-term electric load forecasting in Chinese cities.

With the rapid popularization of intelligent terminals and the explosive growth of wireless communication service demand, future mobile communication technology will face many challenges. Non-orthogonal multiple access (NOMA) technology for 5G can provide many connections and effectively improve the frequency spectrum and energy efficiency compared to traditional orthogonal multiple access technologies. Therefore, in recent years, NOMA technology has become one of the research hotspots of numerous scholars. However, the resource allocation problem in the NOMA system, as a high-dimensional nonlinear programming problem, has not been well studied. In addition, the particle swarm optimization algorithm can also effectively find the optimal solution for complex and constrained problems. Still, at the same time, it is easy to fall into local optimal defects. In this context, we decouple the high-dimensional nonlinear programming problem to maximize system energy efficiency into sub-problems: subchannel and power allocation. Firstly, a low-complexity greedy algorithm based on the principle of worst-case subchannel priority matching is proposed to solve the subchannel assignment problem. In addition, we further apply the modified particle swarm optimization algorithm to allocate power to the NOMA downlink system, aiming to improve the energy efficiency of the communication system as much as possible under the premise of ensuring the quality of service (QoS). Simulation results show that our proposed scheme has low complexity and can significantly improve the energy efficiency of the NOMA system and achieve better user fairness.

Person re-identification is essential to intelligent video analytics, whose results affect downstream tasks such as behavior and event analysis. However, most existing models only consider the accuracy, rather than the computational complexity, which is also an aspect to consider in practical deployment. We note that self-attention is a powerful technique for representation learning. It can work with convolution to learn more discriminative feature representations for re-identification. We propose an improved multi-scale feature learning structure, DM-OSNet, with better performance than the original OSNet. Our DM-OSNet replaces the $9\times 9$ convolutional stream in OSNet with multi-head self-attention. To maintain model efficiency, we use double-layer multi-head self-attention to reduce the computational complexity of the original multi-head self-attention. The computational complexity is reduced from the original $O\left({(H\times W)}^2\right)$ to $O(H\times W\times G^2)$. To further improve the model performance, we use SpCL to perform unsupervised pre-training on the large-scale unlabeled pedestrian dataset LUPerson. Finally, our DM-OSNet achieves an mAP of 87.36%, 78.26%, 72.96%, and 57.13% on the Market1501, DukeMTMC-reID, CUHK03, and MSMT17 datasets.

With the increasing application of CHP and an industry transition to distributed energy, it is necessary to make a comprehensive economic analysis and comparison of the entire lifetime of CHP from the net present value (NPV), payback period, and cost-saving ratio (CSR). Five systems, including micro-CHP, gas boiler (GB), air-source heat pump (ASHP), domestic gas-fired heater and domestic electric hot water-heater, are simulated. First, this paper takes annual heat use efficiency (AHUE) into account to compare the economy of each domestic hot water (DHW) system. The results show that a domestic gas-fired heater system is the most economical option in the AHUE of 31.28%. The economic influence of CHP and gas-fired heater under different AHUE are then analyzed. The results show that the DHW system based on CHP is the best when the AHUE is more than 55.35%. Finally, three different operation strategies of CHP are considered in this paper. From the perspective of annual energy cost and payback, the internal combustion-based CHP with thermal energy system (TES) is superior to the other two strategies being studied. Considering the optimal economic benefits, the CSR of the three different operation strategies is 41.3%, 69.69% and 69.77%, respectively.

In this paper, RGB image sensors based on visible light communication system are designed and researched. In our study, the spatial inter-symbol interference is considered and the formation mechanism of the stray light, the influence of the spatial inter-symbol interference, and the influence of RGB image sensors are analyzed. The mathematics expression of the system signal-to-noise ratio (SNR) and bit error ratio (BER) is given. The simulation result indicates that there is a critical communication distance in the system. Once the communication distance exceeds the critical value, the system BER performance increases sharply. In addition, an adaptive threshold detection method is introduced and the performance is simulated. By means of estimating the spatial inter-symbol interference noise power, the optimal detection threshold can be obtained and the system BER performance increases significantly.