An Improved Actor-Critic Reinforcement Learning with Neural Architecture Search for the Optimal Control Strategy of a Multi-Carrier Energy System
Bibliographic record
Abstract
In the energy management problem of a multi-carrier energy system, accurate modeling of the resources' dynamics is essential for optimal operational decisions. These dynamics include the units' nonlinear physical characteristics such as valve-point effects of power-only units, fuel cell dynamic efficiency, and nonconvex feasible operating regions of combined heat and power (CHP) units. While model-based techniques may face fesability problems for such non-convex systems, this paper presents a model-free controller using a neural architecture search technique and actor-critic reinforcement learning for optimal scheduling of a multi-carrier energy system. First, an evolutionary-based neural architecture search method has been presented to eliminate the need for manual engineering of deep neural network models and the unnecessary computational burden associated with them. Then, the deep deterministic policy gradient (DDPG) model as an actor-critic method facilitates cost-efficient control strategies for the scheduling problem of the multi-carrier energy system by posing it as a multi-dimensional continuous state and action space. In comparison to the current state-of-the-art methods in the recent literature, the proposed framework demonstrates its effectiveness and applicability.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".