Beruflich Dokumente
Kultur Dokumente
Renewable Energy
journal homepage: www.elsevier.com/locate/renene
a r t i c l e i n f o a b s t r a c t
Article history: Optimization of the layouts of arrays of wave energy converters (WECs) is a challenging problem. The
Received 16 May 2015 hydrodynamic analysis and performance estimation of such systems are performed using semi-analytical
Received in revised form and numerical models such as the boundary element method. However, the analysis of an array of such
4 May 2016
converters becomes computationally expensive, and the computational time increases rapidly with the
Accepted 25 May 2016
Available online 13 June 2016
number of devices in the system. As such determination of optimal layouts of WECs in arrays becomes
extremely difficult. In this paper, a methodology involving multiple optimization strategies is presented
to arrive at the solution to the complex problem. The approach includes a statistical emulator to predict
Keywords:
Wave-energy
the performance of the WECs in arrays, followed by an innovative active learning strategy to simulta-
Oyster neously explore and focus in regions of interest of the problem, and finally a genetic algorithm to obtain
OWSC the optimal layouts of WECs. The method is extremely fast and easily scalable to arrays of any size. Case
Optimization studies are performed on a wavefarm comprising of 40 WECs subject to arbitrary bathymetry and space
Active learning constraints.
Genetic algorithm © 2016 Elsevier Ltd. All rights reserved.
Gaussian process
http://dx.doi.org/10.1016/j.renene.2016.05.083
0960-1481/© 2016 Elsevier Ltd. All rights reserved.
D. Sarkar et al. / Renewable Energy 97 (2016) 504e517 505
optimal layouts of arrays. While the parabolic intersection Upper Confidence Bound with Pure Exploration algorithm (GP-
approach uses simple calculations for a quick estimate of the array UCB-PE) [10]. Since the final goal of the work is to determine
layouts, the genetic algorithm requires many evaluations of a semi- optimal layouts of an array, we are more interested in layouts which
analytical (or numerical) method which is computationally result in good performance of the individual WECs. The active
expensive. Such a direct application of sequential optimization learning strategy determines sequentially which configurations of
techniques also implies that if the number of WECs is changed, a the 3-WEC and 2-WEC clusters should be evaluated aiming to
new set of evaluations needs to be computed and analysed. In this improve the predictions of the optimal clusters using the least
work we propose a fast and scalable approach to address the number of evaluations possible. The algorithm performs a trade-off
challenge of determining the best layout for any number of WECs between exploitation and exploration looking for the maximum
and arbitrary bathymetry constraints. We first use an active while exploring clusters with high uncertainty.
learning strategy to train a statistical emulator of the individual In our optimization methodology, we incorporate some con-
WECs inside the array. We then predict the performance of the straints which are relevant to the problem. The OWSCs are near-
whole wavefarm by evaluating only the quasi-instantaneous shore WECs with depth specific designs, and as such bathymetry
emulator. The optimization of the layout under the various con- will play a significant role in deciding their locations. We consider
straints is then performed on the predicted performances with a an upper and a lower bound on the bathymetry contours, within
genetic algorithm designed specifically for this task. which the placement of the centre of the OWSCs is restricted.
The analysis in this work is performed on a well known WEC- Although the mathematical model (for simulations) is based on a
the Oscillating Wave Surge Converter. A number of studies are now constant water depth assumption, the bathymetry constraints in
available which have looked at various aspects of the device (see the optimization problem take account of the spatial limitations
e.g. Refs. [7,8]). Most recently, a mathematical model was devel- imposed by the depth variations at real locations, in the placement
oped in Ref. [9] to analyse the behavior of the OWSCs in a wave farm of the WECs. In a practical situation, proper utilisation of space is
and the simulations in this work will use this model. The overall also an important consideration and to account for that an upper
performance of the array is decomposed as the sum of the powers bound in the distance separating the centres of the first and the last
captured by each individual WEC. In a realistic scenario, the seas are WEC in the y0 direction (see Fig. 1) is fixed at a particular value.
highly irregular, and the interaction effects on a particular WEC due The methodology of the simulations, statistical emulator and
to WECs located away from it are largely diminished. It is reason- the machine learning algorithm will be illustrated in the following
able to assume that individual WECs in an array are predominantly sections. Later in x5, case studies are performed on the optimization
influenced by those located very close to them. Our approach tar- of a wavefarm comprising of 40 OWSCs, followed by discussions
gets the approximated performance where we simplify the model and conclusion.
of the individual WECs in order to take into account only a limited
number of interactions. A WEC located inside the array is strongly
influenced by the two WECs which are nearest to it, i.e. one on each 2. Simulation model
side (see Fig. 2). To model the behavior of such a WEC, we consider a
3-WEC cluster and focus on the behavior of the central WEC. On the The simulations for the various layouts are performed using the
other hand, the edge WECs are modelled using a 2-WEC cluster. mathematical model of [9]. A wavefarm comprising of M WECs (see
Our prediction function is based on Gaussian process regression Fig. 1) is considered, and so the 2 M variables that need to be
trained with an active learning strategy, the Gaussian Process optimized are x01 ; y01 ; …x0M ; y0M , which are the horizontal coordinates
of the centres of the OWSCs in the x0 and y’ directions respectively.
Fig. 1. Geometry of the physical system (a) side view of one of the WECs (b) top view of a wavefarm comprising of M WECs. The right most OWSC is considered to be the first WEC,
with the numbering increasing towards the left. The horizontal spatial coordinates of the centres of the OWSCs are: (x01 ; y01 ), (x02 ; y02 ), …..., (x0M ; y0M ).
Fig. 2. The methodology considers only the interaction of the WECs with their neighbouring ones. As such the two edge WECs located at the two extremes of the wavefarm can be
modelled with a simplified 2-WEC cluster configuration while those lying in the interior with a 3-WEC cluster arrangement. The right most OWSC is considered to be the first WEC
of the array. The horizontal spatial coordinates of the centres of the OWSCs are: (x01 ; y01 ), (x02 ; y02 ), …..., (x0M ; y0M ).
506 D. Sarkar et al. / Renewable Energy 97 (2016) 504e517
e the Laplace equation in the fluid domain where xm and ym are the x and y co-ordinates of the centre of the m-
th OWSC, Up(u) is the Chebyshev polynomial of the second kind,
V02 F0 ¼ 0; (1) aapnm are the numerically obtained solutions using a collocation
scheme (see Ref. [9]), Zn(z) are the well-known vertical eigenmodes
where V0 f 0
¼ ðf;x0 0 ; f;y0 0 ; f;z0 0 Þ is the nabla operator; subscripts with and kn are the solutions to the dispersion relation
commas denote differentiation with respect to relevant variables; u2 ¼ gkntanh(knh).
Once the solution is known, the hydrodynamic parameters are
e the free surface kinematic-dynamic boundary condition obtained which are then utilized to solve for the body equation of
motion of the WECs. Note, these solutions are for a wave of specific
F0;t0 t0 þ gF0;z0 ¼ 0; z0 ¼ 0; (2) period and amplitude. The behavior in a wave spectrum is obtained
by discretizing the spectrum into a particular number of fre-
where g is the acceleration due to gravity; quencies and then performing linear superposition of the regular
wave outputs [11]. The analysis is performed using a Bretschneider
e the no-flux boundary condition on the sea bed spectrum
4
F0;z0 ¼ 0; z0 ¼ h0 ; (3) 2 4 5
Sðf Þ ¼ 0:257H1=3 T1=3 f exp 1:03 T1=3 f (8)
e the kinematic boundary condition in the WEC boundaries (see Ref. [12]) to model the wave climate of the most probable sea
state at the Isle of Lewis in Scotland, a planned site for wave farms,
F0;x0 ¼ q0m;t0 z0 þ h0 c0m H z0 þ h0 c0m ; with the significant wave height H1/3 ¼ 1 m and the significant
x0 ¼ x0m ±ε0 ; ε0 /0; (4) wave period T1/3 ¼ 8.24 s. Note in (8), f is the frequency of the
0
0 0 incident wave. The spectrum was covered with 51 equispaced fre-
yAm <y < yBm ; m ¼ 1; ::; M; quencies starting at 0.05 Hz and ending at 0.5 Hz. The power from
0 each OWSC was computed according to the relation
where x0m is the x0 coordinate of the centre of the mth flap, yAm and
0
yBm are the y0 coordinates corresponding to the two edges of the
1XN
device and H is the Heaviside step function. Pi ¼ npto Siv ðfl ÞDf (9)
2
The non-dimensional parameters of the problem are chosen to l¼1
be
where Siv ðfl Þ is the spectral density of velocity of the ith OWSC at
pffiffiffiffiffiffiffiffiffiffiffi
ðx; y; z; r Þ ¼ ðx ; y ; z ; r Þ=w ; t ¼ g=w0 t 0 ;
0 0 0 0 0 frequency fl, N ¼ 51 and npto is the optimal power take-off damping
pffiffiffiffiffiffiffiffi 0 (5) coefficient which is obtained using an optimization procedure
F ¼ F0 gw0 AI ; qm ¼ q0m ε; aiming to maximize the power capture by an isolated OWSC.
The effect of the interactions on the performance of the indi-
with ε ¼ A0I =w0 being the small parameter. Assuming the motions of vidual WECs can be quantified using the qmod factor (see Ref. [13])
the WEC to be harmonic, the velocity potential and the angular which is defined as
deflections can be expressed as F ¼ Re{4(x,y,z)eiut} and
qm ¼ RefQm eiut g; m ¼ 1; ::; M respectively, with u being the P i Pisolated
angular velocity. Thanks to linearity, the spatial potential 4 can be qmod;i ¼
Pisolated
decomposed into
where Pi is the power captured by the i-th WEC in the array, while
X
M
4 ¼ 4I þ 4ð0Þ þ Va 4ðaÞ ; (6) Pisolated is the power captured by the same WEC in isolation. The q
a¼1 factor (ratio of the total power captured from the array to that by
the same number of WECs in isolation) and qmod factor can be
where 4(I) is the incident wave potential, 4(0) is the solution to the related as
diffraction potential when all the OWSCs are held fixed, Va ¼ iuQa
while 4(a), a ¼ 1,2,..,M indicates the solution to the a-th radiation 1 X
M
problem where the a-th OWSC is oscillating and the others are
q¼1þ qmod;i :
M
i¼1
stationary.
The solution to the spatial potential is obtained as ~mod and q
We denote by q ~, the approximate form of the qmod and
D. Sarkar et al. / Renewable Energy 97 (2016) 504e517 507
1 0
~ x01 ; y01 ; …x0M ; y0M ¼ 1 þ
q ~mod
q2 x2 x01 ; y02 y01
M
0
~mod
þq2 xM x0M1 ; y0M y0M1
X
M1 0
þ ~mod
q3 xi x0i1 ; y0i
i¼2
!
y0i1 ; x0iþ1 x0i ; y0iþ1 y0i
where q ~mod
2
~mod
and q 3 are respectively the models for the 2-WEC
clusters (see Fig. 4) and the 3-WEC clusters (see Fig. 3). We pre-
dict the interaction factor of the individual WECs using two sta-
~mod
tistical emulators, one for q3
~mod
and one for q 2 .
Fig. 4. The WEC-2 (in red) models the behavior of the edge WEC of the array. The
3. Function estimation through Gaussian process approach position of WEC-1 (in blue) is varied such that its left edge is located within the striped
square box. (For interpretation of the references to colour in this figure legend, the
reader is referred to the web version of this article.)
We describe here how we predict the unknown values of a
function f : X /ℝ given a data set of evaluations of f. This approach
~mod
will be used for predicting q the interaction factor of a WEC with
3 model. The GP is defined in terms of its mean m and covariance
two neighbours (where X ⊂ℝ4 , the relative coordinates of the function k [14] as
neighbours inside two 100 m boxes as shown in Fig. 3) and q ~mod
2 the
interaction factor of a WEC with a single neighbour (where X ⊂ℝ2 f G P ðm; kÞ (10)
as shown in Fig. 4).
with m: X /ℝ and k: X X /ℝ. Note in (10) the symbol ~ means
3.1. Probabilistic setup ‘distributed according to’. For any set of input vectors x1,x2,…,xl in
X , the value of the function is given by a multivariate Gaussian
We assume that the unknown function f is a random sample random variable
from a Gaussian process (GP), which can be viewed as a general
form of the multi-normal distribution. GP is a natural choice for our ðf ðx1 Þ; f ðx2 Þ; …; f ðxl ÞÞ N ðm; KÞ
problem based on the observation that there is high correlation
where the mean vector m and the covariance matrix K are expressed
between layouts which are strongly similar. Let {(x1,y1),…,(xl,yl)} be
as
a training set of l noisy observations, where yt ¼ f(xt) þ εt, t ¼ 1,2,..,l
and X is an arbitrary vector space in ℝd . We consider that the
m½xi ¼ mðxi Þ
variables εt are distributed according to independent Gaussians
N ð0; s2 Þ, they represent the numerical noise of the semi-analytical and
Fig. 3. The general layout of the 3-WEC configuration. The position of the central WEC is fixed while the positions of WEC-1 and 3 vary such that the left side edge of WEC-1 lies
inside the striped square box and the right edge of WEC-3 inside the dotted box.
508 D. Sarkar et al. / Renewable Energy 97 (2016) 504e517
kernel function so as to incorporate the symmetrical nature of the The value for y⋄t describes the lower confidence bound for the
problem with respect to the x0 axis. As a matter of fact, the behavior optimum at each iteration and the region <t is defined as
of the particular WEC which is modelled (e.g. WEC-2 in Fig. 3)
doesn’t change if the y0 coordinates of the WECs on its two sides are ( )
þ
b
interchanged. <t ¼ x2X f t ðxÞ y⋄t
Conditioned on the observations
Y, we have that the distribution
of f is a GP such that f ðxÞY N ð m s 2 ðxÞÞ, where
b ðxÞ; b
as shown in Fig. 5. The first of the B query points is chosen such that
h i1
m
b ðxÞ ¼ kðX; xÞT K þ s2 I Y (12) þ
x0t ¼ arg max b
f t ðxÞ:
x2X
and
Using the fact that the uncertainty does not depend on Y but
h i1
only on X, once we know x0t we can update it to s b 2t;1 before having
s 2 ðxÞ ¼ kðx; xÞ kðX; xÞT K þ s2 I kðX; xÞ
b (13)
the associated observation. The remaining B 1 points are chosen
by Pure Exploration inside <t . We greedily select the configuration
are the prediction and uncertainty respectively. Note in (12) and b 2t;b
with highest updated uncertainty s
(13), X indicates the training point and k(X,x) is the vector of size l
of the covariance terms between X and x. The hyperparameters of
the setting, which are the diagonal terms of the matrix D in (11),
and the noise variance s2, are chosen so as to maximize the pseudo-
likelihood of our training data set (see Ref. [14]). The optimization
of the hyperparameters is performed with a Quasi-Newton method
using the Broyden-Fletcher-Goldfarb-Shanno (BFGS) algorithm
[17].
The larger the data set of observations is, the better the pre-
dictions are. But each training point requires to run a computa-
tionally expensive semi-analytical method. Since we are more
interested in configurations leading to good performance, we use a
sequential strategy to select the most informative training points,
the Gaussian Process Upper Confidence Bound with Pure Explora-
tion algorithm (GP-UCB-PE) [10]. This algorithm proceeds in an
iterative way so as to reduce the uncertainty of the prediction of the Fig. 5. A simple illustration of the GP-UCB-PE strategy showing the first two query
best configuration. It has recently been used in the estimation of points. The horizontal axis represents the x coordinate while the vertical axis indicate
the function value. The red continuous line is the prediction m b while the black
maximum wave run-up of tsunami waves behind conical islands
continuous lines bound the high confidence region. The lower confidence bound on
[18]. At iteration t after having computed m b t and s b 2t , we simulta- the optimum is shown by the blue dotted line which is the maximum of the lower
neously explore the configurations with high uncertainty and focus confidence bound. The intersection of the blue dotted line and the upper confidence
on the ones with high prediction. We choose a batch of B unknown bound defines the limits of our region of interest < which is shown in blue in the
configurations using a tradeoff between m b t and bs 2t , we then query figure. The first point x0 is chosen to be the maximum of the upper confidence bound.
The dotted line in black shows the updated variance confidence after having selected
the semi-analytical model on those B configurations to improve our x0. The next query point x1 is chosen such that it has the maximum updated uncer-
prediction, and continue to iteration t þ 1. The value of B is arbi- tainty inside <. (For interpretation of the references to colour in this figure legend, the
trarily equal to 20 in our setting, it is typically the number of runs of reader is referred to the web version of this article.)
D. Sarkar et al. / Renewable Energy 97 (2016) 504e517 509
Table 2
2
s t;b ðxÞ;
xbt ¼ arg max b 2-WEC cluster iterations.
x2X
Iteration no. t 2t ct Þ
maxð m
with b varying from 1 to B 1. Under mild probabilistic assump- 1 0.00320 0.116084
tions the queries selected with this active learning strategy are 2 0.00001 0.121031
shown to converge to the global optimum of the unknown function
at a rate (tB)½ (with omission of logarithmic factors).
approximate the power captured by any layout in a fast and scalable
3.2.2. Experimental design manner. Once we trained the two statistical emulators of the per-
Since the GP-UCB-PE algorithm requires to fix the hyper- formance of a WEC inside or at an edge of an array, it is easy to sum
parameters of the GP, we first optimize their value on an initial data the outputs for the M WECs to get a prediction bq of the q ~ factor.
set constructed following a classical experimental design approach.
A simple choice would be a regular grid in which every coordinate
1 mod 0
is divided into a particular number of equally spaced intervals. But q x01 ; y01 ; …x0M ; y0M ¼ 1 þ
b b
q2 x2 x01 ; y02 y01
such an approach is highly inefficient because of the high compu- M
tational costs associated with it, e.g. if there are l input variables, mod 0
þb
q2 xM x0M1 ; y0M y0M1
each of which is divided into p equidistant, non-overlapping in-
tervals, then the total number of evaluations required to cover the X mod
M1
Fig. 7. Illustration of the crossover operation - (a) position of the m-th WEC of parent P1, (b) position of the m-th WEC of parent P2 and (c) position of the m-th WEC of the child.
(x0 (,m,UB), y0 (,m,UB)) and (x0 (,m,LB), y0 (,m,LB)) are the coordinates of the upper bound and lower bound at the location of the m-th WEC. The y0 coordinate of the m-th WEC of the child is
simply the average of the same of the parents. The x0 coordinate of the m-th WEC of the parents is first normalized with respect to the upper and lower bounds of the bathymetry,
such that the normalized values of x0 (,m,LB) and x0 (,m,UB), are 0 and 1, respectively. The average of the normalized x0 coordinate of the two parents is then computed and projected at
the y0 coordinate (y0C;m ) of the child and un-normalized, to obtain the location of the m-th WEC.
consider uniform spacing between the neighbouring devices. arrangement of the WECs and to demonstrate the robustness of the
However, there are now two parameters instead of one - x0d and y0d . presented methodology, we consider five different arbitrary ba-
The variation of b q with respect to the two spacing parameters is thymetry constraints which take account of the limitations in the
plotted in Fig. 13. For small distances of separation, the cumulative placement of the WECs due to depth variations. The centre of the
effect of the interactions on the performance of the array is mostly WECs must be located within the upper and lower bounds of the
destructive. The highest value of b q is not much different from that bathymetry constraints. The upper bound for the spatial extent of
of the inline case. In fact in Fig. 13, the x0 ¼ 0 m line corresponds to the wavefarm in the y0 direction (perpendicular to the direction of
the inline configuration. However, by staggering the array config- incident waves) is set at 2500 m.
urations, there is now a wider possible range of layouts by which
the maximum of b q can be achieved.
5.3.1. Genetic algorithm
Fig. 14 shows five layouts of wavefarms of 40 WECs with
5.3. Optimal layouts different bathymetry constraints, obtained after 100 (2 M) ¼ 8000
generations, that is over 16 million predictions. The optimum value
The optimization of the layouts of a wavefarm comprising of 40 of bq obtained for all the cases is similar. The layouts are well
WECs is considered in this work. In order to understand the general distributed along the y0 direction, so that the full spatial extent is
512 D. Sarkar et al. / Renewable Energy 97 (2016) 504e517
Fig. 8. In the mutation operation, n consecutive WECs (n ¼ 4) are randomly selected and replaced by a new distribution of the same number of WECs. In this figure, four consecutive
WECs, shown in blue in (a), are replaced by the new arrangement, shown in red in (b). The dashed red vertical lines, which are the edges of the WECs before and after the n
consecutive WECs indicate the y0 coordinate bounds within which the new configuration of the WECs is to be placed. (For interpretation of the references to colour in this figure
legend, the reader is referred to the web version of this article.)
mod
Fig. 9. Prediction of the performance ( b
q ) of the central WEC for the 3-WEC configuration using the leave-one-out scheme with 800 training examples.
properly used. Even in the case of the perfect inline and staggered while planning wavefarms and can be considered as a guideline for
layouts (see Figs. 12 and 13), we observe that close spacings lead to designers. Also note that b
q for the optimized layouts of the five
strong destructive influence on the overall performance of the bathymetry configurations is marginally less than the maximum b q
array. This suggests that clustering of devices should be avoided for the inline and staggered cases (maximum of b q 1.03, see
D. Sarkar et al. / Renewable Energy 97 (2016) 504e517 513
mod
Fig. 10. Prediction of the performance ( b
q ) of a WEC for the 2-WEC configuration using 200 training examples.
Fig. 11. The layout of an (a) inline and (b) staggered layout of an OWSC array with uniform spacings. The parameters x0d and y0d are the distances between the neighbouring WECs in
the x0 and y’ direction respectively.
Fig. 14. The optimal configuration of a wavefarm comprising of 40 OWSCs subject to various constraints, obtained with the presented methodology using genetic algorithm. The
OWSCs are shown in red. The blue and the pink coloured arbitrary curves indicate the upper and lower bathymetry constraints, respectively, and the centres of the WECs must lie
between them. In addition, the total extent of the wavefarm in the y0 direction must be less than 2500 m. The arrow from the top indicates the direction of incident waves. (For
interpretation of the references to colour in this figure legend, the reader is referred to the web version of this article.)
which can be considered as a combination of inline and slightly using a Monte Carlo type method. In this approach, b q is evaluated
staggered layouts, while following the bathymetry contours. for a particular number of randomly selected arrangement of the
To check the accuracy of the results, simulations of the identified WECs. The methodology to obtain the random distribution of the
optimal arrangement of WECs are performed using the mathe- WECs is the same as that used for the selection of initial points and
matical model of [9], where the interactions between all the WECs mutation operation of the GA. The layout corresponding to the
are accounted for. Table 3 shows the comparison of b q (predictions) maximum value of b q is considered to be the optimal arrangements
and q (simulations) for the optimal configurations identified by the of the WECs. Over 16 million evaluations (same number as that
GA. The good agreement between b q and q demonstrates the required with the GA approach) of the prediction function were
robustness of the methodology presented in this paper, despite the used for each case of the bathymetry. Fig. 15 plots the layout of the
use of a simplified interaction approach. optimal configurations obtained using the Monte Carlo approach.
The maximum of b q , corresponding to the optimal configurations
was always less than those obtained using the GA (see Table 4).
5.3.2. Monte Carlo optimization Notably, the arrangement of the WECs is much more arbitrary than
In order to check the effectiveness of the proposed optimization that of the latter (see Fig. 14).
methodology using GA, the same optimization is also performed In the recent work of [23], optimizations were performed on
small OWSC arrays (5 WECs) with equidistant spacings for some
specific layouts of the WECs. A different wave spectrum and a
Table 3
Comparison of b q (predictions) and q (simulations) for the optimal configurations slightly disparate configuration of the OWSCs were considered in
identified by the presented methodology. The q factors are obtained from the sim- the latter analysis, and optimal spacings of x0d z50m and y0d z65m
ulations of the mathematical model which considers the interactions between all were determined. These results are qualitatively close to the region
the WECs, while bq are the predictions using the simplified interaction approach. of constructive layouts identified in Fig. 13, although our analysis is
Bathymetry no. b
q q for larger wavefarms (40 OWSCs with a different configuration).
1 1.021 1.005
2 1.016 1.006 6. Discussion
3 1.012 1.006
4 1.014 1.003 The general approach of developing a statistical emulator and
5 1.02 1.004
then performing an optimization using genetic algorithm could be
D. Sarkar et al. / Renewable Energy 97 (2016) 504e517 515
Fig. 15. The optimal configurations obtained using a Monte Carlo type approach, with the number of evaluations of the prediction function being the same as that required using
GA. The maximum values of b q are less than that obtained using GA for all the five cases.
Fig. 16. The method can be extended to include the effect of the interaction of two of the nearest neighbours for a particular WEC. For such a system, a 5-WEC cluster models the
behavior of a WEC located well inside an array, a 4-WEC cluster models the second most extreme WEC and a 3-WEC cluster is used for the edge WECs. The coloured lines with
arrowheads indicate the interactions between the WECs.
clusters (dimension-4), although the number of samples used in using 3-WEC and 2-WEC clusters. The evaluations of the statistical
the latter case is much higher (3-WEC: 800 samples; 2-WEC: 200 emulators are quasi-instantaneous and so once the hyper-
samples). Increase in dimensionality and computational con- parameters of the GP are computed, one can immediately predict
straints can be a hindrance in performing more complex optimi- the variation for an unknown arrangement of the WECs. A recently
zation tasks. developed active learning strategy, the GP-UCB-PE algorithm, was
Our interaction model takes account of the most dominant then used to train the predictor in regions of interest of the prob-
interaction effects (from each side) on any particular OWSC. In lem. The algorithm focuses on the maxima and regions of high
general, it provides fairly accurate predictions, however there can uncertainty of the function. This in-turn enables the algorithm to
be a reduction in the prediction accuracy for closely spaced array make better predictions in the process of determining the optimal
configurations i.e. negligible separation between the edges of the layout of the WECs. The predictions of the statistical emulator are
neighbouring OWSCs. Even in such situations, the interaction ef- reasonably good despite the complexity of the problem and small
fects on particular OWSCs are strongest due its neighbouring de- number of training data used.
vices, with the influence of next-to-neighbouring devices being Variation of the performance of an inline and a staggered array
significantly less. Construction of a better prediction model would of 40 WECs and uniform spacing is analysed using the prediction
involve the consideration of 5-WECs system (see Fig. 16) to model function. The b q factor for the inline configuration has a maximum
WECs well inside the array (2 WECs on each side instead of 1 as for for a separation distance of 76.5 m between the centres of the
3-WECs system), 4-WECs system to predict the performance of neighbouring WECs. Optimization of the layout of a wavefarm
WECs just beside the ones at the edges and a 3-WECs configuration comprising of 40 WECs with arbitrary bathymetry constraints and
for prediction of the edge WECs. Fig. 16 illustrates the interaction space limitations is then performed using a genetic algorithm. It is
model. Such an analysis would obviously require much computa- shown that it is possible to achieve a b q factor greater than one even
tional resources, time and increase in complexity of machine with various restrictions. It is also suggested that clustering of de-
learning algorithm due to the increase in size of the input param- vices is to be avoided while designing layouts of wave energy
eter space. The latter approach would have been necessitated if the converter arrays.
effect of the interactions was such that very close spacings led to Another significant advantage of the presented methodology is
better cumulative performance of the OWSCs. However, in the its scalability to large problems. The prediction formulation once
present problem, close spacings led to destructive interaction effect developed needs no modification, and optimization using GA can
on the array performance, and the optimization algorithm auto- be performed for a wavefarm with an arbitrary number of WECs
matically selects locations with moderate spacing between the and constraints. A similar approach of decomposing a problem into
devices (demonstrating constructive interaction effects). smaller problems and applying machine learning/optimization
The developments in this work can have several implications. techniques may be pursued in solving other problems in the field of
Besides providing a procedure for optimization, the analysis can marine renewable energy research.
offer some practical guidelines to wavefarm developers in
designing arrays - closed spacings are to be avoided and slightly Acknowledgements
staggered configurations should be preferred. The presented
methodology can also support inclusion of experimental observa- The authors would like to thank Mr. Cedric Malherbe of ENS-
tions into the optimization procedure e.g. experimental analysis Cachan for fruitful discussions. The first author would like to
can be performed on small OWSC (2e3 WEC clusters) and the re- thank ENS-Cachan for hosting him during the period of this
sults could then be used to optimize large arrays. In general, many research work. This work is supported by Science Foundation
problems related to ocean engineering/wave energy require eval- Ireland (SFI) under the research project High-end computational
uation of costly functions (simulation models). Surrogate models modelling for wave energy systems (Grant number SFI/10/IN.1/
based on GP can be used to mimic the outcome of the simulations. 12996) in collaboration with Marine Renewable Energy Ireland
(MaREI), the SFI Centre for Marine Renewable Energy Research
-Grant number SFI/12/RC/2302.
7. Conclusion
References
A methodology for the prediction and optimization of layouts of
WECs in a wave farm is presented using an innovative active [1] K. Budal, Theory for absorption of wave power by a system of interacting
learning approach. The predictions are performed using a GP bodies, J. Ship Res. 21 (4) (1977).
regression method. Such a strategy is relevant when the perfor- [2] M. Simon, Multiple scattering in arrays of axisymmetric wave-energy devices.
Part 1. A matrix method using a plane-wave approximation, J. Fluid Mech. 120
mance of similar layouts of WECs are strongly correlated. The (1982) 1e25.
problem is simplified into an additive model with local interaction [3] H. Kagemoto, D. Yue, Interactions among multiple three-dimensional bodies
D. Sarkar et al. / Renewable Energy 97 (2016) 504e517 517
in water waves: an exact algebraic method, J. Fluid Mech. 166 (1) (1986) [16] A.G. Wilson, R.P. Adams, Gaussian process kernels for pattern discovery and
189e209. extrapolation, in: Proceedings of the 30th International Conference on Ma-
[4] S. Mavrakos, P. Koumoutsakos, Hydrodynamic interaction among vertical chine Learning, Atlanta, Georgia, USA, 2013.
axisymmetric bodies restrained in waves, Appl. Ocean Res. 9 (3) (1987) , Quasi-newton methods, motivation and theory, SIAM
[17] J.E. Dennis Jr., J.J. More
128e140. Rev. 19 (1) (1977) 46e89.
[5] S. Mavrakos, Hydrodynamic coefficients for groups of interacting vertical [18] T. Stefanakis, E. Contal, N. Vayatis, F. Dias, C. Synolakis, Can small islands
axisymmetric bodies, Ocean. Engg 18 (5) (1991) 485e515. protect nearby coasts from tsunamis? an active experimental design
[6] B. Child, V. Venugopal, Optimal configurations of wave energy device arrays, approach, Proc. R. Soc. A 470 (2172) (2014) 20140575.
Ocean. Engg 37 (16) (2010) 1402e1417. [19] M. Mitchell, An Introduction to Genetic Algorithms, MIT press, 1998.
[7] T. Whittaker, M. Folley, Nearshore oscillating wave surge converters and the [20] E. Renzi, A. Abdolali, G. Bellotti, F. Dias, Wave-power absorption from a finite
development of Oyster, Philos. T Roy. Soc. A 370 (1959) (2012) 345e364. array of oscillating wave surge converters, Renew. Energy 63 (2014) 55e68.
[8] E. Renzi, F. Dias, Resonant behaviour of an oscillating wave energy converter [21] E. Renzi, F. Dias, Relations for a periodic array of oscillating wave energy
in a channel, J. Fluid Mech. 701 (2012) 482e510. converters, Appl. Ocean. Res. 39 (2013) 31e39.
[9] D. Sarkar, E. Renzi, F. Dias, Wave farm modelling of oscillating wave surge [22] E. Renzi, F. Dias, Motion-resonant modes of large articulated damped oscil-
converters, Proc. R. Soc. A 470 (2167) (2014) 20140118. lators in waves, J. Fluids Struct. 49 (2014) 705e715.
[10] E. Contal, D. Buffoni, A. Robicquet, N. Vayatis, Parallel gaussian process opti- [23] I. Noad, R. Porter, Optimisation of arrays of flap-type oscillating wave surge
mization with pure exploration, in: Proceedings of ECML, 2013. converters, Appl. Ocean Res. 50 (2015) 237e253.
[11] D. Sarkar, E. Renzi, F. Dias, Wave power extraction by an oscillating wave [24] E. Renzi, F. Dias, Hydrodynamics of the oscillating wave surge converter in the
surge converter in random seas, in: Procedings of the ASME 2013 32nd In- open ocean, Eur. J. Mech. B-Fluids 41 (2013) 1e10, http://dx.doi.org/10.1016/
ternational Conference on Ocean, Offshore and Artic Engineering (OMAE j.euromechflu.2013.01.007.
2013), Nantes, France, 2013. [25] D. Sarkar, K. Doherty, F. Dias, The modular concept of the oscillating wave
[12] Y. Goda, A comparative review on the functional forms of directional wave surge converter, Renew. Energy 85 (2016) 484e497.
spectrum, Coast. Eng. J. 41 (1999) 1e20. [26] P. Sammarco, S. Michele, M. d’Errico, Flap gate farm: from Venice lagoon
[13] A. Babarit, Impact of long separating distances on the energy production of defense to resonating wave energy production. Part 1: Natural modes, Appl.
two interacting wave energy converters, Ocean. Engg 37 (2010) 718e729. Ocean Res. 43 (2013) 206e213.
[14] C. Rasmussen, C. Williams, Gaussian Processes for Machine Learning, the MIT [27] S. Michele, P. Sammarco, M. d’Errico, E. Renzi, A. Abdolali, G. Bellotti, et al.,
Press, 2006. Flap gate farm: from Venice lagoon defense to resonating wave energy pro-
[15] D.J. MacKay, Introduction to gaussian processes, NATO ASI Ser. F Comput. Syst. duction. Part 2: Synchronous response to incident waves in open sea, Appl.
Sci. 168 (1998) 133e166. Ocean Res. 52 (2015) 43e61.