A Hybrid Evolutionary Algorithm Framework for Optimising Power Take Off and Placements of Wave Energy Converters Mehdi Neshat, Bradley Alexander, Nataliia Sergiienko, Markus Wagner GECCO '19 Slide 1 Neshat et al., Optimisation and Logistics Group
Problem Definition • Goal is to place and tune wave energy converters: GECCO '19 Slide 2 Neshat et al., Optimisation and Logistics Group
Problem DefiniQon • ...in a constrained area of sea: GECCO '19 Slide 3 Neshat et al., OpQmisaQon and LogisQcs Group
Problem Definition • ...in a constrained area of sea: GECCO '19 OpQmisaQon and LogisQcs Group Slide 4
Problem Definition • ...in a constrained area of sea: • and tune each to maximise average energy output GECCO '19 Slide 5 Neshat et al., Optimisation and Logistics Group
Wave energy complements wind and solar • Wind and solar are now the cheapest form of new- build power generaQon. – Solar contracts ~US 2c/kWh • (Saudi Arabia – 1.79c kWh (the naQonal Abu Dhabi – Jan 2018)). – Average wind price ~US 2c/kWh • (h`ps://emp.lbl.gov/sites/default/files/2017_wind_technologies_market_report.pdf) GECCO ‘19 Slide 6 Neshat et al., Optimisation and Logistics Group
...and are growing fast... • Growing level of investment – Global investment totalled US $332.1 billion in 2018 • (source BloombergNEF, Jan 2019) GECCO '19 Slide 7 Neshat et al., OpQmisaQon and LogisQcs Group
Wind energy is abundant ure 2: The potential for wind power generation in Australia GECCO '19 Slide 8 Neshat et al., OpQmisaQon and LogisQcs Group
Wind energy is abundant ure 2: The potential for wind power generation in Australia GECCO '19 Optimisation and Logistics Group Slide 9
Solar energy is abundant GECCO '19 Slide 10 Neshat et al., OpQmisaQon and LogisQcs Group
Solar energy is abundant • Solar A farm this big would match world energy demand GECCO '19 Slide 11 Neshat et al., Optimisation and Logistics Group
But – Wind and Solar are Intermittent • South Australian generaQon– end of June 2019 Source: Open-NEM GECCO '19 Optimisation and Logistics Group Slide 12
But – Wind and Solar are Intermittent • South Australia electricity market – end of June 2019 not good! GECCO '19 Slide 13 Neshat et al., Optimisation and Logistics Group
But Wave Energy was Still Good! • Waves persist long ager winds have passed. 02 July ’19 (same time as red box on previous chart!) source: surf-forecast.com GECCO '19 Slide 14 Neshat et al., Optimisation and Logistics Group
Advantages of Wave Energy • Out of sync with sun and wind. • High energy densities – up to 60kw per m 2 • High capacity factors – predicted to get to 50% GECCO '19 Slide 15 Neshat et al., Optimisation and Logistics Group
Our Contributions • First opQmisaQon of both buoy parameters and posiQons. – High fidelity models. – Variety of algorithms tested – some new. – New algorithms outperform best-published. – Explored four different real wave scenarios. GECCO '19 Optimisation and Logistics Group Slide 16
Wave Buoys • One of the most efficient designs for extracting wave energy are three-tether wave buoys. • These are submerged and extract energy from heave, pitch and surge motions. • We model the CETO 6 wave-energy-converter (WEC) Carnegie Wave Energy GECCO '19 Slide 17 Neshat et al., OpQmisaQon and LogisQcs Group
Wave Farms • WECs can reinforce each other through wave interactions. • This means we can extract more energy per-buoy if WECs are carefully laid out in farms. GECCO '19 Slide 18 Neshat et al., Optimisation and Logistics Group
Power-Take-Off Settings • Each buoy has Power-Take-Off (PTO) units for converQng mechanical energy to electricity. • Can be modelled as springs • Two tunable parameters – d PTO : damping rate – controls how fast oscillaQons are damped down – controls amplitude. – k PTO : sQffness – controls oscillaQon frequency. • We opQmise these for each buoy. GECCO '19 Slide 19 Neshat et al., Optimisation and Logistics Group
Problem FormulaQon • We want to maximise power output for N-buoys by placing them in X,Y locations in a farm with PTO settings of D PTO and K PTO for each buoy. P ⇤ Σ = argmax X , Y , K pto , D pto P Σ ( X , Y , K pto , D pto ) • We use N=4 (16 parameters) and N=16 (64 parameters) GECCO '19 Slide 20 Neshat et al., OpQmisaQon and LogisQcs Group
Constraints • Farm size is limited to a square area: [ l u √ 0 d x u = � u = N ∗ 20000 m . This area per-buoy. Moreover, a safety – violations fixed by re-sampling • Buoys have to be more than 50 metres apart – violations punished with steep penalty function. GECCO '19 OpQmisaQon and LogisQcs Group Slide 21
Real Wave Scenarios • Four real wave scenarios Perth Adelaide Sydney Tasmania GECCO '19 Slide 22 Neshat et al., Optimisation and Logistics Group
Real Wave Scenarios • Modelled as distribuQons Perth Significant wave height, m Significant wave height (m) 0.06 9 0 330 30 8 7 6 Sydney Significant wave height, m Significant wave height (m) 300 60 8 0.06 0.04 6 0 0.6 330 30 7 0.3 5 270 90 6 4 4 6 300 60 0.04 3 0.02 5 0.075 0.15 240 120 2 270 90 4 4 2 210 150 1 3 180 0.02 0 0 240 120 2 5 10 15 2 Peak wave period, s 1 210 150 180 0 0 5 10 15 Perth Peak wave period, s Adelaide Sydney Tasmania GECCO '19 Slide 23 Neshat et al., Optimisation and Logistics Group
Landscape - PosiQon • Landscape for buoy positions is complex and multi- modal. – Primarily due to inter-buoy interactions. GECCO '19 Optimisation and Logistics Group Slide 24
Landscape – PTO parameters • Landscape for for PTO parameters is simpler – but evolves for each buoy as more buoys are added. 10 5 10 5 5 Power(Watt) Power (Watt) 5 0 6 4 0 5 4 4 3 4 3 10 5 3 10 5 10 5 2 2 2 2 10 5 1 1 Perth 1 kPTO dPTO kPTO dPTO (c) Sydney (a) 10 5 10 5 10 5 10 5 4 7 4 4 6 3 5 3 3 dPTO 4 dPTO 2 2 3 2 2 1 1 1 1 0 1 2 3 4 5 1 2 3 4 5 kPTO 10 5 10 5 kPTO (b) (d) GECCO '19 Slide 25 Neshat et al., Optimisation and Logistics Group
Fitness FuncQon • Our Fitness function is a detailed simulation modelling hydrodynamic interactions for a given environment and PTO settings. • Runtime scales quadratically with number of buoys. – 2 buoys – Fast! – 16 buoys – 9 minutes! • For fairness – all optimisation runs given up to 3 days on 12 cores. GECCO ‘19 Slide 26 Neshat et al., OpQmisaQon and LogisQcs Group
Optimisation Frameworks (1) • All-at-once frameworks: – Random Search – CMA-ES (pop=12) – Differential Evolution (DE) – (1+1)EA – Particle Swarm Otpimisation (PSO) – Nelder-Mead (NM) (plus mutation) GECCO '19 OpQmisaQon and LogisQcs Group Slide 27
Optimisation Frameworks (2) • Cooperative approaches – Alternate CMA-ES for buoy pos and NM for PTOs – Alternate DE for buoy pos and NM for PTOs. – Alternate (1+1)EA for buoy pos and NM for PTOs. – Parallel DE optimisation of buoy pos and PTOs + exchange of values. GECCO '19 Slide 28 Neshat et al., Optimisation and Logistics Group
Optimisation Frameworks (3) • Hybrid Approaches – LS-NM Local search to sequenQally place buoys with NM phase for each placement and PTO (Neshat, GECCO 2018) – SLS-NM(2D) as above but idenQfy search sectors for be`er local sampling. – SLS-NM-B as above inherit last PTO setngs as start for next buoy and backtrack to reopQmise worst previous buoy posiQons and PTO using NM. – SLS-NM-B2 as above but simultaneous opt of PTO and pos in backtracking stage. GECCO '19 Slide 29 Neshat et al., Optimisation and Logistics Group
Performance 10 6 2.8 2.6 Positions parameters 2.4 Power (Watt) energy 2.2 Perth – 16 buoys ys power 2 1.8 1.6 1.4 Layout GECCO '19 30 Neshat et al., OpQmisaQon and LogisQcs Group
Performance 10 6 1.55 1.5 Power (Watt) 1.45 Sydney – 16 buoys 1.4 1.35 1.3 1.25 GECCO '19 31 Neshat et al., Optimisation and Logistics Group
Convergence 10 6 16-buoy, Perth 10 6 16-buoy, Sydney 10 5 4-buoy, Perth 1.6 7 1.5 CMA-ES 2.5 DE Power (Watt) 1.4 6.5 NM-M 1+1EA DE-NM 1.3 CMAES-NM 2 6 1+1EA-NM 1.2 Dual-DE LS-NM(64s) 5.5 SLS-NM(BR) 1.1 1.5 SLS-NM-B1 PSO 1 5 0.5 1 1.5 2 2.5 0.5 1 1.5 2 2.5 5000 10000 15000 10 5 10 5 Computational Budget (s) GECCO '19 32 Neshat et al., Optimisation and Logistics Group
Convergence 10 6 16-buoy, Perth 10 6 16-buoy, Sydney 10 5 4-buoy, Perth 1.6 7 1.5 CMA-ES 2.5 DE Power (Watt) 1.4 6.5 NM-M 1+1EA DE-NM 1.3 CMAES-NM 2 6 1+1EA-NM 1.2 Dual-DE LS-NM(64s) 5.5 SLS-NM(BR) 1.1 1.5 SLS-NM-B1 PSO 1 5 0.5 1 1.5 2 2.5 0.5 1 1.5 2 2.5 5000 10000 15000 10 5 10 5 Computational Budget (s) Best methods converge fast! GECCO '19 33 Neshat et al., Optimisation and Logistics Group
Recommend
More recommend
