Presentation is loading. Please wait.

Presentation is loading. Please wait.

Passive Solar Building Design Using Genetic Programming M. Mahdi Oraei Gholami Brock University Dept. of Computer Science 500 Glenridge Ave. St. Catharines,

Similar presentations

Presentation on theme: "Passive Solar Building Design Using Genetic Programming M. Mahdi Oraei Gholami Brock University Dept. of Computer Science 500 Glenridge Ave. St. Catharines,"— Presentation transcript:

1 Passive Solar Building Design Using Genetic Programming M. Mahdi Oraei Gholami Brock University Dept. of Computer Science 500 Glenridge Ave. St. Catharines, Ontario L2S 3A1, Canada Brian J. Ross Brock University Dept. of Computer Science 500 Glenridge Ave. St. Catharines, Ontario L2S 3A1, Canada Brian J. Ross Brock University Dept. of Computer Science 500 Glenridge Ave. St. Catharines, Ontario L2S 3A1, Canada GECCO 2014

2 Introduction Passive solar building design goals: o Collect heat in winter o Reject heat in summer o No mechanical system How to design a building? o Computer aided design o Interactive evolutionary systems o Automated evolutionary systems GECCO 20142/55

3 Introduction What affects a building design ? o Building location o Local climate o Materials o Window and Shading: size and placement. o Budget GECCO 20143/55

4 Objectives Objectives o Building designs having good solar performance Performance may include... o Cooling energy o Heating energy o Window heat gain o … GECCO 20144/55

5 Approach CFG-based system o Modeling language. o Building shape and size. o Door and window. o Materials. Genetic programming o Implements split grammar ideas and CFG expressions. EnergyPlus o Simulate and analyze all aspects of the building. GECCO 20145/55

6 Conflicting objectives Heat Gain o windows allow sunlight to heat interior in winter but results in air conditioning cost in summer Heat Loss o windows lose heat at night, which requires additional heating expense GECCO 20146/55

7 Single-objective evolution Minimize Energy Usage o small insulated shack with no windows and small door is very efficient to heat and cool. Maximize solar heat gain o Maximizes sun intake with its walls of windows on the east, south, and west sides. GECCO 20147/55

8 Background GECCO 2014

9 Evolutionary Design Evolutionary design is the application of evolutionary computation in designing forms. Architecture, art, engineering, etc. GECCO 20149/55

10 Design Language Context free grammar design language. Strongly typed GP. Split grammar: simplified shape grammar o Some aspects (roofs, windows,...) based on split grammar approach. GECCO 201410/55

11 Split Grammar Rules: Taken from [21] Result: GECCO 201411/55

12 Energy Efficiency Reducing the cost and the amount of energy, specially non-renewable energies, that is needed for providing services and products. Practical result o Saving energy o Pollution is reduced. o Reducing noise of mechanical devices. GECCO 201412/55

13 Energy Plus GECCO 2014

14 EnergyPlus EnergyPlus is a free energy simulation, load calculation, building and energy performance, heat and mass balance application. o GECCO 201414/55

15 EnergyPlus Input 1. Input data file (IDF) o Materials, and Constructions o Geometry: place and size of walls, roofs, floors, doors, windows, and overhang o Lights & Electrical equipment o Ideal Loads Air System 2. Weather file (EPW) o Temperature o Latitude, longitude o wind, rain, snow o... and lots more! GECCO 201415/55

16 EnergyPlus Output Annual Building Utility Performance o Total energy o Heating o Cooling Geometric characteristics: o Building area o Window area o Wall area GECCO 201416/55

17 Literature Review GECCO 2014

18 Evolutionary Design and Energy Efficient Architecture Malkawi et al. (2005) : Windows, supply airs ducts, and return air ducts placement. Marin et al. (2008): Winter comfort. Caldas (2008) : Sustainable energy-efficient buildings. Turrin et al. (2010) : Large roofs structures. Harrington (2012) : Summer and winter comfort. GECCO 201418/55

19 Methodology GECCO 2014

20 System Overview ECJ : evolutionary system GP: Strongly typed CFG-guided design language with split grammar functions. Energy Plus: simulation and analysis system. Multi-objective technique: normalized rank- sum GECCO 201420/55

21 Multi-Objective Techniques Comparison FitnessPareto Ranking RanksNRS (33,0,125,39)1*(3,1,6,3)2.27 (30,24,38,18)1*(2,3,3,2)1.4 (0,47,43,18)1*(1,4,4,2)1.73 (78,62,2,0)1*(6,6,1,1)1.37* (43,19,20,79)1*(4,2,2,4)1.47 (55,55,89,80)2(5,5,5,5)2.67 GECCO 201421/55

22 GP Types and Functions TypeFunction RAdd Root(S) SAdd Cube(D,D,D,FF), Add Cube(D,D,D,F) FFFirst Floor(DG,G,G,G,R2,I) FAdd Floor(G,G,G,G,R2,I) DGAdd Door Grid(I,I,I,d,W,I) GAdd Grid(I,I,W,I), Add Empty Grid(I) DRAdd Door(D,D,I,I) WAdd Window(D,D,I) WAdd Window Overhang(D,D,D,D,D,I) GECCO 201422/55

23 GP Types and Functions ( cont.) TypeFunction R2Add Simple Roof(I), Add Skylight(G) R2Add Gabled Roof(I,G,G,D) R2Add Gabled Roof2(I,G,G,D) D (& I)Avg(D,D),Max(D,D), Min(D,D), Mul(D,D), Div(D,D), IfElse(D,D,D,D), ERC DHalf(D), halffwd(D) IInc(I), dec(I) GECCO 201423/55

24 Roof, Overhangs, Skylights. (a) Gabled roof 1. (b) Gabled roof 2. (c) Overhangs and skylights. (d) Gabled & Skylight roof. GECCO 201424/55

25 Building Model and Its Grammar Tree. GECCO 201425/55

26 Constraints Some of the constraints are as follows: o Min/max size limits o No interior design o symmetric window placement per wall GECCO 201426/55

27 Experimental Setup GECCO 2014

28 GP Parameters ParameterValue Number of Runs10 Generations100 Population Size300 Initialization MethodHalf-and Half Tournament Size3 Crossover Rate90% Mutation Rate10% Elitism2 Grow Tree Max Depth6 Grow Tree Min Depth2 Full Tree Max Depth12 Full Tree Min Depth5 GECCO 201428/55

29 Design Parameters ParameterValue (m) Max/Min Floor Length20/10 Max/Min Floor Width20/10 Max/Min Floor Height8/4 Maximum Number of Rows on a Façade2 Maximum Number of Columns on a Façade 6 Max/Min Door Height8/2 Max/Min Door Width6/1 Max/Min Roof Height10/3 GECCO 201429/55

30 Materials Constructio n MaterialU-factor Wall_1Wood, fiberglass quilt, and plaster0.516 Wall_2Wood, plywood, insulation, gypsum0.384 Wall_3Gypsum, air layer with 0.157 thermal resistance, gypsum 1.978 Wall_4Gypsum, air layer with 0.153 thermal resistance, gypsum 1.994 Wall_5Dense brick, insulation, concrete, gypsum plaster 0.558 Roof_1No mass with thermal resistance 0.651.189 Roof_2Roof deck, fiberglass quilt, plaster0.314 Roof_3Roof gravel, built up roof, insulation, wood 0.268 Floor_1Concrete, hardwood3.119 Floor_2Concrete, hardwood3.314 GECCO 201430/55

31 Window and Door Materials Constructio n MaterialU-factorSHGC Window_13 mm glass, 13 mm air, 3 mm glass2.7200.764 Window_23 mm glass, 13 mm argon, 3 mm glass 2.5560.764 Window_36 mm glass, 6 mm air, 6 mm glass3.0580.700 Window_46 mm low emissivity glass, 6 mm air, 6 mm low emissivity glass 2.3710.569 Window_53 mm glass5.8940.898 Window_66 mm glass5.7780.819 Door_14 mm wood2.875- Door_23 mm wood, air, 3 mm wood4.995- Door_3Single layer 3 mm glass5.8940.716 GECCO 201431/55

32 Different Geographical Locations Experiment GECCO 2014

33 Different Geographical Locations Toronto, Canada o (baseline) humid continental Anchorage, Alaska o northern subarctic. Eldoret, Kenya o equatorial, tropical. Las Vegas, USA o subtropical, hot desert. Melbourne, Australia o southern hemisphere, temperate. GECCO 201433/55

34 Objectives GECCO 201434/55

35 Results GECCO 201435/55

36 Window Area Analysis LocationSouthWestNorthEast Toronto9427.52435 Las Vegas87282528 Eldoret4552.527.555 Anchorage892622.528 Melbourne252981.538 Window area percentage of top solutions. Window Placement: o North hemisphere: south. o South hemisphere: north. o Near equator: east and west. GECCO 201436/55

37 Performance Plots GECCO 201437/55

38 Scatter Plot GECCO 201438/55

39 Scatter Plot (cont.) a- Worst model (Toronto) b- Best model (Melbourne) GECCO 201439/55

40 Consistency: Toronto Models GECCO 201440/55

41 Best Models Toronto Anchorage Las Vegas EldoretMelbourne GECCO 201441/55

42 Best Models Analysis (cont.) Neither skylights nor complex roofs are selected. o Annual energy consumption increases in either cases. o larger roofs = increased room volume Size: o Maximum length o Maximum width. o Height changes based on the location. Materials : o Walls: third lowest U-factor. o Double pane windows with argon Second lowest in U-factor and the best in SHGC o Floors and Roofs: biggest U-factor GECCO 201442/55

43 Multi-Floor Experiment GECCO 2014

44 Stylistic multi-floor buildings Building name: Statoil Headquarters Location: Fornebu, Norway. Designed by: A-lab GECCO 201444/55

45 Multi-floor Experiment GECCO 201445/55

46 Multi-floor Experiment Results: o More energy consumption than when either window constraint or volume constraints are not considered. o Less window heat gain than when window constraint is not considered. o Without window constraint: volume constraints are met easier. o Without volume constraints: window constraint is met easier. GECCO 201446/55

47 Multi-Floor Experiment Materials : GECCO 201447/55

48 Performance Plots GECCO 201448/55

49 Performance Plots GECCO 201449/55

50 The Best Model GECCO 201450/55

51 The Best Model Heat Gain and Annual Energy GECCO 201451/55

52 Discussion A comparison to Caldas (2008) work: Similarities : o Materials, roofs, doors, overhangs, and windows are considered in both. o Multi-objective approach. o Both have the problem of no window when only energy consumption is considered. Differences: o Illumination vs. window heat gain o DOE2 vs. EnergyPlus o GA vs. GP o Two objectives vs. five objectives o Pareto ranking vs. normalized rank sum GECCO 201452/55

53 Conclusion Evolutionary design (GP) o Highly performance building design CFG based grammar guided system o Walls, floors, roofs, windows, overhangs, materials o Grammars were straightforward for our purpose EnergyPlus o Simulation and analysis system. o Worked well, although it is not designed to be used in batch mode with 1000’s of simulations! GECCO 201453/55

54 Conclusion Multi-Objective o Normalized rank sum worked well with even 5 objectives. o Trade-off of objectives: Energy objectives treated “equally”, with no preferred biases. Consistent solutions with respect to size, geometry, materials, and design elements are achieved in all experiments. GECCO 201454/55

55 Thank you GECCO 201455/55

Download ppt "Passive Solar Building Design Using Genetic Programming M. Mahdi Oraei Gholami Brock University Dept. of Computer Science 500 Glenridge Ave. St. Catharines,"

Similar presentations

Ads by Google