Energy Data Management for Future Cities Mr. Bejay Jayan 2 nd year PhD Researcher Supervisors : Dr. Haijiang Li & Prof. Yacine Rezgui
Content Sustainability Challenges -ENERGY. Why Buildings. Saving energy in buildings. EU Project experience My research using ontologies for energy management. Conclusions
Challenges Global energy demand increase by 41 % between 2012-2035. (BP energy outlook) Energy production increase proportionally. Problem : rising CO2 emissions rate (increase by 29 % during this period)? As a consequence of this : climate change act 2008, 2020 target by EU of generating 15 % electricity from renewables, strict carbon budgets etc.
Challenges What can we do? Increase use of renewables Low carbon technologies. Save energy whenever/wherever possible through little steps (management)
Why Buildings? 1/3rd of the global energy consumption. Energy production proportional to greenhouse gas emissions In UK : Buildings responsible for 37 % greenhouse gas emissions. Solution : Energy management in BUILDINGS.
Saving energy in Buildings Level 1 TakeActionbased on monitored results. These systems, nowadays, are also used to improve energy performance of buildings and not just for comfort or security reasons. Level 2 Most recent technological developments based on artificial intelligence techniques such as neural networks, fuzzy logic, and genetic algorithms.? LEVEL 2 : Neural Netowrk/Optimisation/ Simulation Models LEVEL 1 : Building automation systems (BAS)
Level 2 -EU FP7 project - SPORTE2 Intelligent management system to integrate and control energy generation, consumption, and exchange for European Sport and Recreation Buildings. Real time energy management. Cardiff university involved in optimisation module development.
Remote Energy Optimization in Sport Facilities Scenario: Optimisation of the Air handling units in swimmingpoolzone. Control parameters: Supplied air flow rate ;supplied air temperature. Objective : Minimise energy consumption ; maintain Comfort
Remote Energy Optimization in Sport Facilities Optimum parameters to be controlled by pilot Sensors relay information initial optimum Supplied Air flow rate (m3/s) 1.6 2.391 Air temp. Inlet (deg. C) 4.827 9.279 obj 5.503 0.105 Elec_Cons (kwh) 0.036 0.039 Therm_Eng_Cons (kwh) 0.354 0.025 PMV 5.113 0.042 Stage 2 Optimisation Stage 1 Artificial Neural Network models
EU FP7 project -SPORTE2 Results removed due to confidentiality
Why Level 3? Results removed due to confidentiality Scenarios donot consider aholistic viewpoint. Solely numerical optimisation. The results shown above. Can weachieve thisin reality?
Saving energy in Buildings Ontology Neural Netowrk/Optimisation/ Simulation Models + BAS Building automation systems (BAS)
Ontology Ontology a data model that represents knowledge as a set of concepts within a domain and the relationships between these concepts. Form of knowledge management. (Marco Grassi, 2013)
Workflow Building Automation systems Optimisation ONTOLOGY
Level 3 -Ontology at a Building Level Ontologies allow us to see the bigger picture - whole building context for more efficient energy management in buildings. Add layer of intelligence into traditional optimisation process through human expertise,or simulation models orderivedfrom historicaldata
Level 3 -Ontology at a Building Level two complementary way forward to energy saving Real World Sensors Energy Model Historical Data Mining Database Sensitivity Analysis Scenario Definition Predictive Rules Simulation -based Rules Dynamic Ontology Historical Data approach: More accurate representation of a building through its metered data. Rules derived from data. Rules used through the ontology for energy saving decision making Real Time Control and Actuation Simulation approach: Holistic coverage of the building energy equation. Acute understanding of governing variables and parameters.
Level 3 -Ontology at a DISTRICT LEVEL Energy Optimization at District Level Energy Storage Large Scale Renewable Energy Generation
Level 3 -Ontology at a DISTRICT LEVEL OWL/RDF back-office Ontology management system Purpose-built ontology and international standards District Energy Visualisation Tool District editor Multiagent-based coordination District simulation framework District Energy System Real-time management framework
Level 3 Meeting Industry Requirements We cannot progress fast enough by optimising the city s individual components and systems. We need innovation in integrated and city-wide solutions (Technology StrategyBoard&Arup,2013) Over time there will be alarge market for integrated approaches to delivering efficient, attractive and resilient cities (Technology Strategy Board & Arup,2013) CO2emissionsis asystematicproblem (VOcamp,2014)
Conclusions Holistic approach to Energy management needs to be given importance to tackle CO2 emissions. Ontologies make traditional optimisation RICH. Energy management in Buildings >>>> Districts>>>> Future cities.
Thank you for listening. Acknowledgements Special thanks to SPORTE2 project partners for the research efforts and for contributing to some of the content mentioned in this presentation. Mr.Bejay Jayan jayanb@cardiff.ac.uk + 447595701431 School of Engineering Cardiff University