Sort:
Open Access Issue
Optimization Scheduling Strategy for Interconnected Energy Storage Vehicles in Agricultural Grid Power Supply Risk Control
Distributed Energy 2026, 11(5): 85-97
Published: 25 October 2026
Abstract PDF (1.1 MB) Collect
Downloads:0

Aiming at the problem of large load shedding caused by insufficient power supply capacity of rural distribution stations due to the superposition of photovoltaic output fluctuation and centralized operation of seasonal agricultural loads in rural distribution networks with high photovoltaic penetration, this paper proposes an optimal scheduling strategy for interconnected energy storage vehicles (IESV) oriented to power supply risk control in agricultural distribution networks. The system architecture of a rural distribution network based on IESV is constructed, and the mathematical model of IESV is established. The significant spatio-temporal fluctuation characteristics of agricultural loads are described, and on this basis, a two-stage scheduling strategy including pre-layout and dynamic dispatch is proposed. In the pre-layout stage, based on typical scenarios before the busy farming period, with the objectives of minimizing the configuration cost and load rate deviation penalty, the interconnected distribution station pairs are determined to reserve operation margin for the load peak during the busy farming period. On this basis, the dynamic dispatch stage is proposed to further cope with load fluctuations. Based on the topology formed by pre-layout, this stage optimizes the access locations and discharge power of IESV with the objective of minimizing the load shedding power. The two stages cooperate under the sequential optimization framework of "planning-operation" to realize the comprehensive optimization of operation cost and load shedding. Finally, the simulation based on the IEEE 33-node system verifies that the proposed strategy can significantly reduce agricultural load shedding and the total system operation cost while controlling the power supply risk of agricultural distribution networks.

Open Access Issue
A Convolutional Autoencoder-Based Approach for Feature Extraction and Label Optimization of Typical Loads in Distribution Networks
Distributed Energy 2026, 11(1): 54-62
Published: 25 February 2026
Abstract PDF (1.7 MB) Collect
Downloads:1

Extracting the latent value embedded in electricity load data constitutes one of the key challenges in the power industry. To address the difficulty faced by conventional clustering approaches in capturing the intrinsic features of high-dimensional load data, this paper proposes an optimized clustering method based on a one-dimensional convolutional autoencoder (1D-CAE). First, a 1D-CAE is employed to extract temporal features from daily customer load profiles through nonlinear dimensionality reduction, with the objective of minimizing reconstruction loss. Second, we introduce an improved Cayley orthogonal constraint to enhance the structural information of the clustering space, thereby optimizing the mapping of latent features and improving clustering stability. Third, a generative adversarial network (GAN) is integrated with K-means clustering to refine the cluster centers and fine-tune the encoder. Finally, the effectiveness of the proposed method is evaluated on real-world load datasets using three widely accepted internal validation metrics: the Davies–Bouldin index (DBI), the Calinski–Harabasz index (CHI), and the silhouette coefficient (SC). Experimental results demonstrate that the proposed approach significantly enhances both inter-cluster separability and intra-cluster compactness. The study confirms that the method can effectively identify and extract morphological characteristics of diverse load profiles, offering robust support for demand response and optimal dispatch in virtual power plants.

Total 2