abstract bibtex

Implementation of reinforcement learning control for LowEx Building systems. Learning allows adaptation to local environment without prior knowledge. Presentation of reinforcement learning control for real-life applications. Discussion of the applicability for real-life situations. a b s t r a c t Over a third of the anthropogenic greenhouse gas (GHG) emissions stem from cooling and heating build-ings, due to their fossil fuel based operation. Low exergy building systems are a promising approach to reduce energy consumption as well as GHG emissions. They consists of renewable energy technologies, such as PV, PV/T and heat pumps. Since careful tuning of parameters is required, a manual setup may result in sub-optimal operation. A model predictive control approach is unnecessarily complex due to the required model identification. Therefore, in this work we present a reinforcement learning control (RLC) approach. The studied building consists of a PV/T array for solar heat and electricity generation, as well as geothermal heat pumps. We present RLC for the PV/T array, and the full building model. Two methods, Tabular Q-learning and Batch Q-learning with Memory Replay, are implemented with real building settings and actual weather conditions in a Matlab/Simulink framework. The performance is evaluated against standard rule-based control (RBC). We investigated different neural network structures and find that some outperformed RBC already during the learning phase. Overall, every RLC strategy for PV/T outperformed RBC by over 10% after the third year. Likewise, for the full building, RLC outperforms RBC in terms of meeting the heating demand, maintaining the optimal operation temperature and com-pensating more effectively for ground heat. This allows to reduce engineering costs associated with the setup of these systems, as well as decrease the return-of-invest period, both of which are necessary to create a sustainable, zero-emission building stock.

@article{ title = {Reinforcement learning for optimal control of low exergy buildings}, type = {article}, year = {2015}, identifiers = {[object Object]}, keywords = {Energy efficient buildings,Low exergy building systems,Reinforcement learning control,Sustainable building systems,Zero net energy buildings,low exergy building systems,reinforcement learning control,zero net energy buildings}, pages = {577-586}, volume = {156}, websites = {http://linkinghub.elsevier.com/retrieve/pii/S030626191500879X}, month = {10}, publisher = {Elsevier Ltd}, id = {5c819548-ddff-3c10-8756-1b67c50895fe}, created = {2015-10-14T13:06:24.000Z}, file_attached = {false}, profile_id = {930c6fc3-4f7d-3268-8cb7-e7bbdd7b5ce3}, last_modified = {2015-10-14T13:06:24.000Z}, read = {false}, starred = {false}, authored = {true}, confirmed = {true}, hidden = {false}, citation_key = {Yang2015}, source_type = {article}, abstract = {Implementation of reinforcement learning control for LowEx Building systems. Learning allows adaptation to local environment without prior knowledge. Presentation of reinforcement learning control for real-life applications. Discussion of the applicability for real-life situations. a b s t r a c t Over a third of the anthropogenic greenhouse gas (GHG) emissions stem from cooling and heating build-ings, due to their fossil fuel based operation. Low exergy building systems are a promising approach to reduce energy consumption as well as GHG emissions. They consists of renewable energy technologies, such as PV, PV/T and heat pumps. Since careful tuning of parameters is required, a manual setup may result in sub-optimal operation. A model predictive control approach is unnecessarily complex due to the required model identification. Therefore, in this work we present a reinforcement learning control (RLC) approach. The studied building consists of a PV/T array for solar heat and electricity generation, as well as geothermal heat pumps. We present RLC for the PV/T array, and the full building model. Two methods, Tabular Q-learning and Batch Q-learning with Memory Replay, are implemented with real building settings and actual weather conditions in a Matlab/Simulink framework. The performance is evaluated against standard rule-based control (RBC). We investigated different neural network structures and find that some outperformed RBC already during the learning phase. Overall, every RLC strategy for PV/T outperformed RBC by over 10% after the third year. Likewise, for the full building, RLC outperforms RBC in terms of meeting the heating demand, maintaining the optimal operation temperature and com-pensating more effectively for ground heat. This allows to reduce engineering costs associated with the setup of these systems, as well as decrease the return-of-invest period, both of which are necessary to create a sustainable, zero-emission building stock.}, bibtype = {article}, author = {Yang, Lei and Nagy, Zoltan and Goffin, Philippe and Schlueter, Arno and Yang L., undefined and Nagy Z., undefined and Goffin Ph., undefined and Schlueter, Arno}, journal = {Applied Energy} }

Downloads: 0