Comparison of machine learning and MPC methods for control of home battery storage systems in distribution grids
Bibliographic record
Abstract
Control methods for Home Energy Management Systems implemented with traditional optimization techniques and state-of-the-art Machine Learning methods are presented and compared in this paper in the context of their impact on and interactions with Active Distribution Networks. Thus, model-based methods based on Model Predictive Control algorithms with different prediction qualities are first described and compared against model-free methods based on imitation learning and reinforcement learning. A practical, state-of-the-art, heuristic, rule-based controller is used as the baseline. An in-depth comparison is performed using metrics consisting of objective function values, grid constraint violations, and computational time. The results of applying these Home Energy Management Systems to a realistic German low voltage benchmark grid with 13 connected households, each containing solar generation, a battery storage system, and electrical loads are discussed. It is demonstrated that model-based and model-free methods can achieve improvements over typical rule-based methods, with varying performance in terms of objective function values and grid constraint violations depending on the forecasts, at the cost of higher computational complexity. Furthermore, model-free methods are shown to have in general low computational burden at higher objective function values with more grid constraint violations, with imitation-learning-based techniques proving to be the best compromise for practical applications. • Applied Machine Learning and optimization for Home Energy Management Systems (HEMS). • Comparison of rule-/model-based and model-free HEMS. • Integrated Graph Neural Networks (GNNs) into HEMS control for the first time. • Analyzed Imitation Learning trade-offs between computational demand and performance. • Benchmarked HEMS methods using realistic low voltage grid and household and PV data.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".