What the study found: Conditional diffusion models can generate plausible daily active and reactive power profiles for low-voltage distribution substations. The synthesised load profiles were described as plausible both on their own and as part of a wider power systems cohort.
Why the authors say this matters: The study suggests that more representative load profiles are needed for meaningful analysis of low-voltage substations, because limited visibility at this level can affect planning and congestion management. The authors conclude that realistic synthetic scenarios can support sub-regional power distribution network planning and operations.
What the researchers tested: The researchers proposed conditional diffusion models for synthesising daily active and reactive power profiles at the low-voltage distribution substation level. They evaluated fidelity using conventional metrics for temporal and statistical realism, along with power flow modelling, and tested multiple model settings ranging from unconditional synthesis to informed generation using metadata and daily statistics.
What worked and what didn't: The results show that the synthesised load profiles were plausible in both individual form and as part of a cohort in a power systems context. The Conditional Diffusion model was benchmarked against naive and commonly used generative models, and the abstract says it demonstrated effectiveness in producing realistic scenarios. The abstract does not state specific failures or cases where the approach did not work.
What to keep in mind: The abstract does not provide detailed numerical results, and it does not describe specific limitations beyond the general issue of limited low-voltage visibility and simplified traditional profiles. It also does not list any particular data constraints or failure modes for the proposed models.
Key points
- Conditional diffusion models were used to synthesize daily active and reactive power profiles for low-voltage substations.
- The synthesised load profiles were described as plausible individually and as a cohort in a wider power systems context.
- The study used temporal and statistical realism metrics, plus power flow modelling, to evaluate fidelity.
- The model was benchmarked against naive and commonly used generative models.
- The abstract says the approach can support sub-regional power distribution network planning and operations.
Disclosure
- Research title:
- Conditional diffusion synthesizes plausible low-voltage load profiles
- Authors:
- Alistair Brash, Junyi Lu, Bruce Stephen, Blair Brown, Robert Atkinson, Craig Michie, Fraser MacIntyre, Christos Tachtatzis
- Institutions:
- National Health Service Scotland, University of Strathclyde, Scottish and Southern Energy (United Kingdom)
- Publication date:
- 2026-04-20
- OpenAlex record:
- View
Get the weekly research newsletter
Stay current with peer-reviewed research without reading academic papers — one filtered digest, every Friday.

