Layered Timeseries Analysis for Smart Grid Agents
Bibliographic record
Abstract
The vision of evolving the current electrical power grid towards a Smart Grid promises increased utilization of distributed renewable energy resources through more robust technical and economic control systems and active participation from customers. We study two problems within the distribution grid that employ autonomous agents to enable robust control and customer participation. First, we study the evolution of hourly electricity prices in a modern wholesale electricity market with the goal of predicting hourly forward prices so that an intermediary broker agent can effectively manage trading risk. We analyze real market data from the Ontario Independent Electricity System Operator (IESO) from 2002 to 2011 and corresponding real weather data from the US National Climatic Data Center (NCDC). Our analysis shows that a layered combination of a multi-class classification approach and a multiplicative seasonal ARIMA model can be used to predict the hourly forward prices with confidence. Second, we develop generative hierarchical models to simulate the demand for and supply of electricity from various types of retail customers (e.g., households, universities, industrial plants). Demand and supply depend on various factors such as installed load capacity, household size, geographic locale, day of week, month of year, cloud cover and wind speed. We assume that a sample of data from real world metering or finegrained simulation is available a priori for training and an additional small sample of data is made available online. We then generate more data for forward simulation from the online data, while borrowing characteristics from the training data, using a coarse-grained model based on a novel combination of ARIMA and hierarchical Bayesian methodology. We evaluate our methodology using data from a fine-grained simulation model based on real data from the MeRegio pilot project in Baden-Wurttemberg, Germany. 1 1
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.028 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.007 | 0.001 |
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 source (direct Gemma or distilled Codex), 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".