Feasibility-guaranteed machine learning unit commitment: Fuzzy Optimization approaches
Bibliographic record
Abstract
The unit commitment (UC) problem is solved several times daily in a limited amount of time and is commonly formulated using mixed-integer linear programs (MILP). However, solution time for MILP formulation increases exponentially with the number of binary variables required. To address this, machine learning (ML) models have been attempted with limited success as they cannot be trained for all scenarios, whereby they may contain false predictions leading to infeasibility, hindering their practical applicability. To overcome these issues, we first propose a hybrid deep learning model comprising a convolutional neural network (CNN) and bidirectional long-short-term memory (BiLSTM) to predict the UC decisions. Second, we incorporate these predictions as non-binding fuzzy constraints, enhancing the traditional UC model and creating an ML-fuzzy UC model. Two implementations of non-binding fuzzy constraints are studied. The first develops each ML decision variable as a separate fuzzy set, while the second creates one fuzzy set per hour, considering all decisions within. Introducing ML-UC decisions as non-binding fuzzy constraints ensures the ML-fuzzy UC model has a feasible solution if the basic MILP-UC problem does, while leveraging ML predictions. Moreover, the proposed model benefits from a reduced solution space, leading to substantial reductions in computing time. Results on IEEE 118-bus and Polish 2383-bus systems demonstrate 92 % and 89 % computation time reductions for both systems, respectively and achieve 100 % feasibility for both seen and unseen datasets when the basic MILP-UC problem has a feasible solution. • A hybrid CNN and BiLSTM model was created to provide the unit commitment schedules. • ML predictions modeled as non-binding fuzzy constraints enhancing MILP-UC formulation. • Fuzzy constraints improved ML decision utilization, ensuring 100 % feasibility.
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 | 0.005 |
| 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 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 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".