ElectroBlock: Reinforcement Learning and Blockchain-based Energy Trade to Optimize Tariffs
Bibliographic record
Abstract
Energy prices have increased by more than ${6 2 \%}$ globally on average, while power companies are trying to provide more affordable energy with different options: fixed-rate, slab-based tariffs, and Time-of-Use pricing. This article aims to combine blockchains, smart contracts, smart grids, energy forecasting through reinforcement learning, and energy trading between closed communities, bringing consumer savings. Our proposed model, ElectroBlock, uses the first 25 days of each month’s energy usage history along with seasonal and exogenous factors to forecast the final end-of-month usage. Then with the forecast we can predict which customers are the most likely to be pushed to the next energy consumption slab and be charged at a higher rate for the remaining month. This allows these customers to be buyers, and seamlessly buy energy units from users who would sell, the energy units they are predicted to leave unused by the end of the month. Moreover, trading is done with WalletCoins, at a coin per kilowatt hour, but could also be traded directly for fiat currency. Furthermore, the power company makes a profit on every trade through transaction fees. Hence there is great incentive for both customers and power companies to adopt our proposed model. We integrated Hyperledger Fabric into our ElectroBlock prototype to store all customer data and prevent tampering with WalletCoin and consumption records. Finally, we did a performance analysis, on the actual cost savings based on a real-world dataset; and a scalability test for concurrency and customer bases on our prototype.
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 | 0.003 |
| 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 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.001 |
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".