To address the issues of fuzzy scene details, reduced definition, and poor visibility in images captured under non-uniform lighting conditions, this paper presents an algorithm for effectively enhancing such images. Firstly, an adaptive color balance method is employed to address the color differences in low-light images, ensuring a more uniform color distribution and yielding a low-light image with improved color consistency. Subsequently, the image obtained is transformed from the RGB space to the HSV space, wherein the multi-scale Gaussian function is utilized in conjunction with the Retinex theory to accurately extract the lighting components and reflection components. To further enhance the image quality, the lighting components are categorized into high-light areas and low-light areas based on their pixel mean values. The low-light areas undergo improvement through an enhanced adaptive gamma correction algorithm, while the high-light areas are enhanced using the Weber–Fechner law for optimal results. Then, each block area of the image is weighted and fused, leading to its conversion back to the RGB space. And a multi-scale detail enhancement algorithm is utilized to further enhance image details. Through comprehensive experiments comparing various methods based on subjective visual perception and objective quality metrics, the algorithm proposed in this paper convincingly demonstrates its ability to effectively enhance the brightness of non-uniformly illuminated areas. Moreover, the algorithm successfully retains details in high-light regions while minimizing the impact of non-uniform illumination on the overall image quality.

Arc droop presents significant challenges in power system management due to its inherent complexity and dynamic nature. To address these challenges in predicting arc sag for transmission lines, this paper proposes an innovative time–series prediction model, AROA-CNN-LSTM-Attention(AROA-CLA). The model aims to enhance arc sag prediction by integrating a convolutional neural network (CNN), a long short-term memory network (LSTM), and an attention mechanism, while also utilizing, for the first time, the adaptive rabbit optimization algorithm (AROA) for CLA parameter tuning. This combination improves both the prediction performance and the generalization capability of the model. By effectively leveraging historical data and exhibiting superior time–series processing capabilities, the AROA-CLA model demonstrates excellent prediction accuracy and stability across different time scales. Experimental results show that, compared to traditional and other modern optimization models, AROA-CLA achieves significant improvements in RMSE, MAE, MedAE, and R² metrics, particularly in reducing errors, accelerating convergence, and enhancing robustness. These findings confirm the effectiveness and applicability of the AROA-CLA model in arc droop prediction, offering novel approaches for transmission line monitoring and intelligent power system management.

In the future, the large-scale participation of renewable energy in electricity market bidding is an inevitable trend. In order to describe the Nash equilibrium effect and market power between renewable energy and traditional power generators in the tacit competition in the electricity market, a bidding strategy based on deep reinforcement learning is proposed. The strategy is divided into two layers; the inner layer is the electricity market clearing model, and the outer layer is the deep reinforcement learning optimization algorithm. Taking the equilibrium supply function as the clearing model of the electricity market, considering the green certificate trading mechanism and the carbon emission mechanism, and taking the maximization of social welfare as the objective function, the optimal bidding on the best electricity price is solved. Finally, the calculation examples of the 3-node system and the 30-node system show that compared with other algorithms, more stable convergence results can be obtained, the Nash equilibrium in game theory can be reached, social welfare can be maximized, renewable energy has more market power in the market. The market efficiency evaluation index is introduced to analyze the market efficiency of the two case systems. The final result is one of great significance and value to the reasonable electricity price declaration, the optimization of market resources, and the policy orientation of the electricity market with renewable energy.

Timely and accurate fault location in active distribution networks is of vital importance to ensure the reliability of power grid operation. However, existing intelligent algorithms applied in fault location of active distribution networks possess slow convergence speed and low accuracy, hindering the construction of new power systems. In this paper, a new regional fault localization method based on an improved northern goshawk search algorithm is proposed. The population quality of the samples was improved by using the chaotic initialization strategy. Meanwhile, the positive cosine strategy and adaptive Gaussian–Cauchy hybrid variational perturbation strategy were introduced to the northern goshawk search algorithm, which adopted the perturbation operation to interfere with the individuals to increase the diversity of the population, contributing to jumping out of the local optimum to strengthen the ability of local escape. Finally, simulation verification was carried out in a multi-branch distribution network containing distributed power sources. Compared with the traditional regional localization models, the new method proposed possesses faster convergence speed and higher location accuracy under different fault locations and different distortion points.

Under the “carbon peak and carbon neutrality” goal, the construction of an efficient, low-carbon, and economical energy supply system is of great significance for advancing a dual carbon strategy. In allusion to the integrated energy systems (IES) with hydrogen energy coupling, a hydrogen energy coupling IES low-carbon optimization operation strategy that took account of green certificate and ladder-type carbon joint trading and dual-incentive demand response was proposed in this paper. First, a hydrogen energy multiuse system composed of an electrolyzer, a hydrogen fuel cell, a methane reactor, and hydrogen energy storage was constructed to make full use of the low-carbon cleaning characteristics of hydrogen energy. Besides, a combined model of hydrogen mixed with natural gas was established to improve the utilization efficiency of hydrogen energy. Second, a dual-incentive demand response model including price incentives and subsidy incentives was constructed to fully use the ability to adjust demand-side resources. Next, in view of the carbon emission reduction mechanism of the green certificate, a green certificate and ladder-type carbon joint trading mechanism was constructed. In addition, a green certificate trading mechanism and a reward and punishment tiered carbon trading mechanism had been introduced separately in the IES optimization operation model to reduce carbon emissions of the system. The calculation simulation sets up different scenarios for comparative analysis. As shown by the results, the proposed model could effectively improve renewable energy consumption capacity and energy utilization efficiency. The effectiveness of hydrogen energy utilization, demand respond, and green certification carbon trading mechanism in improving system economy and low-carbon efficiency is verified.

The Harris corner detection algorithm is widely applied in image mosaic, which is simple and stable. However, the algorithm has a disadvantage that it obtains a lot of false corners when there exist some noise in an image. An improved Harris corner detection algorithm is proposed in this paper. The new algorithm reduces the noise impact greatly. The experimental results show that the improved algorithm not only reduces false corner points greatly, but also retain the majority of true corners. As a result, it improves the detection accuracy and reduces the chance of error matching in image registration.