Soft Actor-Critic-Based MPPT Control of Solar PV Systems Under Partial Shading Conditions
Bibliographic record
Abstract
This paper presents a soft actor-critic (SAC)-based method for solving the solar photovoltaic (PV) Maximum Power Point Tracking (MPPT) control problem under partial shading conditions (PSCs). The MPPT method optimizes the solar PV power and ensures that it constantly operates at its “maximum power point (MPP),” regardless of the dynamics of weather conditions. Traditional MPPT methods, such as the perturb and observe (P&O) method are commonly employed to solve the MPPT control problem. However, they often suffer from a slower convergence rate, significant oscillation near the MPP, drift problems, and frequently fail to track the solar PV global maximum power point (GMPP) in the presence of partial shading. These problems were addressed using the deep Q-network (DQN) method. However, DQN cannot be applied to continuous action spaces. It also uses inefficient experience replay and suffers from Q-value overestimation. Thus, under PSCs and certain environmental conditions, DQN produces fluctuations of power close to the MPP or GMPP, resulting in power loss. To solve the MPPT control problem, a mathematical model based on a Markov Decision Process which allowed the SAC agent to learn the solar PV behavior was developed. Key hyperparameters affecting the SAC algorithm's performance were also investigated. Furthermore, the P&O method were developed for comparison. Simulation results show that the SAC-based MPPT method achieved better tracking accuracy than the DQN method under standard testing conditions, varying irradiance levels, and PSCs. Also, it is shown that both the DQN and SAC methods have superior tracking performance compared to the P&O method under similar environmental conditions tested.
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) | 0.001 | 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".