Coherent Load Profile Synthesis with Conditional Diffusion for LV Distribution Network Scenario Generation

TL;DR

This work tackles the scarcity of realistic, coherent LV substation load data by introducing a conditional diffusion framework (SSSDS4) to synthesize daily active and reactive power profiles governed by weather and calendar cues. By conditioning on substation metadata and incorporating reactive power, the model captures both temporal structure and cross-substation diversity, enabling coherent sub-regional scenarios. Evaluation against GMM and WGAN, plus a power-flow case study on the UKGDS network, shows that the LVGenWCS model most accurately reproduces distributions, tails, and network responses, supporting more reliable planning and operations under high distributed generation and low-carbon technology penetration. The results demonstrate practical utility for scenario generation in LV networks, with potential extensions to include richer LCT metadata and model explainability to bolster trust and deployment in real-world DNO/DSO workflows.

Abstract

Limited visibility of power distribution network power flows at the low voltage level presents challenges to both distribution network operators from a planning perspective and distribution system operators from a congestion management perspective. Forestalling these challenges through scenario analysis is confounded by the lack of realistic and coherent load data across representative distribution feeders. Load profiling approaches often rely on summarising demand through typical profiles, which oversimplifies the complexity of substation-level operations and limits their applicability in specific power system studies. Sampling methods, and more recently generative models, have attempted to address this through synthesising representative loads from historical exemplars; however, while these approaches can approximate load shapes to a convincing degree of fidelity, the co-behaviour between substations, which ultimately impacts higher voltage level network operation, is often overlooked. This limitation will become even more pronounced with the increasing integration of low-carbon technologies, as estimates of base loads fail to capture load diversity. To address this gap, a Conditional Diffusion model for synthesising daily active and reactive power profiles at the low voltage distribution substation level is proposed. The evaluation of fidelity is demonstrated through conventional metrics capturing temporal and statistical realism, as well as power flow modelling. The results show synthesised load profiles are plausible both independently and as a cohort in a wider power systems context. The Conditional Diffusion model is benchmarked against both naive and state-of-the-art models to demonstrate its effectiveness in producing realistic scenarios on which to base sub-regional power distribution network planning and operations.

Figures (14)

• Figure 1: Diagram outlining the forward and reverse process of the diffusion model, key variable names are provided with the diagrams.
• Figure 2: SSSDS4 Model implementation outlining model inputs, outputs and key layers/blocks.
• Figure 3: Diagram of the Residual Block within the SSSDS4 Model.
• Figure 4: Test Loss for each Model through epochs.
• Figure 5: Comparison of the distributions of Active and Reactive Power for different models and the real data. The detail shows how the upper tail behaviour is captured.