FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3196351275> ?p ?o ?g. }

• W3196351275 endingPage "117634" @default.
• W3196351275 startingPage "117634" @default.
• W3196351275 abstract "Model predictive control (MPC) offers an optimal control technique to establish and ensure that the total operation cost of multi-energy systems remains at a minimum while fulfilling all system constraints. However, this method presumes an adequate model of the underlying system dynamics, which is prone to modelling errors and is not necessarily adaptive. This has an associated initial and ongoing project-specific engineering cost. In this paper, we present an on- and off-policy multi-objective reinforcement learning (RL) approach that does not assume a model a priori, benchmarking this against a linear MPC (LMPC — to reflect current practice, though non-linear MPC performs better) - both derived from the general optimal control problem, highlighting their differences and similarities. In a simple multi-energy system (MES) configuration case study, we show that a twin delayed deep deterministic policy gradient (TD3) RL agent offers the potential to match and outperform the perfect foresight LMPC benchmark (101.5%). This while the realistic LMPC, i.e. imperfect predictions, only achieves 98%. While in a more complex MES system configuration, the RL agent’s performance is generally lower (94.6%), yet still better than the realistic LMPC (88.9%). In both case studies, the RL agents outperformed the realistic LMPC after a training period of 2 years using quarterly interactions with the environment. We conclude that reinforcement learning is a viable optimal control technique for multi-energy systems given adequate constraint handling and pre-training, to avoid unsafe interactions and long training periods, as is proposed in fundamental future work." @default.
• W3196351275 created "2021-09-13" @default.
• W3196351275 creator A5002011208 @default.
• W3196351275 creator A5018630465 @default.
• W3196351275 creator A5020954840 @default.
• W3196351275 creator A5024462942 @default.
• W3196351275 creator A5030051367 @default.
• W3196351275 creator A5044454685 @default.
• W3196351275 creator A5064553018 @default.
• W3196351275 creator A5084761014 @default.
• W3196351275 creator A5086249018 @default.
• W3196351275 date "2021-12-01" @default.
• W3196351275 modified "2023-10-16" @default.
• W3196351275 title "Model-predictive control and reinforcement learning in multi-energy system case studies" @default.
• W3196351275 cites W1794125082 @default.
• W3196351275 cites W1906412962 @default.
• W3196351275 cites W2070841615 @default.
• W3196351275 cites W2082681239 @default.
• W3196351275 cites W2096018174 @default.
• W3196351275 cites W2235126960 @default.
• W3196351275 cites W2288574683 @default.
• W3196351275 cites W2344779493 @default.
• W3196351275 cites W2417168072 @default.
• W3196351275 cites W2552300487 @default.
• W3196351275 cites W2557167654 @default.
• W3196351275 cites W2568650276 @default.
• W3196351275 cites W2583406171 @default.
• W3196351275 cites W2591980212 @default.
• W3196351275 cites W2726531607 @default.
• W3196351275 cites W2765650568 @default.
• W3196351275 cites W2774636080 @default.
• W3196351275 cites W2891156761 @default.
• W3196351275 cites W2980236141 @default.
• W3196351275 cites W2981148847 @default.
• W3196351275 cites W3006765757 @default.
• W3196351275 cites W3106711840 @default.
• W3196351275 doi "https://doi.org/10.1016/j.apenergy.2021.117634" @default.
• W3196351275 hasPublicationYear "2021" @default.
• W3196351275 type Work @default.
• W3196351275 sameAs 3196351275 @default.
• W3196351275 citedByCount "40" @default.
• W3196351275 countsByYear W31963512752022 @default.
• W3196351275 countsByYear W31963512752023 @default.
• W3196351275 crossrefType "journal-article" @default.
• W3196351275 hasAuthorship W3196351275A5002011208 @default.
• W3196351275 hasAuthorship W3196351275A5018630465 @default.
• W3196351275 hasAuthorship W3196351275A5020954840 @default.
• W3196351275 hasAuthorship W3196351275A5024462942 @default.
• W3196351275 hasAuthorship W3196351275A5030051367 @default.
• W3196351275 hasAuthorship W3196351275A5044454685 @default.
• W3196351275 hasAuthorship W3196351275A5064553018 @default.
• W3196351275 hasAuthorship W3196351275A5084761014 @default.
• W3196351275 hasAuthorship W3196351275A5086249018 @default.
• W3196351275 hasBestOaLocation W31963512752 @default.
• W3196351275 hasConcept C111472728 @default.
• W3196351275 hasConcept C126255220 @default.
• W3196351275 hasConcept C13280743 @default.
• W3196351275 hasConcept C138885662 @default.
• W3196351275 hasConcept C144133560 @default.
• W3196351275 hasConcept C154945302 @default.
• W3196351275 hasConcept C162853370 @default.
• W3196351275 hasConcept C172205157 @default.
• W3196351275 hasConcept C185798385 @default.
• W3196351275 hasConcept C205649164 @default.
• W3196351275 hasConcept C2524010 @default.
• W3196351275 hasConcept C2775924081 @default.
• W3196351275 hasConcept C2776036281 @default.
• W3196351275 hasConcept C33923547 @default.
• W3196351275 hasConcept C41008148 @default.
• W3196351275 hasConcept C75553542 @default.
• W3196351275 hasConcept C86251818 @default.
• W3196351275 hasConcept C91575142 @default.
• W3196351275 hasConcept C97541855 @default.
• W3196351275 hasConceptScore W3196351275C111472728 @default.
• W3196351275 hasConceptScore W3196351275C126255220 @default.
• W3196351275 hasConceptScore W3196351275C13280743 @default.
• W3196351275 hasConceptScore W3196351275C138885662 @default.
• W3196351275 hasConceptScore W3196351275C144133560 @default.
• W3196351275 hasConceptScore W3196351275C154945302 @default.
• W3196351275 hasConceptScore W3196351275C162853370 @default.
• W3196351275 hasConceptScore W3196351275C172205157 @default.
• W3196351275 hasConceptScore W3196351275C185798385 @default.
• W3196351275 hasConceptScore W3196351275C205649164 @default.
• W3196351275 hasConceptScore W3196351275C2524010 @default.
• W3196351275 hasConceptScore W3196351275C2775924081 @default.
• W3196351275 hasConceptScore W3196351275C2776036281 @default.
• W3196351275 hasConceptScore W3196351275C33923547 @default.
• W3196351275 hasConceptScore W3196351275C41008148 @default.
• W3196351275 hasConceptScore W3196351275C75553542 @default.
• W3196351275 hasConceptScore W3196351275C86251818 @default.
• W3196351275 hasConceptScore W3196351275C91575142 @default.
• W3196351275 hasConceptScore W3196351275C97541855 @default.
• W3196351275 hasLocation W31963512751 @default.
• W3196351275 hasLocation W31963512752 @default.
• W3196351275 hasLocation W31963512753 @default.
• W3196351275 hasOpenAccess W3196351275 @default.
• W3196351275 hasPrimaryLocation W31963512751 @default.
• W3196351275 hasRelatedWork W1490753184 @default.

• next