Study on Constructing a Risk Monitoring and Early Warning Model for Transactions in Southern Regional Electricity Market under New Power System Based on Time Series Bayesian Networks
Bibliographic record
Abstract
Aiming at the potential risks existing in the power market transaction under the new power system, and considering the temporal attributes of the information, this paper proposes to use dynamic Bayesian network to construct the risk monitoring and early warning model of the power market transaction.The dynamic Bayesian network is utilized to calculate the correlation between different risk factors, estimate the risk value of power market transactions, and classify the warning level.Taking the southern regional electricity market as the research object, the relationship between electricity price and transaction volume is explored based on the experimental dataset.A credit grading system is introduced to carry out transaction prediction simulation experiments, relying on the prediction data to determine the link between electricity price and transaction volume.The results show that overall power price and transaction volume show a negative correlation, but in June, when the power price is 0.4370 yuan per kWh, the transaction volume still reaches 19.65 million kWh, and the inverse relationship between the transaction volume and the price is not obvious.The use of dynamic Bayesian network to construct the power market transaction risk monitoring and early warning model can dynamically update and adjust the risk monitoring with the passage of time, making the power market transaction early warning more flexible and real-time.
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 | 0.002 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.004 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".