High-precision short-term photovoltaic (PV) power prediction has become a critical technology in ensuring grid accommodation capacity, optimizing dispatching decisions, and enhancing plant economic benefits. This paper proposes a long short-term memory (LSTM)-based short-term PV power prediction method with the genetic algorithm (GA)-optimized adaptive fusion of space-based cloud imagery and ground-based meteorological data. The effective integration of satellite cloud imagery is conducted in the PV power prediction system, and the proposed method addresses the issues of low accuracy, poor robustness, and inadequate adaptation to complex weather associated with using a single type of meteorological data for PV power prediction. The multi-source heterogeneous data are preprocessed through outlier detection and missing value imputation. Spearman correlation analysis is employed to identify meteorological attributes highly correlated with PV power output. A dedicated dataset compatible with LSTM algorithm-based prediction models is constructed. An LSTM prediction model with a GA algorithm-based adaptive multi-source heterogeneous data fusion method is proposed, and the ability to construct a precise short-term PV power prediction model is demonstrated. Experimental results demonstrate that the proposed method outperforms single-source LSTM, single-source CNN-LSTM, and dual-source CNN-Transformer models in prediction accuracy, achieving an RMSE of 0.807 kWh and an MAPE of 6.74% on a critical test day. The proposed method enables real-time precision forecasting for grid dispatch centers and lightweight edge deployment at PV plants, enhancing renewable energy integration while effectively mitigating grid instability from power fluctuations.

To address the severe damage and outage risks to distribution networks caused by extreme weather, this paper proposes a coordinated optimization strategy for distribution network repair sequencing and rapid restoration, which considers multi-source collaboration and incomplete fault information. In response to the challenge of incomplete fault information after a disaster, a two-layer robust optimization model is constructed. The upper-layer model aims to minimize the completion time of repairs for all faults under the most unfavorable fault scenario to obtain a robust repair time for potential faulty lines, providing a reliable basis for the restoration decisions of the lower-layer model. The lower-layer model’s objective is to maximize the weighted restored load quantity by comprehensively coordinating mobile diesel generators (MDGs), distributed generators (DGs), photovoltaics (PVs), wind turbines (WTs), and energy storage systems (ESSs) to achieve the optimal restoration strategy. The proposed service restoration strategy is validated through simulation on a modified IEEE 33-bus power system, and the results demonstrate that the strategy can efficiently and comprehensively utilize multi-source collaborative resources and improve the resilience of the distribution network.

A vulnerability surface modeling method based on dual intensity metrics is proposed to assess the impact of typhoons and heavy rainfall disasters on the distribution pole-tower conductor system. A three-dimensional finite-element model is developed for a typical “three-pole four-conductor” distribution line, considering the uncertainties in both load-side and structural-side parameters. A spatially coherent turbulent wind field is generated using the Davenport spectrum and harmonic superposition method, while an equivalent rain load is derived based on raindrop spectrum integration. Nonlinear dynamic time-history analysis is then conducted under multiple combinations of basic wind speeds and rainfall intensities, extracting engineering demand parameters such as conductor axial tension and pole-base bending moments. Based on probabilistic demand analysis, the relationship between engineering demand parameters and dual intensity measures is regressed in the logarithmic domain to construct bivariate fragility surfaces for both the conductors and the poles. Critical failure curves are obtained by intersecting the fragility surfaces with the 10% exceedance probability level, enabling rapid classification of structural risk under the joint effects of wind and rain. The results show that the regression model provides a high fit, effectively revealing that wind speed is the dominant control factor, while rainfall intensity serves as a secondary amplifying factor. The resulting critical failure curves can be directly used as operation and maintenance warning thresholds and can be coupled with observed and forecast meteorological data for time-varying risk assessment. These findings provide methodological support and engineering guidance for risk assessment, operation and maintenance decision-making, and resilience enhancement of distribution networks under multi-hazard coupling.

Limited by the computational performance limits of the CPU(Central Processing Unit), the traditional Spark architecture struggles to achieve high throughput and low latency under the dual pressure of a large data scale and real-time requirements in centralized control systems. This work uses a publicly available CNC(Computer Numerical Control) milling dataset as a functional validation proxy for time-series data processing, then extends validation to a large-scale synthetic power transmission grid dataset. Furthermore, Spark-GPU(Graphics Processing Unit) collaboration suffers from load balancing failure due to heterogeneous resource scheduling and communication overhead, thus failing to unleash its performance potential. This paper proposes a Spark-GPU fusion acceleration technology path. The path consists of three key components: first, it integrates the RAPIDS accelerator; second, it designs a GPU-aware partitioning and task co-scheduling strategy; and third, it optimizes the zero-copy data path. Together, these components realize an integrated collaboration of heterogeneous resources. Validation on real-world datasets yields the following results. In real-time aggregation scenarios, the proposed solution improves throughput by a factor of 3.7 over the pure CPU baseline and reduces end-to-end latency by 62%. Compared with the basic GPU solution, GPU utilization rises from 51.7% to 72.3%, representing a relative improvement of 39.8%. Furthermore, the solution meets industrial-grade high availability requirements. This research significantly improves the processing throughput and reduces end-to-end latency in typical centralized control scenarios, thus providing a feasible technical route for demanding concurrent centralized control scenarios such as electric power industry manufacturing with high real-time demands.

In the context of achieving sustainable development goals and promoting a sustainable, low-carbon global energy transition, accurately quantifying and proactively managing the carbon intensity of power systems is a core challenge in monitoring the sustainability of the power sector. However, existing demand response methods often overlook the dynamic characteristics of power system carbon emissions and fail to accurately characterize the complex relationship between power consumption and carbon emissions, which results in suboptimal emission reduction results. To address this challenge, this paper proposes and validates an innovative low-carbon demand response optimization scheduling method as a sustainable tool. The core of this method is the development of a dynamic carbon emission factor (DCEF) assessment model. By innovatively integrating marginal and average carbon emission factors, it becomes a dynamic sustainability indicator that can measure the environmental performance of the power grid in real time. To characterize the relationship between power consumption behavior and carbon emissions, we employ an adaptive Dirichlet process mixture model (DPMM). This model does not require a preset number of clusters and can automatically discover patterns in the data, such as grouping holidays and working days with similar power consumption characteristics. Based on the clustering results and historical data, a dual long short-term memory (LSTM) deep learning network architecture is designed to achieve a coordinated prediction of power consumption and DCEFs for the next 24 h. On this basis, a method is established with the goal of maximizing carbon emission reduction while considering constraints such as fixed daily power consumption, user comfort, and equipment safety. Simulation results demonstrate that this approach can effectively reduce regional carbon emissions through accurate prediction and optimized scheduling. This provides not only a quantifiable technical path for improving the environmental sustainability of the power system but also decision-making support for the formulation of energy policies and incentive mechanisms that align with sustainable development goals.