Given that the power load data are stochastic and it is difficult to obtain accurate forecasting results by a single algorithm. In this study, a combined forecasting method for short-term power load was proposed based on the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), Multiverse optimization algorithm (MVO), and the Gated Recurrent Unit (GRU) based on Rectified Adam (RAdam) optimizer. Firstly, the model uses the CEEMDAN algorithm to decompose the original electric load data into subsequences of different frequencies, and the dominant factors are extracted from the subsequences. Then, a GRU network based on the RAdam optimizer was built to perform the forecasting of the subsequences using the existing subsequences data and the associated influencing factors as the data set. Meanwhile, the parameters of the GRU network were optimized with the MVO optimization algorithm for the prediction problems of different subsequences. Finally, the prediction results of each subsequence were superimposed to obtain the final prediction results. The proposed combined prediction method was implemented in a case study of a substation in Weinan, China, and the prediction accuracy was compared with the traditional prediction method. The prediction accuracy index shows that the Root Mean Square Error of the prediction results of the proposed model is 80.18% lower than that of the traditional method, and the prediction accuracy error is controlled within 2%, indicating that the proposed model is better than the traditional method. This will have a favorable impact on the safe and stable operation of the power grid.

The integration of renewable energy sources and distributed energy storage systems increasingly complicates the operation of distribution networks, while stringent carbon reduction targets demand low-carbon operational strategies. To address these complexities, this paper introduces a two-stage model for reconfiguring distribution networks and ensuring low-carbon dispatch. Initially, second-order cone programming is employed to minimize losses in the network. Subsequently, the outputs of renewable energy and energy storage systems are optimized using the mantis search algorithm (MSA) to achieve low-carbon dispatch, with the network’s carbon potential as the evaluation metric. The proposed model demonstrates a significant reduction in average active power loss by 34.85%, a decrease in daily carbon emissions by 509.97 kg, and a reduction in carbon emission costs by 17.24%, thereby markedly enhancing the economic and social benefits of grid operations.