K-means and agglomerative clustering for source-load mapping in distributed district heating planning
Bibliographic record
Abstract
• Data-driven clustering optimizes heat source placement in Stockholm's district heating network. • Distributed sources supply 54% of annual heat demand (7.7 TWh/year) from data centers, water bodies, and supermarkets. • Marginal heat costs (12.7–20 EUR/MWh) are below market prices, confirming economic feasibility. • Scalable framework offers sustainable solutions for district heating in global urban contexts. • Findings guide policy for cost-effective, low-carbon energy systems. This study introduces a high-resolution, data-driven approach for optimizing district heating networks using source-load mapping, focusing on Stockholm as a case study. The methodology integrates detailed building energy performance data (2014–2022) with geographic data from the Swedish Survey Agency, employing advanced clustering techniques such as K-means Clustering, Agglomerative Clustering, DBSCAN, Spectral Clustering, and Gaussian Mixture Model (GMM) Clustering to identify optimal locations for distributed heat sources, including data centers, supermarkets, and water bodies. Quantitative results show that these environmentally friendly sources could supply 54 % of Stockholm’s total annual heat demand of 7.7 TWh/year, equating to 4.2 TWh from residual heat sources. Data centers contribute 0.48 TWh, water bodies provide 3.4 TWh, and supermarkets contribute 0.3 TWh annually. Economic analysis further reveals that 98 % of residual heat sources are economically viable, with marginal costs of heat (MCOH) for data centers, supermarkets, and water bodies estimated at 12.7 EUR/MWh, 16.0 EUR/MWh, and 20.0 EUR/MWh, respectively—well below the Open District Heating (ODH) market price of 22.0 EUR/MWh. The policy implications of these findings are profound. Policymakers can leverage this methodology to identify economically viable heat sources, enabling the creation of regulations that incentivize the integration of distributed heat sources into existing district heating networks. This can lead to reduced energy costs, enhanced sustainability, and more resilient energy systems. Practically, urban planners and energy utilities can use clustering insights to optimize the placement of new infrastructure, such as data centers, ensuring they are strategically located in high-demand zones. Furthermore, the study’s methodology can be replicated in other urban contexts, offering cities worldwide a scalable tool for improving the efficiency and sustainability of their heating networks. These findings support the transition to low-carbon energy solutions and provide actionable recommendations for the long-term development of urban energy systems.
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 | 0.002 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 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".