Academic Journal
Hardware–software codesign for peer-to-peer energy market resolution ; Adéquation Algorithme Architecture pour la résolution d'un marché pair à pair de l'électricité
| العنوان: | Hardware–software codesign for peer-to-peer energy market resolution ; Adéquation Algorithme Architecture pour la résolution d'un marché pair à pair de l'électricité |
|---|---|
| المؤلفون: | Thomas, Beatrice, Le Goff Latimier, Roman, Ben Ahmed, Hamid, Jodin, Gurvan, El Ouardi, Abdelhafid, Bouaziz, Samir |
| المساهمون: | Systèmes et Applications des Technologies de l'Information et de l'Energie (SATIE), École normale supérieure - Rennes (ENS Rennes)-Conservatoire National des Arts et Métiers CNAM (CNAM)-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-Ecole Normale Supérieure Paris-Saclay (ENS Paris Saclay)-Université Gustave Eiffel-CY Cergy Paris Université (CY) |
| المصدر: | ISSN: 2352-4677 ; Sustainable Energy, Grids and Networks ; https://hal.science/hal-04202817 ; Sustainable Energy, Grids and Networks, 2023, 35, pp.101122. ⟨10.1016/j.segan.2023.101122⟩. |
| بيانات النشر: | HAL CCSD Elsevier |
| سنة النشر: | 2023 |
| المجموعة: | Université Paris Seine: ComUE (HAL) |
| مصطلحات موضوعية: | Electricity market, Peer to Peer (P2P), CPU-GPU Partitioning, Parallel computing, Performance evaluation, [INFO.INFO-DC]Computer Science [cs]/Distributed, Parallel, and Cluster Computing [cs.DC] |
| الوصف: | International audience ; The growth of distributed energy resources raises the challenge of scaling up network management algorithms. This difficulty may be overcome in operating conditions with the help of a rich literature that frequently calls upon the distribution of computations. However, this issue persists during preliminary simulations validating the performances, the operation’s safety, and the infrastructure’s sizing. A hardware–software co-design approach is conducted here for a Peer-to-Peer market to address this scaling issue while computing simulations on a single machine. The mapping between several algorithms and different models of partitioning on Central and Graphic Processing Units (CPU–GPU) has been conducted. The complexity and performance of the Operator Splitting Quadratic Program (OSQP) or Alternating Direction Method of Multipliers (ADMM) for a centralized or decentralized resolution according to the hardware have been studied and analyzed in different test cases. The dominance of the pair ADMM and GPU has been demonstrated by having a speed-up of more than 98% compared to the other methods when the market has more than 500 agents |
| نوع الوثيقة: | article in journal/newspaper |
| اللغة: | English |
| Relation: | hal-04202817; https://hal.science/hal-04202817; https://hal.science/hal-04202817/document; https://hal.science/hal-04202817/file/ArticleElsevierFinalVClean.pdf |
| DOI: | 10.1016/j.segan.2023.101122 |
| الاتاحة: | https://hal.science/hal-04202817 https://hal.science/hal-04202817/document https://hal.science/hal-04202817/file/ArticleElsevierFinalVClean.pdf https://doi.org/10.1016/j.segan.2023.101122 |
| Rights: | info:eu-repo/semantics/OpenAccess |
| رقم الانضمام: | edsbas.4FE826E8 |
| قاعدة البيانات: | BASE |
| DOI: | 10.1016/j.segan.2023.101122 |
|---|