Uncertainty Quantification in Load Forecasting for Smart Grids Using Non-Parametric Statistics
Bibliographic record
Abstract
In flexibility markets, aggregators serve as crucial intermediaries by consolidating and selling consumer flexibility to grid operators or distribution system operators (DSOs). They are essential for grid management, offering load reductions based on power limits, and estimating expected consumer load in demand response scenarios. However, the inherent uncertainty in consumer behaviour poses a significant challenge, leading to deviations between projected and actual power consumption. In this context, this paper proposes a methodology for quantifying forecast uncertainties in power profiles at the aggregator level. The proposed methodology introduces a model-based approach to provide a more comprehensive representation of uncertainty and investigation of load variations. It provides load forecast values as comprehensive distributions, which are then sampled to generate newly sampled data from which the probability density function is extracted to quantify uncertainty, expressed by confidence intervals around the expected output. This approach aids in identifying the flexibility requirements for aggregated household power consumption, assists in quantifying uncertainties, and determines the flexibility needed for accurate forecasts of such consumption, which is essential for informed decision-making. The effectiveness of the proposed strategy is demonstrated using a synthetic dataset to assess its capability to quantify uncertainties in probabilistic forecasts. Additionally, a potential case study with a neighborhood of 14 houses connected to the same distribution transformer is presented to validate the proposed method. A comparative investigation of quantified uncertainties is presented by employing the Additive Gaussian Process (AGP), the Prophet forecasting, and the quantile regression, highlighting the usefulness of the proposed approach in flexibility markets. The results demonstrated the superiority of AGP-based load forecasts and flexibility needs with precise prediction accuracy. The comparative study demonstrates that the proposed method with AGP presents a minimum uncertainty when forecasting the total residential load than other benchmark models with a percentage of 26% and 21% in mean absolute error, respectively, for the different datasets. The continuous ranked probability score also revealed a 39% increase in the accuracy of probabilistic forecasts via the proposed method in contrast to others.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".