Accurate prediction of the generation capacity of photovoltaic systems is fundamental to ensuring the stability of the grid and to performing scheduling arrangements correctly. In view of the temporal defect and the local minimum problem of back-propagation neural network, a forecasting method of power generation based on long short-term memory-back-propagation is proposed. On this basis, the traditional prediction data set is improved. According to the three traditional methods listed in this article, we propose a fourth method to improve the traditional photovoltaic power station short-term power generation prediction. Compared with the traditional method, the long short-term memory-back-propagation neural network based on the improved data set has a lower prediction error. At the same time, a horizontal comparison with the multiple linear regression and the support vector machine shows that the long short-term memory-back-propagation method has several advantages. Based on the long short-term memory-back-propagation neural network, the short-term forecasting method proposed in this article for generating capacity of photovoltaic power stations will provide a basis for dispatching plan and optimizing operation of power grid.

Chaos theory has been widely utilized in password design, resulting in an encryption algorithm that exhibits strong security and high efficiency. However, rapid advancements in cryptanalysis technology have rendered single system generated sequences susceptible to tracking and simulation, compromising encryption algorithm security. To address this issue, we propose an image encryption algorithm based on hybrid heterogeneous time-delay chaotic systems. Our algorithm utilizes a collection of sequences generated by multiple heterogeneous time-delay chaotic systems, rather than sequences from a single chaotic system. Specifically, three sequences are randomly assigned to image pixel scrambling and diffusion operations. Furthermore, the time-delay chaotic system comprises multiple hyperchaotic systems with positive Lyapunov exponents, exhibiting a more complex dynamic behavior than non-delay chaotic systems. Our encryption algorithm is developed by a plurality of time-delay chaotic systems, thereby increasing the key space, enhancing security, and making the encrypted image more difficult to crack. Simulation experiment results verify that our algorithm exhibits superior encryption efficiency and security compared to other encryption algorithms.

In response to the critical challenges of securing multi-image transmissions in cloud and 5G/6G networks, this paper proposes an innovative encryption algorithm that synergistically combines hybrid chaotic maps with computer-generated holography (CGH). The authors introduce three groundbreaking contributions: (1) A novel integrated chaotic system (NICS) fusing logistic, sinus, and tent mappings through modular arithmetic to achieve full-range chaos with a $ 10^{84} $ key space and 40% higher Lyapunov exponents; (2) An enhanced Gerchberg Saxton algorithm incorporating adaptive feedback to accelerate convergence by 35% while enabling parallel encryption of eight $ 512\times512 $ images; (3) A dynamic secure hash algorithm 256 (SHA-256) bits based key binding mechanism that resists chosen plaintext attacks. Extensive experiments validate the exceptional performance metrics: Information entropy approaching the theoretical maximum (7.992±0.005), near-zero adjacent pixel correlation (< 0.004), and robust resistance to noise (20%) and cropping attacks (60% recovery at 60% loss). The algorithm's practical superiority is demonstrated through 2.3× faster processing speeds compared with conventional methods, along with successful deployments in medical imaging and military communication systems, establishing a new benchmark for secure multi-image transmission in next-generation networks.

Vehicle type recognition algorithms are broadly used in intelligent transportation, but the accuracy of the algorithms cannot meet the requirements of production application. For the high efficiency of the multilayer perceptive layer of Network in Network (NIN), the nonlinear features of local receptive field images can be extracted. Global average pooling (GAP) can avoid the network from overfitting, and small convolution kernel can decrease the dimensionality of the feature map, as well as downregulate the number of model training parameters. On that basis, the residual error is adopted to build a novel NIN model by altering the size and layout of the original convolution kernel of NIN. The feasibility of the algorithm is verified based on the Stanford Cars dataset. By properly setting weights and learning rates, the accuracy of the NIN model for vehicle type recognition reaches 97.2%.