Received: April 16, 2020. Revised: July 3, 2020.

286

Darts Game Optimizer: A New Optimization Technique Based on Darts Game

Mohammad Dehghani1* Zeinab Montazeri1 Hadi Givi2

3 4
Josep M. Guerrero Gaurav Dhiman

1
Department of Electrical and Electronics Engineering, Shiraz University of Technology, Shiraz, Iran
2
Department of Electrical Engineering, Faculty of Engineering,
University of Shahreza, Shahreza 86481-41143, Iran
3
Center for Research on Microgrids (CROM), Department of Energy Technology,
Aalborg University, Aalborg, Denmark
4
Department of Computer Science, Government Bikram College of Commerce, Patiala, Punjab 147004, India
* Corresponding author’s Email: [email protected]

Abstract: In this paper, a novel game-based optimization technique entitled darts game optimizer (DGO) is proposed.
The novelty of this investigation is DGO designing based on simulating the rules of Darts game. The key idea in DGO
is to get the most possible points by the players in their throws towards the game board. Simplicity of equations and
lack of control parameters are the main features of the proposed algorithm. The ability and quality of DGO performance
in optimization is evaluated on twenty-three objective functions, and then is compared with eight other optimization
algorithms including Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Gravitational Search Algorithm
(GSA), Teaching Learning-Based Optimization (TLBO), Grey Wolf Optimizer (GWO), Grasshopper Optimization
Algorithm (GOA), Whale Optimization Algorithm (WOA), and Marine Predators Algorithm (MPA). The results of
simulation and comparison indicate the superiority and optimal quality of the proposed DGO algorithm over the
mentioned algorithms.
Keywords: Optimization, Optimizer, Darts game, Darts game optimizer, Game-based algorithm.

1. Introduction 1.2 Background

1.1 Motivation In general, optimization algorithms can be

categorized into four groups including physics-based,
There are many optimization problems in swarm-based, evolutionary-based, and game-based
different disciplines of science and technology that algorithms.
need to be solved using appropriate optimization Physics-based algorithms are designed based on
methods. Hence, employing an effective optimization simulation and application of existing laws in physics.
algorithm is of great importance for solving such For example, the spring search algorithm (SSA) is
problems. In this regard, optimization algorithms designed using Hawk's law in the weight and spring
have been applied by scientists in various fields such system. In SSA, the members of the population are a
as energy [1], protection [2], electrical engineering number of weights that are connected to each other
[3-6], energy carriers [7,8], and data mining [9] to by a spring and the optimal answer is provided by
achieve the optimal solution. This issue motivates reaching the equilibrium point [10, 11]. Some of the
researchers to focus on optimization studies, other algorithms in this category are Ray
modification of existing methods, and especially Optimization (RO) algorithm [12], Black Hole (BH)
introduction of new optimization methods. algorithm [13], Artificial Chemical Reaction
Optimization Algorithm (ACROA) [14], Charged
International Journal of Intelligent Engineering and Systems, Vol.13, No.5, 2020 DOI: 10.22266/ijies2020.1031.26
Received: April 16, 2020. Revised: July 3, 2020. 287

System Search (CSS) [15], Curved Space This study proposes a new game-based
Optimization (CSO) [16], Galaxy-based Search optimization algorithm called Darts Game Optimizer
Algorithm (GbSA) [17], Small World Optimization (DGO), which is designed based on simulation of the
Algorithm (SWOA) [18], and Gravitation Search attractive Darts game. The population members in the
Algorithm (GSA) [19]. proposed algorithm are darts players, who try to
Swarm-based algorithms have been introduced collect the most points in their throws towards the
based on careful attention towards natural game board. In optimization problems, this effort can
phenomena such as animal social behaviors, insects’ be modelled to obtain an algorithm to reach the
behaviors, and various plant processes. Particle optimal solution.
swarm optimization (PSO) is one of the most popular
techniques in this category. Simulation of movements 1.4 Paper structure
and behaviors of birds has been used in PSO
designing [20]. Artificial Bee Colony (ABC) [21], In the continuation of this article, darts game is
Spotted Hyena Optimizer (SHO) [22], Bat-inspired first introduced in section 2. The design steps of the
Algorithm (BA) [23], Emperor Penguin Optimizer proposed algorithm are described in Section 3. The
(EPO) [24], Cuckoo Search (CS) algorithm [25], simulation and evaluation of the proposed algorithm
‘Following’ Optimization Algorithm (FOA) [26], are accomplished in Section 4. Finally, conclusions
Grey Wolf Optimizer (GWO) [27], Group and suggestions are expressed in Section 5.
Optimization (GO) [28], Donkey Theorem
Optimization (DTO) [29], Rat Swarm Optimizer 2. Darts game
(RSO) [30], Grasshopper Optimization Algorithm Darts is a sport that everyone enjoys it regardless
(GOA) [31], and Ant Colony Optimization (ACO) of age or gender. Although this game seems simple,
[32, 33] also belong to this category. the skill of the players has an important effect on the
In Evolutionary-based algorithms, evolution of a collection of points. The equipment of Darts game
population is considered in order to create new includes a dartboard and darts, which are shown in
generations of genetically superior individuals [34]. Fig. 1. Based on the division, the dartboard has 82
Genetic Algorithm (GA) [35], which is one of the areas with different points. According to Fig. 2, the
oldest-known techniques is among these algorithms. scoring method for each throw is that the inner bull
The GA is designed by simulating three phases of has 50 and the outer bull has 25 points. The score of
selection, crossover, and mutation. Some other each sector is written above it. If the darts hit the inner
algorithms of this type are Evolution Strategy (ES) narrow ring, the score is tripled, and if they hit the
[36], Biogeography-based Optimizer (BBO) [37], outer narrow ring, the score is doubled. The important
Genetic Programming (GP) [38], and Differential thing is that the center of the dartboard is the fifth
Evolution (DE) [39]. highest scoring area of the game. This issue is
Game-based algorithms have been proposed explained by the fact that the areas of sectors 20, 19,
based on modeling the rules and the behavior of 18, and 17 each have 60, 57, 57, and 51 points,
players in different games. For example, Shell Game respectively.
Optimization (SGO) [40] is based on shell game
modeling. In SGO, players try to find the object 3. Darts game optimizer (DGO)
hidden under one of the three shells. Orientation
Search Algorithm (OSA) [41, 42], Hide Objects In this section, the potential of Darts game is
Game Optimization (HOGO) [43], and Dice Game
Optimizer (DGO) [44] are also in this category.

1.3 Contribution

Numerous studies and investigations have been

conducted by researchers in the field of optimization
to present effective optimization algorithms.
Although different games can be a good source for
designing optimization algorithms, researchers have
paid less attention to this potential. Therefore, the
authors of this article are interested in designing a
game-based algorithm. Figure. 1 Equipment of darts game

International Journal of Intelligent Engineering and Systems, Vol.13, No.5, 2020 DOI: 10.22266/ijies2020.1031.26
Received: April 16, 2020. Revised: July 3, 2020. 288

Table 1. Information of different sectors in the dartboard

Angel interval
sector Area (mm2)
(degree)
Inner bull 0 ≤ Ɵ ≤ 360 506.7075
Outer bull 0 ≤ Ɵ ≤ 360 2.6702×10+3
Inner single
0 ≤ Ɵ ≤ 18 910.1131
score
Outer single
0 ≤ Ɵ ≤ 18 5.3535×10+3
score
double ring 0 ≤ Ɵ ≤ 18 556.6902
treble ring 0 ≤ Ɵ ≤ 18 278.9734

Figure. 2 Scoring method for darts game Here 𝐹𝑏𝑒𝑠𝑡 represents the best fitness function
value, 𝑋𝑏𝑒𝑠𝑡 is the best variables’ values, 𝐹𝑤𝑜𝑟𝑠𝑡 is
applied to design and introduce a new optimizer. the worst fitness function value, 𝑋𝑤𝑜𝑟𝑠𝑡 is the worst
Searcher agents in DGO are the players in this game variables’ values, 𝐹 𝑛 is the normalize value of fitness
and their goal is to get the highest score (optimal functions, and 𝑃𝑖 is the probability function of 𝑖 th
answer). player.
3.1 Mathematical modelling For all dartboards, dimensions follow a standard
as follows:
The population of the players is modeled with a • Inside measurement of double and treble ring:
matrix, each row of which represents one player and 8mm
each column represents the different characteristics • Inside diameter of bull: 12.7mm
of each player. The number of columns in this matrix • Inside diameter of outer bull: 31.8mm
is actually the same as the number of problem • Center bull to the inside edge of treble wire:
variables and the values suggested for these variables. 107mm
The players' matrix is specified using (1). • Center bull to outside edge bull wire: 170mm
• Outside edge of the double wire to outside edge of
𝑋1 𝑥11 ⋯ 𝑥1𝑑 ⋯ 𝑥1𝑚 double wire: 340mm
⋮
|
⋮ ⋱ ⋮ ⋰ ⋮ • Overall dartboard diameter: 451mm
𝑋 = 𝑋𝑖 𝑥𝑖1 ⋯ 𝑥𝑖𝑑 ⋯ 𝑥𝑖𝑚 (1) As mentioned in the previous section, the
|
⋮ ⋮ ⋰ ⋮ ⋱ ⋮ Dartboard has 82 areas with different scores. Each
1
[ 𝑋𝑁 𝑥𝑁 ⋯ 𝑥𝑁𝑑 ⋯ 𝑥𝑁𝑚 ] player can throw three darts in each iteration. The
location of the darts on the Dartboard depends on two
Here 𝑋 is the players' matrix, 𝑥𝑖𝑑 is the 𝑑 th factors: player skill and chance.
dimension of 𝑖th player, m is the number of variables, There are six types of sectors with different areas
and N is the number of players. on the Dartboard as specified in Table 1.
By placing 𝑋𝑖 in the fitness function, useful Therefore, the throwing score is modelled and
information is obtained, which is presented in (2) to calculated for each player using (8) to (11).
(7).
𝐶𝑖 = 𝑟𝑜𝑢𝑛𝑑(82 × (1 − 𝑃𝑖 )) (8)
𝐹𝑏𝑒𝑠𝑡 = min(𝑓𝑖𝑡)𝑁×1 (2)
𝑆(1: 𝐶), 𝑟𝑎𝑛𝑑 < 𝑃𝑖
𝑆𝐶𝑖 = { (9)
𝑋𝑏𝑒𝑠𝑡 = 𝑋(𝑙𝑜𝑐𝑎𝑡𝑖𝑜𝑛 𝑜𝑓 min(𝑓𝑖𝑡) , 1: 𝑚) (3) 𝑆(𝐶 + 1: 82), 𝑒𝑙𝑠𝑒

𝐹𝑤𝑜𝑟𝑠𝑡 = max(𝑓𝑖𝑡)𝑁×1 (4) 𝑠𝑖 = 𝑆𝐶𝑖 (𝑘) & 1 ≤ 𝑘 ≤ 82 (10)

𝑋𝑤𝑜𝑟𝑠𝑡 = 𝑋(𝑙𝑜𝑐𝑎𝑡𝑖𝑜𝑛 𝑜𝑓 max(𝑓𝑖𝑡) , 1: 𝑚) (5) ∑3throws=1 𝑠𝑖throws

𝑠𝑖𝑛 = (11)
180
𝑓𝑖𝑡−𝐹𝑤𝑜𝑟𝑠𝑡
𝐹 𝑛 = ∑𝑁 (6)
𝑗=1(𝑓𝑖𝑡𝑗 −𝐹𝑤𝑜𝑟𝑠𝑡 ) Here 𝑆𝐶𝑖 denotes the score candidates for 𝑖 th
player, 𝑆 is the score matrix, which is sorted from
𝐹𝑛 high scores to low scores, 𝑠𝑖 is the score for each
𝑃𝑖 = max𝑖(𝐹𝑛 ) (7)
throw of 𝑖th player, and 𝑠𝑖𝑛 is the normalized score of
𝑖th player.
International Journal of Intelligent Engineering and Systems, Vol.13, No.5, 2020 DOI: 10.22266/ijies2020.1031.26
Received: April 16, 2020. Revised: July 3, 2020. 289

Finally, the new status of each player and in fact, 2 presents the results of testing the proposed
the values of the problem variables are updated using algorithm and the eight aforementioned algorithms
(12). on these functions, which indicates the significant
superiority of the proposed algorithm for this type of
𝑋𝑖 = 𝑋𝑖 + 𝑟𝑎𝑛𝑑(1, 𝑚) × (𝑋𝑏𝑒𝑠𝑡 − 3𝑠𝑖𝑛 𝑋𝑖 ) (12) objective functions.

3.2 Steps of DGO 4.2 Performance evaluation on multimodal

functions F8-F13
After modelling the proposed DGO algorithm, it
can be used to solve various optimization problems. Objective functions F8 to F13 are in this group,
The DGO has some basic parameters that need to which have several local solutions. Therefore, by
be determined. The number of members in the implementing optimization algorithms on this type of
algorithm population is 50 players and the number of objective functions, exploration capability can be
repetitions of the algorithm as a stop condition for the evaluated. The results of this evaluation are presented
algorithm is considered as 1000 repetitions. The in Table 3, which shows the strong performance of
initial population of players is created at random at the proposed algorithm compared to the other
the beginning of the algorithm. algorithms.
Each player in the suggested algorithm is actually
an m-member vector that represents a suggested 4.3 Performance evaluation on fixed-dimension
answer to the problem. The members of this vector multimodal functions F14-F23
show the problem variables that are evaluated by
DGO and eight other algorithms have been
placing them in the objective function.
evaluated on the functions in this category. These
The various steps in implementing the DGO are
functions have lower dimension of variables in
as follows:
comparison with the previous two categories. The
Start DGO
obtained results in Table 4 indicate the superiority of
Step1: Creating the initial population of players.
the proposed algorithm for F14 to F23.
Step2: Calculating the fitness function.
Step3: Updating 𝐹𝑏𝑒𝑠𝑡 , 𝑋𝑏𝑒𝑠𝑡 , 𝐹𝑤𝑜𝑟𝑠𝑡 , and 𝑋𝑤𝑜𝑟𝑠𝑡 4.4 Theoretical analysis
using (2) to (5).
Step4: Updating 𝐹 𝑛 and 𝑃𝑖 using (6) and (7). As can be seen from the numerical analysis, the
Step5: Calculating 𝑠𝑖𝑛 using (8) to (11). proposed DGO algorithm has an acceptable
Step6: Updating 𝑋𝑖 using (12). advantage over the other eight algorithms. The two
Step7: Checking the stop condition. most important indicators for evaluating exploration
Step8: Printing solution. algorithms are exploitation and exploration capacities.
End DGO Exploitation capacity indicates the algorithm's
ability to achieve the optimal answer. The Unimodal
4. Simulation study and discussion objective functions are used to evaluate this index.
The results in Table 2 indicate the appropriate
In this section, the performance of DGO is
exploitation capacity of the proposed DGO algorithm
evaluated and compared with eight other algorithms
compared to other algorithms.
considering twenty-three standard objective
Exploratory capacity indicates the accurate search of
functions. These objective functions are categorized
the search space, which prevents the algorithm from
into Unimodal [45,46], Multimodal [46,47], and
getting stuck in a local area. The Multimodal and
Fixed-dimension Multimodal [46]. Eight algorithms
Fixed-dimension Multimodal test functions are used
including GA, PSO, GSA, TLBO, GWO, GOA,
to evaluate this index. The results in Table 3 and
WOA, and MPA are considered to compare the
Table 4 indicate the appropriate exploration capacity
optimization results. The average (Ave) and standard
of the proposed algorithm compared to other
deviation (std) of the best optimal solution are
algorithms.
utilized for evaluation.
The authors have been working in the field of
4.1 Performance evaluation on unimodal optimization to develop game-based optimization
functions F1-F7 algorithms. Several algorithms such as OSA, BOSA,
HOGO, and SGO have been proposed in our previous
The objective functions F1 to F7 are used to researches. In the study of optimization algorithms, it
evaluate the exploitation ability of optimization is important to note that no algorithm is necessarily
algorithms in achieving the optimal response. Table the best one. Optimization algorithms provide quasi-
International Journal of Intelligent Engineering and Systems, Vol.13, No.5, 2020 DOI: 10.22266/ijies2020.1031.26
Received: April 16, 2020. Revised: July 3, 2020. 290

optimal answers, so researchers try to propose new

algorithms to improve the efficiency. The main

F7

F6

F5

F4

F3

F2

F1
advantage of the proposed algorithm, in addition to
its superiority in numerical analysis, is the simplicity

Ave

Ave

Ave

Ave

Ave

Ave

Ave
std

std

std

std

std

std

std
of the equations and its implementation, as well as the
lack of any control parameters.

7.70×10-10
5.10×10-17
6.53×10-18
2.01×10-11
1.95×10-12
4.16×10+1
5.57×10+2
5.67×10+1
9.17×10+1
3.29×10-3
6.79×10-4
9.98×10-2
3.15×10-1

7.36×10-9
5. Conclusions

GA
The authors' contribution in this paper is
presenting a new game-based optimization algorithm
named Darts Game Optimizer (DGO). The
innovation of the proposed method is design of a new

3.89×10+1
4.93×10+1

1.40×10+1
2.87×10-2
6.92×10-2
1.78×10-8
9.23×10-9

1.72×10-1
6.00×10-1

1.84×10-3
7.29×10-4
1.40×10-8
4.98×10-9
optimization technique based on simulating the Darts

PSO
7.13
game, in which players try to get the most points from
Dart's throws. The mathematical modelling and the
steps of implementing the proposed algorithm were
thoroughly described. In order to evaluate the

4.00×10-17
1.08×10-16

6.10×10-17
1.16×10-16
proposed algorithm, a collection of twenty-three

3.47×10+1
3.85×10+1

1.56×10+2
4.16×10+2
7.68×10-1

9.89×10-1

9.29×10-1
1.70×10-1

GSA
Table 2. Evaluation results on unimodal functions F1-F7
2.77

1.12
objective functions were considered as case studies in
three different categories including unimodal,
Multimodal, and Fixed-dimension Multimodal test
functions. DGO was implemented on this set of
objective functions, and to show its effectiveness, the
1.98×10+3
7.37×10+2

1.87×10+1
3.89×10+3
4.91×10+3
5.79×10-2
3.88×10-2
9.75×10-1

8.57×10-5
3.23×10-5
1.06×10-1
3.55×10-2
TLBO
results were compared with eight other algorithms 4.88

8.21
including Genetic Algorithm (GA), Particle Swarm
Optimization (PSO), Gravitational Search Algorithm
(GSA), Teaching Learning Based Optimization
(TLBO), Grey Wolf Optimizer (GWO), Grasshopper
1.43×10+2
1.18×10+2

4.31×10+1
7.43×10-3
2.02×10-2
9.98×10-2
3.15×10-1

2.50×10-1
8.80×10-1

1.41×10-1
3.96×10-1
1.11×10-1
2.81×10-1
Optimization Algorithm (GOA), Whale Optimization

GOA
8.97

Algorithm (WOA), and Marine Predators Algorithm

(MPA). The results confirmed the superiority of the
proposed algorithm and its ability of exploration and
exploitation for solving different optimization
1.70×10-18
8.18×10-17

7.18×10-17

6.59×10-28
2.97×10+2
8.91×10+2

7.91×10+1
1.89×10-1
5.37×10-3

1.19×10-1
8.73×10-1

3.29×10-6
2.90×10-2

6.34×10-5

problems compared to the mentioned algorithms. GWO

In addition to the results of experiments and
numerical analysis that indicated the superiority of
the DGO algorithm, a theoretical analysis was
performed on the proposed algorithm, which
represented excellence and features of the DGO
2.39×10-21
1.06×10-21
4.91×10-30
1.41×10-30
2.79×10+1
1.14×10-3
1.42×10-3
5.32×10-1

7.63×10-1

3.97×10-1
7.25×10-2
2.93×10-6
5.39×10-7

WOA

algorithm such as simplicity of the equations and

3.11

implementation, lack of any control parameters, and

good exploitation and exploration capacities.
For future works, the authors propose several
ideas for investigation. One can create a binary
1.42×10-12
1.57×10-12
4.61×10-21
3.27×10-21
1.91×10-1
3.98×10-1
4.22×10-1

9.25×10-9
1.0×10-3
1.8×10-3

2.6×10-8

variant of DGO as an important potential contribution.

46.049

0.1444
0.0864

MPA

DGO may also be used to overcome many-objective

real-life optimization as well as multi-objective
problems.

Conflicts of Interest
9.55×10-24
1.99×10-25

4.63×10-10
1.30×10-11
7.22×10-11
4.32×10-10
1.42×10-20
1.57×10-23
4.61×10-40
3.27×10-45
2.30×10+1

DGO
5.00×10-4
9.00×10-4

2.11×10-1

The authors declare no conflict of interest.

International Journal of Intelligent Engineering and Systems, Vol.13, No.5, 2020 DOI: 10.22266/ijies2020.1031.26
291

DOI: 10.22266/ijies2020.1031.26
Table 4. Evaluation results on fixed-dimension multimodal functions F14-F23
GA PSO GSA TLBO GOA GWO WOA MPA DGO
Ave 4.39 2.77 3.61 6.79 9.98×10+1 1.26 2.11 9.98×10-1 9.98×10-1
F14
std 4.41×10-2 2.32 2.96 1.12 9.14×10-1 6.86×10-1 2.49 2.47×10-13 5.24×10-20
Ave 7.36×10-2 9.09×10-3 6.84×10-2 5.15×10-2 7.15×10-2 1.01×10-2 3.66×10-3 8.21×10-3 2.65×10-4
F15
std 2.39×10-3 2.38×10-3 7.37×10-2 3.45×10-3 1.26×10-1 3.75×10-3 7.60×10-2 4.09×10-15 3.65×10-19
Ave -1.02 -1.02 -1.02 -1.01 -1.02 -1.02 -1.02 -1.02 -1.03
F16
std 4.19×10-7 0.00 0.00 3.64×10-8 4.74×10-8 3.23×10-5 7.02×10-9 4.46×10-16 1.25×10-20
Ave 3.98×10-1 3.98×10-1 3.98×10-1 3.98×10-1 3.98×10-1 3.98×10-1 3.98×10-1 3.98×10-1 3.98×10-1
F17
std 3.71×10-17 9.03×10-16 1.13×10-16 9.45×10-15 1.15×10-7 7.61×10-4 7.00×10-5 9.12×10-15 6.45×10-20
Ave 3.00 3.00 3.00 3.00 3.00 3.00 3.00 3.00 3.00
F18
std 6.33×10-7 6.59×10-5 3.24×10-2 1.94×10-10 1.48×10+1 2.25×10-5 7.16×10-6 1.95×10-15 7.49×10-17
Ave -3.81 -3.80 -3.86 -3.73 -3.77 -3.75 -3.84 -3.86 -3.86
F19
std 4.37×10-10 3.37×10-15 4.15×10-1 9.69×10-4 3.53×10-7 2.55×10-3 1.57×10-3 2.42×10-7 8.62×10-13

International Journal of Intelligent Engineering and Systems, Vol.13, No.5, 2020

Ave -2.39 -3.32 -1.47 -2.17 -3.23 -2.84 -2.98 -3.32 -3.32
F20
std 4.37×10-1 2.66×10-1 5.32×10-1 1.64×10-1 5.37×10-2 3.71×10-1 3.76×10-1 1.14×10-11 2.91×10-19
Ave -5.19 -7.54 -4.57 -7.33 -7.38 -2.28 -7.05 -8.11 -10.12
F21
std 2.34 2.77 1.30 1.29 2.91 1.80 3.62 2.53×10-11 7.54×10-19
Ave -2.97 -8.55 -6.58 -1.00 -8.50 -3.99 -8.18 -10.01 -10.40
F22
std 1.37×10-2 3.08 2.64 2.89×10-4 3.02 1.99 3.82 2.81×10-11 7.28×10-13
Ave -3.10 -9.19 -9.37 -2.46 -8.41 -4.49 -9.34 -10.41 -10.51
F23
std 2.37 2.52 2.75 1.19 3.13 1.96 2.41×10-4 3.89×10-11 1.95×10-14
Revised: July 3, 2020.

Table 3. Evaluation results on multimodal functions F8-F13

GA PSO GSA TLBO GOA GWO WOA MPA DGO
Ave -5.11×10+2 -5.01×10+2 -2.75×10+2 -3.81×10+2 -6.92×10+2 -6.12×10+1 -5.10×10+2 -8.36×10+2 -9.52×10+3
F8
std 4.37×10+1 4.28×10+1 5.72×10+1 2.83×10+1 9.19×10+1 3.94×10+1 6.95×10+2 8.11×10+2 8.13×10-1
Ave 1.23×10-1 1.20×10-1 3.35×10+1 2.23×10+1 1.01×10+2 3.10×10-1 0 0 0
F9
std 4.11×10+1 4.01×10+1 1.19×10+1 3.25×10+1 1.89×10+1 3.91×10+1 0 0 0
Ave 5.31×10-11 5.20×10-11 8.25×10-9 1.55×10+1 1.15 1.06×10-13 7.40 9.69×10-12 3.12×10-25
F10
1.11×10-10 1.08×10-10 1.90×10-9 7.87×10-1 4.34×10-2 6.13×10-12 6.07×10-20
Received: April 16, 2020.

std 8.11 9.89

Ave 3.31×10-6 3.24×10-6 8.19 3.01×10-1 5.74×10-1 2.49×10-3 2.89×10-4 0 0
F11
std 4.23×10-5 4.11×10-5 3.70 2.89×10-1 1.12×10-1 1.34×10-4 1.58×10-3 0 0
Ave 9.16×10-8 8.93×10-8 2.65×10-1 5.21×10+1 1.27 1.34×10-2 3.39×10-1 8.50×10-3 8.57×10-4
F12
std 4.88×10-7 4.77×10-7 3.14×10-1 2.47×10+2 1.02 6.23×10-2 2.14×10-1 5.20×10-3 8.25×10-4
Ave 9.39×10-1 8.26×10-1 5.73 2.81×10+2 6.60×10-2 6.54×10-1 1.89 9.90×10-1 2.51×10-3
F13
std 4.49×10-2 4.39×10-2 8.95 8.63×10+2 4.33×10-2 4.47×10-3 2.66×10-1 1.93×10-1 2.62×10-5
Received: April 16, 2020. Revised: July 3, 2020. 292

Author Contributions Engineering and Innovation (KBEI), Tehran,

Iran, pp. 0215-0219, 2017.
Conceptualization, M. Dehghani, Z. Montazeri, [6] Z. Montazeri and T. Niknam, “Optimal
and J. M. Guerrero.; methodology, M. Dehghani and Utilization of Electrical Energy from Power
Z. Montazeri.; software, M. Dehghani and H. Givi.;
Plants Based on Final Energy Consumption
validation, J. M. Guerrero, H. Givi, and G. Dhiman.;
Using Gravitational Search Algorithm”,
formal analysis, H. Givi and G. Dhiman.; Электротехника и Электромеханика, No. 4,
investigation, M. Dehgani and Z. Montazeri.; pp. 70-73, 2018.
resources, J. M. Guerrero.; data curation, H. Givi and [7] M. Dehghani, Z. Montazeri, A. Ehsanifar, A.
G. Dhiman; writing—original draft preparation, M. Seifi, M. Ebadi, and O. Grechko, “Planning of
Dehghani and Z. Montazeri.; writing—review and Energy Carriers Based on Final Energy
editing, H. Givi and G. Dhiman.; visualization, M. Consumption Using Dynamic Programming and
Dehghani.; supervision, M. Dehghani.; project Particle Swarm Optimization”,
administration, M. Dehghani and Z. Montazeri; Электротехника и Электромеханика, No. 5,
funding acquisition, J. M. Guerrero.
pp. 62-71, 2018.
[8] Z. Montazeri and T. Niknam, “Energy Carriers
Acknowledgments Management Based on Energy Consumption”,
J. M. Guerrero was supported by VILLUM In: Proc. of IEEE 4th International Conf. on
FONDEN under the VILLUM Investigator Grant (no. Knowledge-Based Engineering and Innovation
25920): Center for Research on Microgrids (CROM); (KBEI), Tehran, Iran, pp. 539-543, 2017.
www.crom.et.aau.dk [9] Y. Djenouri, A. Belhadi, and R. Belkebir, “Bees
Swarm Optimization Guided by Data Mining
References Techniques for Document Information
Retrieval”, Expert Systems with Applications,
[1] M. Dehghani, Z. Montazeri, and O. P. Malik, Vol. 94, pp. 126-136, 2018.
“Energy Commitment: A Planning of Energy [10] M. Dehghani, Z. Montazeri, A. Dehghani, N.
Carrier Based on Energy Consumption”, Nouri, and A. Seifi, “BSSA: Binary Spring
Электротехника и Электромеханика, No. 4, Search Algorithm”, In: Proc. of IEEE 4th
pp. 69-72, 2019. International Conf. on Knowledge-Based
[2] A. Ehsanifar, M. Dehghani, and M. Engineering and Innovation (KBEI), Tehran,
Allahbakhshi, “Calculating The Leakage Iran, pp. 0220-0224, 2017.
Inductance for Transformer Inter-Turn Fault [11] M. Dehghani, Z. Montazeri, A. Dehghani, and A.
Detection Using Finite Element Method”, In: Seifi, “Spring Search Algorithm: A New Meta-
Proc. of Iranian Conf. on Electrical Engineering Heuristic Optimization Algorithm Inspired by
(ICEE), Tehran, Iran, pp. 1372-1377, 2017. Hooke's Law”, In: Proc. of IEEE 4th
[3] M. Dehghani, Z. Montazeri, and O. P. Malik, International Conf. on Knowledge-Based
“Optimal Sizing and Placement of Capacitor Engineering and Innovation (KBEI), Tehran,
Banks and Distributed Generation in Iran, pp. 0210-0214, 2017.
Distribution Systems Using Spring Search [12] A. Kaveh and M. Khayatazad, “A New Meta-
Algorithm”, International Journal of Emerging Heuristic Method: Ray Optimization”,
Electric Power Systems, Vol. 21, No. 1, Computers & Structures, Vol. 112, pp. 283-294,
20190217, 2020. 2012.
[4] M. Dehghani, Z. Montazeri, O. P. Malik, K. Al- [13] A. Hatamlou, “Black Hole: A New Heuristic
Haddad, J. M. Guerrero, and G. Dhiman, “A Optimization Approach for Data Clustering”,
New Methodology Called Dice Game Optimizer Information Sciences, Vol. 222, pp. 175-184,
for Capacitor Placement in Distribution 2013.
Systems”, Электротехника и [14] B. Alatas, “ACROA: Artificial Chemical
Электромеханика, No. 1, pp. 61-64, 2020. Reaction Optimization Algorithm for Global
[5] S. Dehbozorgi, A. Ehsanifar, Z. Montazeri, M. Optimization”, Expert Systems with
Dehghani, and A. Seifi, “Line Loss Reduction Applications, Vol. 38, pp. 13170-13180, 2011.
and Voltage Profile Improvement in Radial [15] A. Kaveh and S. Talatahari, “A Novel Heuristic
Distribution Networks Using Battery Energy Optimization Method: Charged System Search”,
Storage System”, In: Proc. of IEEE 4th Acta Mechanica, Vol. 213, pp. 267-289, 2010.
International Conf. on Knowledge-Based [16] F. F. Moghaddam, R. F. Moghaddam, and M.
Cheriet, “Curved Space Optimization: A
International Journal of Intelligent Engineering and Systems, Vol.13, No.5, 2020 DOI: 10.22266/ijies2020.1031.26
Received: April 16, 2020. Revised: July 3, 2020. 293

Random Search Based on General Relativity [29] M. Dehghani, M. Mardaneh, O. P. Malik, and S.
Theory”, arXiv preprint arXiv:1208.2214, 2012. M. NouraeiPour, “DTO: Donkey Theorem
[17] H. Shah-Hosseini, “Principal Components Optimization”, In: Proc. of 27th Iranian Conf.
Analysis by the Galaxy-Based Search on Electrical Engineering (ICEE), Yazd, Iran,
Algorithm: A Novel Metaheuristic for pp. 1855-1859, 2019.
Continuous Optimisation”, International [30] G. Dhiman, M. Garg, A. Nagar, V. Kumar, and
Journal of Computational Science and M. Dehghani, “A Novel Algorithm for Global
Engineering, Vol. 6, pp. 132-140, 2011. Optimization: Rat Swarm Optimizer”, Journal
[18] H. Du, X. Wu, and J. Zhuang, “Small-World of Ambient Intelligence and Humanized
Optimization Algorithm for Function Computing, 2020.
Optimization”, In: Proc. of International Conf. [31] S. Saremi, S. Mirjalili, and A. Lewis,
on Natural Computation, pp. 264-273, 2006. “Grasshopper Optimisation Algorithm: Theory
[19] E. Rashedi, H. Nezamabadi-Pour, and S. and Application”, Advances in Engineering
Saryazdi, “GSA: A Gravitational Search Software, Vol. 105, pp. 30-47, 2017.
Algorithm”, Information Sciences, Vol. 179, pp. [32] M. Dorigo and T. Stützle, “Ant Colony
2232-2248, 2009. Optimization: Overview and Recent Advances”,
[20] R. Eberhart and J. Kennedy, “A New Optimizer In: Handbook of Metaheuristics, ed: Springer,
Using Particle Swarm Theory”, In: Proc. of Sixth pp. 311-351, 2019.
International Symposium on Micro Machine and [33] H. Givi, M. A. Noroozi, B. Vahidi, J. S.
Human Science, pp. 39-43, 1995. Moghani, and M. A. V. Zand, “A Novel
[21] D. Karaboga and B. Basturk, “Artificial Bee Approach for Optimization of Z-Matrix
Colony (ABC) Optimization Algorithm for Building Process Using Ant Colony Algorithm”,
Solving Constrained Optimization Problems”, Journal of Basic and Applied Scientific
In: Proc. of International Fuzzy Systems Research, Vol. 2, No. 9, pp. 8932-8937, 2012.
Association World Congress, pp. 789-798, 2007. [34] N. E. Karkalos, A. P. Markopoulos, and J. P.
[22] G. Dhiman and V. Kumar, “Spotted Hyena Davim, “Evolutionary-Based Methods”, In:
Optimizer: A Novel Bio-Inspired Based Computational Methods for Application in
Metaheuristic Technique for Engineering Industry 4.0, ed: Springer, pp. 11-31, 2019.
Applications”, Advances in Engineering [35] K. S. Tang, K.-F. Man, S. Kwong, and Q. He,
Software, Vol. 114, pp. 48-70, 2017. “Genetic Algorithms and Their Applications”,
[23] X.-S. Yang, “A New Metaheuristic Bat-Inspired IEEE Signal Processing Magazine, Vol. 13, pp.
Algorithm”, In: Nature Inspired Cooperative 22-37, 1996.
Strategies for Optimization (NICSO 2010), ed: [36] H. G. Beyer and H.-P. Schwefel, “Evolution
Springer, pp. 65-74, 2010. Strategies–A Comprehensive Introduction”,
[24] G. Dhiman and V. Kumar, “Emperor Penguin Natural Computing, Vol. 1, pp. 3-52, 2002.
Optimizer: A Bio-Inspired Algorithm for [37] S. Mirjalili, “Biogeography-Based
Engineering Problems”, Knowledge-Based Optimisation”, In: Evolutionary Algorithms and
Systems, Vol. 159, pp. 20-50, 2018. Neural Networks, ed: Springer, pp. 57-72, 2019.
[25] A. H. Gandomi, X.-S. Yang, and A. H. Alavi, [38] J. R. Koza, “Genetic Programming: A Paradigm
“Cuckoo Search Algorithm: A Metaheuristic for Genetically Breeding Populations of
Approach to Solve Structural Optimization Computer Programs to Solve Problems”,
Problems”, Engineering with Computers, Vol. Stanford University, Department of Computer
29, pp. 17-35, 2013. Science, 1990.
[26] M. Dehghani, M. Mardaneh, and O. P. Malik, [39] R. Storn and K. Price, “Differential Evolution-A
“FOA: Following’ Optimization Algorithm for Simple and Efficient Adaptive Scheme for
Solving Power Engineering Optimization Global Optimization over Continuous Spaces
Problems”, Journal of Operation and [r]”, Berkeley: ICSI, 1995.
Automation in Power Engineering, Vol. 8, No. 1, [40] M. Dehghani, Z. Montazeri, and O. P. Malik, H.
pp. 57-64, 2020. Givi, and J. M. Guerrero, “Shell Game
[27] S. Mirjalili, S. M. Mirjalili, and A. Lewis, “Grey Optimization: A Novel Game-Based Algorithm”,
Wolf Optimizer”, Advances in Engineering International Journal of Intelligent Engineering
Software, Vol. 69, pp. 46-61, 2014. and Systems, Vol. 13, No. 3, pp. 246-255, 2020.
[28] M. Dehghani, Z. Montazeri, A. Dehghani, and O. [41] M. Dehghani, Z. Montazeri, O. P. Malik, A.
P. Malik, “GO: Group Optimization”, Gazi Ehsanifar, and A. Dehghani, “OSA: Orientation
University Journal of Science, Vol. 33, 2020. Search Algorithm”, International Journal of
International Journal of Intelligent Engineering and Systems, Vol.13, No.5, 2020 DOI: 10.22266/ijies2020.1031.26
Received: April 16, 2020. Revised: July 3, 2020. 294

Industrial Electronics, Control and

Optimization, Vol. 2, No. 2, pp.99-112, 2019.
[42] M. Dehghani, Z. Montazeri, O. P. Malik, G.
Dhiman, and V. Kumar, “BOSA: Binary
Orientation Search Algorithm”, International
Journal of Innovative Technology and Exploring
Engineering (IJITEE), Vol. 9, pp. 5306-5310,
2019.
[43] M. Dehghani, Z. Montazeri, S. Saremi, A.
Dehghani, O. P. Malik, K. Al-Haddad, J. M.
Guerrero, “HOGO: Hide Objects Game
Optimization”, International Journal of
Intelligent Engineering and Systems, Vol. 13,
2020.
[44] M. Dehghani, Z. Montazeri, and O. P. MALIK,
“DGO: Dice Game Optimizer”, Gazi University
Journal of Science, Vol. 32, pp. 871-882, 2019.
[45] J. G. Digalakis and K. G. Margaritis, “On
Benchmarking Functions for Genetic
Algorithms”, International Journal of Computer
Mathematics, Vol. 77, No. 4, pp. 481-506, 2001.
[46] G. G. Wang, A. H. Gandomi, X.-S. Yang, and A.
H. Alavi, “A Novel Improved Accelerated
Particle Swarm Optimization Algorithm for
Global Numerical Optimization”, Engineering
Computations, Vol. 31, No. 7, pp. 1198-1220,
2014.
[47] X. S. Yang, “Firefly Algorithm, Stochastic Test
Functions and Design Optimisation”,
International Journal of Bio-Inspired
Computation, Vol. 2, No. 2, pp. 78-84, 2010.

International Journal of Intelligent Engineering and Systems, Vol.13, No.5, 2020 DOI: 10.22266/ijies2020.1031.26