Designing aggregation criteria for end-users integration in energy communities: Energy and economic optimisation based on hybrid neural networks models
Bibliographic record
Abstract
This study presents innovative methodologies addressing critical challenges in energy community real-cases implementation. The investigation is conducted by exploring and enhancing the concept of Peer-to-Peer energy community, where prosumers interact with consumers by sharing surplus energy to meet their electricity demands. The end-users' connections are optimised by maximizing their energy interactions and the proposed pricing strategies are based on balancing the supply and demand curves for tailored unit costs. This study aims to optimise the design of energy communities' configurations and the applicability in real case scenarios by suggesting novel aggregation criteria. These criteria are focused to select the type and the number of users in an energy community to maximize the economic benefit and the amount of self-consumed renewable energy. A bi-level optimisation approach is at the basis of these aggregation criteria. The first level maximizes self-sufficiency and economic benefits by aggregating prosumers and consumers into subgroups. The second level determines the optimal community configuration, prioritizing total energy self-consumption. This methodology requires the knowledge of users' electrical needs, therefore, to address the problem related to insufficient data, a Hybrid Neural Network model is proposed to simulate building electrical demands. A case study in a residential area of Caserta, Italy, demonstrates the methodology's effectiveness. By identifying user types, predicting demands, and employing optimisation techniques, the study estimates economic benefits for consumers (1.6% to 19.5% savings) and prosumers (return on investment <3 years) compared to the reference scenario where the consumers and prosumers are connected only to the national electricity grid. Moreover, the optimised aggregation strategy achieves an 89% annual self-consumption compared to 64% of the reference scenario, significantly reducing network imbalances caused by prosumer surpluses.
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".