LouWei1
HuRong1,*
LuoGang2
YangRui2
-
(Power System Technology Support Center, East China Branch of State Grid Corporation
of China, Shanghai 200120, China)
-
(Power Grid Business Unit, Beijing Tsintergy Technology Co., Ltd., Beijing 100084,
China )
Copyright © The Institute of Electronics and Information Engineers(IEIE)
Keywords
Improved ABC algorithm, Load, Power dispatch, Search factor
1. Introduction
The large-scale extraction and use of fossil fuels have led to their sharp depletion
worldwide. In addition, the use of fossil fuels directly causes environmental issues,
such as haze, acid rain, and global warming, which threaten sustainable human development
and species diversity. A sustainable development model with better quality and structure
is a major development goal in society. The rational utilization of resources is a
major research focus. Therefore, the rational utilization of power resources has attracted
increasing attention [1,2]. Power resource scheduling is a vital optimization problem in power systems. The
purpose is to allocate reasonably the power generated by each unit to minimize costs.
Such allocation is significant in the rational utilization of energy, equipment, and
cost savings. The development of the power industry has basically solved the shortage
of power supply. The main problems faced by the power grid-scheduling department of
contemporary power enterprises are how to fully utilize the power grid, an intelligent
and intensive power supply, reduce the loss of electricity during transmission, and
achieve maximum profits and benefits for enterprises. The dynamic economic dispatch
(DED) of power resources is crucial in the power system operation. The demand for
electricity resources is enormous. The dynamic economic dispatch of power resources
can minimize the electricity cost and balance the demand for power resources [3,4]. Dynamic power economic dispatch can be seen as a nonlinear, nonconvex, and large-scale
optimization problem with various complex constraints [5]. Several methods have been used to solve power system optimization problems, including
traditional technology and artificial intelligence technology. These methods are being
improved and developed to handle large-scale power systems. On the other hand, existing
power resource scheduling methods have low efficiency and cannot reasonably meet the
actual demand for power resources. Therefore, a power resource-scheduling model based
on the Artificial Bee Colony (ABC) was constructed. A power dispatch model based on
the improved ABC was designed to respond to the local convergence problem that is
prone to occur in the operation of ABC. This method is expected to achieve dynamic
and stable operation of power resources, reduce the operating costs of the power system,
and achieve reasonable allocation and utilization of power resources. The paper consists
of four parts. The first section summarizes the relevant research on power resource
scheduling and ABC. The second section constructs a power dispatch model based on
an improved ABC. The third part reports the experimental verification of the performance
of the model. The fourth part summarizes the research and proposes the future research
direction.
There were two main innovations in this research. The first used the ABC model to
calculate and analyze the power resource scheduling. The second introduced a search
factor and a local optimal solution selection strategy to optimize the ABC algorithm
and improve the accuracy and performance of the model.
The contributions of the research were as follows. First, the wavelet decomposition
method was used to preprocess the power load data. Therefore, an improved ABC algorithm
was studied to construct a power-scheduling model. The accurate and efficient analysis
results of power resource scheduling were obtained, supporting more efficient power
resource allocation.
2. Related Works
Power dispatch can effectively achieve a balance between power customers, power resource
utilization efficiency, and environmental pollution emissions. Many scholars have
conducted intensive studies on the reasonable scheduling of power resources to enhance
the stability of the power grid. Jusoh MA et al. proposed a control strategy for hybrid
energy storage systems to mitigate the long and short-run output power fluctuations
of the photovoltaic system. In the control scheme, battery energy storage eliminates
the long-term output power fluctuations, while supercapacitors compensate for short-term
output power fluctuations. The simulation evaluation confirmed that it effectively
alleviates the output power fluctuations of the photovoltaic system. The simulation
reduced unacceptable output power fluctuations [6]. Chen G et al. proposed a new optimal power-scheduling model for regional cooling
systems to address air conditioning energy consumption scheduling. The model optimizes
the water temperature and mass flow rate to maximize energy efficiency. According
to the findings, it can save half the time and cost [7]. Zhang B B et al. proposed a wind farm active power dispatch algorithm based on a
grey correlation. The fluctuations of active power in wind farms were smaller [8]. Luo S et al. established a multi-objective complex constraint optimization model
of a 24-hour period to address the instability of microgrid power generation technology.
Interval optimization was used to address the uncertainty of renewable energy. Fuzzy
membership and the Chebyshev function were applied to the decomposition of multi-objective
optimization problems in parallel. A multi-objective evolutionary algorithm (MOEA)
based on hybrid decomposition was designed. Compared to other algorithms, the MOEA
is more effective [9]. Li X P et al. proposed a hierarchical reactive power optimal dispatching method
for distribution networks based on differential evolution. The upper layer minimizes
the loss of the distribution network. Each microgrid was considered a generator node,
determining the interaction power. The lower level minimizes the grid loss of the
microgrid. The penalty function ensured that the lower power satisfied the upper constraints.
According to the findings, it enhanced the economy of the distribution system and
shortened operating time [10].
ABC is used widely in data optimization to obtain global optimal solutions by optimizing
the individual behavior of artificial bees. Sefati S et al. proposed a new routing
scheme with load balancing capability using the Markov Model and ABC (MMABC). MMABC
was applied to search for the best candidate node for each cluster. The simulation
results showed that it outperformed existing methods in energy efficiency [11]. Wang L Y et al. used an improved derivative-free ABC and self-help method to estimate
the parameters of the weighted least squares method (WLSM). According to the outcomes,
it could obtain consistent results with the WLSM without multiple formula deductions,
providing new ideas for parameter estimation [12]. Tong A X et al. proposed a method that combines the improved adaptive ABC (IAABC)
with the BP-ANN to improve the classification performance of backpropagation artificial
neural networks. The method had better performance according to the outcomes [13]. Wang H et al. proposed an improved high-dimensional multi-objective ABC. The resources
were allocated dynamically during the reconnaissance bee phase. The performance was
superior to other existing methods according to the outcomes [14]. Gurjinder S et al. used ABC to optimize the image histograms. The proposed method
enhanced the contrast while maintaining the brightness of the input image. The performance
was superior to other existing methods [15].
In summary, previous research results have been achieved in the dispatch of power
resources. On the other hand, improving the performance and efficiency of power resource
scheduling has been a research focus of scholars at home and abroad. Many scholars
have conducted extensive optimization research to improve the performance of power
dispatch, but there is insufficient analysis of relevant data on the power loads.
Most of the research focuses on optimizing the operation of the power grid. At the
same time, the ABC algorithm has apparent advantages in data optimization, which is
used widely in various data analyses. Therefore, the ABC algorithm has been used innovatively
to construct a power resource-scheduling model and solve the above problems. Corresponding
optimization strategies were introduced to overcome the shortcomings of the ABC algorithm
in the application process. It is expected to improve the efficiency and performance
of power resource scheduling using this method and efficiently allocate power resources.
3. Construction of Power Dispatching Method based on Improved ABC
A power dispatch model based on ABC was constructed to achieve better power dispatch.
In response to the shortcomings of the ABC algorithm in practical use, this chapter
provides a detailed construction of an improvement method based on the ABC algorithm.
3.1 Preprocessing of Power Load Data
Power load calculation is a fundamental link in achieving power dispatch. Accurate
power load data can help the power grid achieve a balanced distribution of supply
and demand, ensuring reasonable power dispatch. The electrical load data was first
preprocessed to improve the accuracy of power dispatch [16]. The wavelet decomposition method is a method for analyzing and processing non-stationary
signals. The charge data was analyzed by introducing the wavelet decomposition method
to decompose the original signal into high-frequency (HFS) and low-frequency (LFS)
signals. Among them, HFS and LFS underwent drastic and stable changes in a short period,
respectively. Therefore, the power data processed using the wavelet decomposition
method can be applied effectively to analyze the impact factors of power load changes.
Fig. 1 presents the electrical load data processing method based on wavelet decomposition.
Fig. 1. Power load data processing process based on wavelet decomposition.
The initial power data signal $A_{1}$ is decomposed to HFS $A_{1}$ and LFS $D_{1}$.
The HFS continues to decompose to generate new HFS $A_{2}$ and LFS $D_{2}$. The HFS
is decomposed until a noise interference signal is obtained, as expressed in (1).
where $D$ represents a LFS. $A$ represents a HFS. $H'$ is a high-pass filter. $G'$
is a low-pass filter. $A_{m}$ represents the HFS component when the resolution is
$2m$. $D_{m}$ represents the LFS component. The impact of different influencing factors
on electrical load varies in magnitude. Therefore, after processing the charge data
using the wavelet decomposition method, the Pearson correlation coefficient is used
to calculate the correlation $fit_{i}$ of each influencing factor on the electrical
load data. (2) illustrates the calculation method.
where $X$ and $Y$ are two random variables. $E$ is the expected value. $\sigma X$
and $\sigma Y$ are the standard deviations. $\mathrm{cov}$ is the covariance. The
correlation was determined using (2). Table 1 lists the corresponding relationship between the correlation coefficient $r$ and
the correlation.
Table 1. Correlation Coefficient and Correlation Degree.
When decomposing electric load data, the main process includes feature analysis, feature
decomposition, and feature selection of electric load data. In the feature decomposition
process, errors will occur as decomposition times increase. Residual sequences were
calculated to reduce the errors and the impact of decomposition errors on the decomposition
times [17]. Fig. 2 presents the overall decomposition process of electrical load data features.
In the process shown in Fig. 2, the power load data was first subjected to feature analysis ( ). The wavelet transform
was used for feature decomposition to obtain corresponding high-frequency and low-frequency
signal data. The Pearson correlation coefficient was used to calculate various electrical
load data correlations. Based on the Pearson correlation coefficient degree, the calculation
results were judged. The appropriate weights were retained. Finally, the process was
concluded.
Fig. 2. Process of feature decomposition.
DED is meaningful for the operation of power systems. The objective function of DED
is the total production cost of $N$ generator units in $T$. The production cost can
be approximated as the quadratic function of the active power output of the generator
set, as shown in (3).
where $T$ represents the total scheduling time. $i=1,2,3,\ldots ,N$. $N$ denote the
online generator units to be dispatched. v represents the energy consumption coefficient.
$P_{ih}$ represents the actual output power of the generator (MW).
3.2 Construction of Power Dispatching Model based on ABC Algorithm
The power dispatch model in the power grid system belongs to a non-deterministic polynomial
problem. Their difficulty and computational complexity are increasing rapidly with
the increasing complexity of planning problems. Determining the optimal solution in
complex situations is meaningful for solving the scheduling problems. ABC is a Swarm
intelligence optimization algorithm with fewer control parameters, strong robustness,
and a simple structure. The ABC algorithm consists of three stages: leading bees to
find food sources (FSs) and calculating fitness values, following bees to find the
new FS and updating them based on fitness values, and detecting bees to find the new
FS [18]. In the ABC, the FS is located where the optimal solution is located. A point in
the space corresponding to the location of the FS is represented as $\left\{x_{id}\left|
i=1,2,3,\ldots ,M\right.\right\}$. The fitness $fit_{i}$ stands for the quality of
the FS. $M$ is for the FS. When solving optimization problems, every point in space
may become the optimal solution. The location initialization of the FS is expressed
as (4).
where $d$ stands for the dimension of the individual vector. In the search space,
$U_{d}$ represents the upper limit, and $L_{d}$ denotes the lower limit. $rand(0,1)$
is a random number between $fit_{i}$. Guide bees search randomly for a new FS around
the FS, as shown in (5).
where $\varphi $ represents a random number in $\left[-1,1\right]$. $i$ and $j$ are
random integers between $\left[1,N\right]$. If the fitness value of the new FS found
by the leading bee is higher than $x_{id}$, it follows the new FS. On the other hand,
the initial FS will still be used. The probability of selecting a new FS during this
process is expressed as (6).
According to the roulette strategy, $r$ is generated randomly in $\left[0,1\right]$.
This value is compared with $P_{i}$. If $P_{i}>r$, the FS is updated; otherwise, the
existing FSs continue to be used. According to roulette, FSs with better fitness values
are selected. The parameter $trial$ in the FS represents the number of times the FS
has not been updated. If the FS has not been updated, then $trial$ = 0. If the FS
is updated, then $trial$ = 1. During the search process, the FS undergoes $trial$
iterations. Before reaching the threshold $\lim it$, it is determined if there are
FSs with better fitness values. If there is a better FS, it will be updated according
to (2); otherwise, the existing FSs are abandoned. Through self-feedback, leading bees become
reconnaissance bees, searching for new FSs, according to (7).
Fig. 3 shows the basic process of the ABC.
Fig. 3. Artificial bee colony algorithm process.
3.3 Construction of Power Dispatching Model based on the Improved ABC
In the human bee colony algorithm, the leading and following bees are half the total
number of bees. This situation can easily lead to insufficient global search ability
and low efficiency [19]. At the same time, there are also shortcomings when using (7) to develop FSs. When the threshold reaches its limit, the mutation ability of the
ABC is insufficient, resulting in low local search accuracy. Therefore, an improved
bee colony optimization algorithm (IBCOA) is proposed to overcome the shortcomings
of the ABC optimization algorithm in practical use. The adaptive factor $\varphi $
of traditional artificial bee colony algorithms is a random number distributed between
$\left[-1,1\right]$. The search range is not controlled, resulting in low convergence
efficiency. Therefore, the study introduces the search factor $u$ without affecting
the randomness of $\varphi $. The adjustment formula for the search factor $u$ is
expressed as (8).
where $fit_{i}$ is the fitness of the FS after the previous iteration of the leading
bee. $k$ represents a random number that can be adjusted. The index function ensures
that the search scope can be effectively expanded in the early stage. After introducing
the search factor $u$, the leading bee updates the FS using (9).
where the fitness value of the FS determines the search range of the ABC. In the early
stage, if the fitness value of the FS is relatively small and the objective function
value is large, the search range will be expanded to increase the probability of obtaining
the optimal solution. During the following bee search, if the fitness value is high
and the distance from the local optimal solution is small, the search range is reduced
to improve the speed of the following bee to find the global optimal solution. Introducing
search factors can balance global development and local search capabilities. The ABC
is completed mainly by the leading and following bees when searching for the optimal
solution [20]. Therefore, a selection strategy for local optimal solutions is introduced, which
is expressed as (10).
where $X_{P(i),d}$ is the local optimal solution used when updating the FS. The FS
updated by the leader bee is the local optimal solution if the fitness value searched
by the leader bee is greater than the local optimal solution during the iteration
process. The initial FS is considered the local optimal solution if the fitness value
is less than the local optimal value in the existing iteration. The formula for updating
FSs that can reduce the search time by following bees during the exploration phase
is expressed as (11).
where the leader bee provides the location $x_{id}$ of the FS after the information
exchange. This location is updated to the local optimal solution location $X_{P(i),d}$
found by the leader bee. Each update was completed around the local optimal solution.
A search factor $u$ was also added to the adaptive factor $\varphi $. When approaching
the global optimal solution, the fitness increases, the search factor $u$ decreases,
and the change amplitude decreased. As it gradually approached the optimal target
value, the following bee searches continuously to improve the probability of the algorithm
obtaining the optimal value. At the same time, the speed is also more ideal. Fig. 4 presents the specific implementation process of the IBCOA algorithm.
Fig. 4. Implementation of the IBCOA algorithm.
4. Performance Analysis of Power Dispatching Model based on Improved ABC
Relevant experiments were designed to evaluate the performance and prove the availability
of the power dispatch model based on the improved ABC proposed in the study. The experiments
were applied to actual power dispatch. The obtained power dispatch situation was analyzed
to verify the performance.
4.1 Electrical Load Data Preprocessing Analysis based on Wavelet Decomposition Method
Experiments are designed to validate the power dispatch model and prove the availability
of the model. First, the performance of the preprocessing method for electrical load
data based on wavelet decomposition was verified. The experiment used the electricity
load data of a certain power company in A city in 2019 as a sample. The data were
the electricity load for 2019, recorded hourly with 24 pieces of data per day. Eight
thousand seven hundred and sixty pieces of data were collected throughout the year,
measured in kW·h, which is the electricity consumption per hour. Table 2 lists the specific power load data.
Table 2. 2019 Electricity Load Data of Electric Power Company (kW·h) (Partial).
Time
|
00:00:00
|
01:00:00
|
02:00:00
|
...
|
21:00:00
|
22:00:00
|
23:00:00
|
2019/1/1
|
6758.26
|
7405.10
|
6879.26
|
...
|
7302.87
|
6845.63
|
6938.71
|
2019/1/2
|
6831.74
|
6819.23
|
6894.57
|
...
|
7437.81
|
7068.06
|
7002.06
|
2019/1/3
|
7288.03
|
7819.58
|
7061.06
|
...
|
7432.64
|
6994.55
|
7385.29
|
2019/1/4
|
6806.91
|
6728.64
|
6654.23
|
...
|
7364.50
|
6876.08
|
6823.14
|
2019/1/5
|
7201.22
|
7317.06
|
6981.79
|
...
|
6879.46
|
6975.68
|
7006.87
|
The power load data obtained in actual use generally contains much noise. Therefore,
the proposed wavelet decomposition method was used to analyze the power load data.
After decomposition, three component sequences were obtained: one low-frequency component
and two high-frequency components. These three component sequences can exhibit different
patterns of power load data variations. Fig. 5 presents the decomposition results. Fig. 5(a) depicts the time series diagram of the original signal data. Fig. 5(b) shows the low-frequency time series obtained from the wavelet decomposition. Fig. 5(c) represents the first high-frequency time series diagram from the wavelet decomposition.
Fig. 5(d) presents the second high-frequency time series diagram of the wavelet decomposition.
The relevant power load data was divided accurately into high-frequency and low-frequency
sequences. The subsequent power dispatch models can effectively support the scheduling
analysis of power load data.
Fig. 5. Original data and wavelet decomposition time sequence diagram.
The accuracy of the wavelet transform algorithm used was tested. The model parameters
of the final wavelet transform algorithm obtained through model training and parameter
adjustment were as follows. The learning rate of the low-frequency time series was
0.0005. The learning rate of the high-frequency detail sequence was 0.001. The time
steps were all one. The number of neurons was 250. The batch sizes were all 256. The
dropout was 0.25, which means randomly removing 25\% of neurons. The training duration
epochs were all 300. Fig. 6 shows the error change in training and verification of each subsequence. In Fig. 6, the low-frequency sequence converged from 0.03 and 0.015 in the training and validation
sets, respectively. Both eventually converge to 0.0015, with small fluctuations throughout
the entire process. The first high-frequency sequence converged from 0.035 and 0.004
in the training and validation sets, respectively. Ultimately, they all converged
to 0.001, with small fluctuations occurring after 210 iterations. The second high-frequency
training converged from 0.005 and 0.0005 in the training and validation sets, respectively.
The final convergence value of both was 0.0001. There were no significant fluctuations
throughout the entire iteration process. Overall, the training errors under the three
conditions stabilized and approached zero in the validation and testing sets. Hence,
the fitting ability of the three sequence models was good, and the training effect
was ideal. The obtained training data can be used for testing the power dispatch model.
Fig. 6. Error of Subsequence in the training and verification sets.
4.2 Application Analysis of Improved ABC Algorithm in Power Dispatch Model
After preprocessing the data using the above methods, the performance of the power
dispatch model based on the improved ABC was verified. The test environment was set
as follows. The simulation environment was that the processor was Inter(R) Core (TM)i5-4590S3.00G
Hz, and the operating system was Windows 7. The programming software was MATLAB R2014a.
In the experiment, IBCOA was compared with the ABC and the improved algorithm based
on hierarchical optimization (HABC) to verify the competitiveness of the algorithm.
First, six benchmark functions were used to analyze the accuracy of the proposed algorithm.
The six benchmark functions were the Sphere function (f$_{1}$), Rosenbrock function
(f$_{2}$), Quartic function (f$_{3}$), Griewink function (f$_{4}$), Shifted and Rotated
Rastigins Function (f$_{5}$), and Shifted and Rotated Levy Function (f$_{6}$). Table 3 lists the test results in six benchmark functions. From Table 3, the IBCOA was superior to the other optimization methods. In particular, in the
f$_{1}$ and f$_{6}$ functions, the accuracy reached 10$^{-16}$ and 10$^{-15}$, respectively.
Hence, the IBCOA algorithm can achieve high optimization accuracy.
Table 3. Test results from six benchmark functions.
Function
|
Algorithm
|
Maximum
|
minimum
|
Average
|
Variance
|
Sphere
|
IBCOA
|
5.25E-16
|
1.43E+2
|
2.73E-2
|
1.78E-7
|
ABC
|
6.22E+5
|
1.45E-2
|
4.56E+2
|
1.37E+9
|
HABC
|
2.33E +4
|
2.27E-12
|
9.41E+3
|
1.46E+6
|
Rosenbrock
|
IBCOA
|
5.21E+3
|
2.00E-15
|
4.45E-5
|
1.41E-5
|
ABC
|
2.89E+8
|
1.49E+1
|
1.56E+6
|
1.47E+7
|
HABC
|
1.11E+5
|
3.22E-3
|
4.54E+4
|
4.51E+4
|
Quartic
|
IBCOA
|
4.49E+3
|
2.05E-14
|
4.32E-1
|
4.24E-2
|
ABC
|
4.68E+2
|
8.74E+1
|
7.46E+2
|
7.45E+3
|
HABC
|
3.45E+1
|
1.94E-10
|
1.09E+1
|
1.12E+1
|
Griewank
|
IBCOA
|
1.20E+2
|
1.22E-15
|
1.10E-1
|
1.10E-1
|
ABC
|
6.45E-1
|
5.89E-6
|
3.37E-3
|
3.39E-3
|
HABC
|
1.87E-7
|
4.69E-4
|
1.76E-5
|
1.72E-5
|
Shifted and Rotated Rastrigins
|
IBCOA
|
1.31E+2
|
5.45E-11
|
4.04E-6
|
4.04E-6
|
ABC
|
2.08E+1
|
7.45E+1
|
1.62E+1
|
1.62E+1
|
HABC
|
1.47E+2
|
1.78E+1
|
4.39E+1
|
4.39E+1
|
Shifted and Rotated Levy
|
IBCOA
|
3.06E-15
|
1.46E+3
|
8.45E-3
|
8.45E-3
|
ABC
|
2.12E+3
|
8.59E-4
|
1.78E+2
|
1.78E+2
|
HABC
|
2.06E+2
|
2.88E-1
|
3.12E+1
|
3.12E+1
|
The proposed power dispatching methods were compared using common methods, including
the Whale Optimization Algorithm (WOA), Fruit Fly Optimization Algorithm (FOA), and
Particle Swarm Optimization (PSO). Fig. 7 shows the convergence rate of this method in the six different reference functions.
In the f$_{1}$ function, the loss values of the four types of power dispatch models
decreased gradually as the iterations increased. Among them, the loss values of FOA
and PSO models were relatively close. The trend of the change was consistent. The
loss value of the IBCOA algorithm proposed in this study was significantly lower than
other methods. In the f$_{2}$ function, the PSO algorithm remained at 10$^{10}$. The
WOA algorithm converged from 10$^{10}$. The FOA and IBCOA algorithms converged from
10$^{8}$. The IBCOA algorithm had the best convergence effect when the function iteration
value was 10$^{3}$. The minimum loss value was 10$^{4}$. In the f$_{3}$ function,
both PSO and FOA algorithms converged from 10$^{11}$. The WOA algorithm converged
from 10$^{10}$. The IBCOA algorithm converged from 10$^{5}$. The loss value was significantly
lower than the other three methods. In the f$_{\mathrm{4-}}$f$_{6}$ functions, the
IBCOA algorithm exhibited the best convergence performance. This suggests the proposed
IBCOA power dispatch model exhibits good convergence performance under different benchmark
function conditions.
Fig. 7. Convergence rate of the different algorithms.
The proposed algorithm was then applied to power dispatch. In this experiment, each
algorithm ran independently 50 times under 1000 iterations. The population size was
30, 50, 100, and 500 respectively. Fig. 8 shows the fitting effect of the obtained power dispatch model. When the population
size was 30, the convergence changes in the FOA and WOA models were consistent, without
significant differences. The IBCOA algorithm showed the best performance. At this
point, all four methods changed smoothly, and the convergence effect was not significant.
When the population size was 50, after 10 iterations, except for the PSO algorithm,
all three other methods began to converge. The convergence rate was fast. The convergence
performance of IBCOA was superior to the other methods. The loss value was 10$^{4}$
when the iterations reached 10$^{3}$. All four methods began to converge when the
population size was 100. After 10$^{3}$ iterations, however, the final loss of the
IBCOA was 10$^{2}$, which is significantly below the other methods. The initial loss
value of the IBCOA algorithm was the smallest when the population size was 500. On
the other hand, the convergence rate was slow. Overall, when the population size was
100, the IBCOA algorithm showed the best performance. In addition, the IBCOA algorithm
achieved significantly better quality and computational efficiency than other methods
when the objective function became complex. Therefore, the IBCOA algorithm is an important
tool for solving more complex optimization problems in power systems.
Fig. 8. Convergence of different scales in power dispatch.
The IBCOA algorithm is used for power dispatch experiments. Table 4 lists the experimental results under different population sizes. For the DED, a lower
cost of electricity was obtained. In actual power dispatch, the variance value was
the smallest when the population was 100, indicating that the data was relatively
more stable and less volatile at this time. In terms of the DED problem, the improved
algorithm was more suitable for power dispatch to achieve cost reduction. These results
confirmed that the IBCOA method has robustness, higher solution quality, and higher
computational efficiency than the original ABC algorithm.
Table 4. Experimental results of the IBCOA algorithm in power dispatch.
Population size
|
Maximum value
|
Minimum value
|
Average
|
Variance
|
30
|
8.25E+0.2
|
8.67E+0.3
|
2.05E +0.4
|
9.78E+0.1
|
50
|
4.46E+0.4
|
7.95E+0.8
|
4.25E+0.4
|
7.62E+0.5
|
100
|
6.25E+0.5
|
2.12E+0.7
|
1.32E+0.6
|
4.15E+0.4
|
500
|
1.98E+0.2
|
1.41E+0.5
|
1.35E+0.4
|
9.42E+0.2
|
Five units were selected to participate in the simulation test. Fig. 9 shows the convergence and optimization results of the proposed IBCOA algorithm. The
convergence iteration of the PSO algorithm was 46 times (Fig. 9(a)). During the iteration process, there was always a local optimal situation. The convergence
iteration of the WOA algorithm was the same as that of the FOA algorithm. The IBCOA
algorithm proposed in this study had the smallest convergence iteration, which was
15 times, avoiding local optima. The IBCOA algorithm proposed in this study had the
lowest cost, 853.4903 million yuan (Fig. 11(b)). The IBCOA algorithm proposed in the
study took the least time, 9.33ms (Fig. 11(c)), indicating the best performance of
the algorithm.
Fig. 9. Convergence and optimization results of the IBCOA.
Fig. 10. Thermal power plant output and system cost under different scale base station energy storage.
The IBCOA algorithm proposed in the study was applied to power dispatch. Fig. 10 shows the output and system cost of thermal power plants under different scale base
station energy storage. Significant differences in the output energy of thermal power
plants were observed under different units (Fig. 10(a)). A larger base station scale in the same unit meant less energy from the thermal
power plant outputs. Under the energy storage of 200000 base stations, Unit 5 had
the lowest energy output of 111.00 MW. The maximum output of Unit 1 thermal power
plant was 117.00 MW. The minimum cost without base station energy storage was 1159.8362
million yuan (Fig. 10(b)). The total optimization cost of the system with 200000 base station energy storage
was at least 853.61278 million yuan, which was 306.22342 million yuan less than that
without base station energy storage.
5. Conclusion
Power resource scheduling can effectively achieve reasonable allocation of power resources
and reduce power production costs. On the other hand, most existing power dispatch
technologies have problems, such as low efficiency and weak accuracy. Therefore, a
power dispatch model based on ABC was constructed based on preprocessing power load
data. In response to the local optimization problem in ABC, search factors and selection
mechanisms were introduced to improve them. According to the findings, the training
errors of the wavelet transform algorithm tended to stabilize under all three conditions,
and all approached zero. When the population size was 30, 50, 100, and 500, the IBCOA
algorithm had the smallest loss value and the best convergence effect. For DED, a
lower cost of electricity was obtained. In actual power dispatch, when the population
was 100, the variance value was the smallest, suggesting that the data was relatively
more stable and less volatile at this time. Hence, the improved ABC proposed in the
study has high performance that can effectively achieve reasonable scheduling of power
resources, reduce power production costs, and achieve reasonable allocation and utilization
of resources. On the other hand, there were some shortcomings in the research. The
limited power load data used in the study may affect the accuracy of the obtained
model to some extent. In subsequent research, more power load data should be collected
for the power dispatch model analysis to improve the accuracy.
REFERENCES
S. Feng, D-S. Yang, B. Zhou, Y-H. Luo, and G-D. Li, “Real‐time active power dispatch
of virtual power plant based on distributed model predictive control,” Electronics
Letters, Vol. 58, no. 23, pp. 872-875, 2022.
![DOI](../../Resources/images/icon_crossref.png)
N. Zhou, C. Zhang, and S-L Zhang, “A multi-strategy firefly algorithm based on rough
data reasoning for power economic dispatch,” Mathematical biosciences and engineering:
MBE, Vol. 19, no. 9, pp. 8866-8891, 2022.
![URL](../../Resources/images/icon_url.png)
F. Gami, Z-A. Alrowaili, M. Ezzeldien, M. Ebeed, S. Kamel, S. Oda Eyad, and A. Mohamed
Shazly, “Stochastic optimal reactive power dispatch at varying time of load demand
and renewable energy resources using an efficient modified jellyfish optimizer,” Neural
Computing and Applications, Vol. 34, no. 22, pp. 20395-20410, 2022.
![DOI](../../Resources/images/icon_crossref.png)
Z-Y. Qu, Y-C. Dong, S. Mugemanyi, T. Yu, X-Y. Bo, H-H. Li, Y. Li, F-X. Rugema, and
C. Bananeza, “Dynamic exploitation Gaussian bare‐bones bat algorithm for optimal reactive
power dispatch to improve the safety and stability of power system,” IET Renewable
Power Generation, Vol. 16, no. 7, pp. 1401-1424, 2022.
![DOI](../../Resources/images/icon_crossref.png)
M. Wang, T. Zhou, H-H. Wang, Y-H. Zhai, and X-B. Dong, “Chinese power dispatching
text entity recognition based on a double-layer BiLSTM and multi-feature fusion,”
Energy Reports, Vol. 8, no. 5, pp. 980-987, 2022.
![DOI](../../Resources/images/icon_crossref.png)
M-A. Jusoh, M-Z. Daud, and M-Z. Ibrahim, “Fuzzy logic-based control strategy for hourly
power dispatch of grid-connected photovoltaic with hybrid energy storage,” Przeglad
Elektrotechniczny, Vol. 98, no. 1, pp. 11-18, 2022.
![URL](../../Resources/images/icon_url.png)
G. Chen, B. Yan, H. Zhang, D-D. Zhang, and Y-H. Song, “Time-efficient Strategic Power
Dispatch for District Cooling Systems Considering Evolution of Cooling Load Uncertainties,”
CSEE Journal of Power and Energy Systems, Vol. 8, no. 5, pp. 1457-1467, 2022.
![DOI](../../Resources/images/icon_crossref.png)
B-B. Zhang, M-X. Jia, C-B. Chen, K. Wang, and J-C Li, “Wind farm active power dispatching
algorithm based on grey incidence,” Global Energy Interconnection, Vol. 6, no. 2,
pp. 175-, 2023.
![DOI](../../Resources/images/icon_crossref.png)
S. Luo and X. Guo, “Multi-objective optimization of multi-microgrid power dispatch
under uncertainties using interval optimization,” Journal of Industrial and Management
Optimization, Vol. 19, no. 2, pp. 823-851, 2023.
![URL](../../Resources/images/icon_url.png)
X-P Li, W-Z. Zhao, and Z-G. Lu, “Hierarchical Optimal Reactive Power Dispatch for
Active Distribution Network with Multi-microgrids,” Journal of Electrical Engineering
& Technology, Vol. 18, no. 3, pp. 1705-1718, 2022.
![DOI](../../Resources/images/icon_crossref.png)
S-S Sefati, M. Abdi, and A. Ghaffari, “QoS-based routing protocol and load balancing
in wireless sensor networks using the Markov model and the artificial bee colony algorithm,”
Peer-to-Peer Networking and Applications, Vol. 16, no. 3, pp. 1499-1512, 2023.
![DOI](../../Resources/images/icon_crossref.png)
L-Y. Wang and S-H. Han, “The improved artificial bee colony algorithm for mixed additive
and multiplicative random error model and the bootstrap method for its precision estimation,”
Geodesy and Geodynamics, Vol. 14, no. 3, pp. 244-253, 2023.
![DOI](../../Resources/images/icon_crossref.png)
A-X. Tong, X-J. Tang, H-B. Liu, H-B. Gao, X-F. Kou, and Q. Zhang, “Differentiation
of NaCl, NaOH, and β-Phenylethylamine Using Ultraviolet Spectroscopy and Improved
Adaptive Artificial Bee Colony Combined with BP-ANN Algorithm,” ACS omega, Vol. 8,
no. 13, pp. 12418-12429, 2023.
![DOI](../../Resources/images/icon_crossref.png)
H. Wang, S. Wang, Z-C. Wei, T. Zeng, and T-Y. Ye, “An improved many-objective artificial
bee colony algorithm for cascade reservoir operation,” Neural Computing and Applications,
2023, 35(18): 13613-13629.
![DOI](../../Resources/images/icon_crossref.png)
S. Gurjinder, and K. Amandeep, “Artificial Bee Colony Optimized Multi-Histogram Equalization
for Contrast Enhancement and Brightness Preservation of Color Images,” International
Journal of Engineering and Manufacturing (IJEM), Vol. 13, no. 1, pp. 45-58, 2023.
![DOI](../../Resources/images/icon_crossref.png)
A. Karaman, D. Karaboga, I. Pacal, B. Akay, A. Basturk, U. Nalbantoglu, S. Coskun,
and O. Sahin, “Hyper-parameter optimization of deep learning architectures using artificial
bee colony (ABC) algorithm for high performance real-time automatic colorectal cancer
(CRC) polyp detection,” Applied Intelligence, Vol. 53, no. 12, pp. 15603-15620, 2022.
![DOI](../../Resources/images/icon_crossref.png)
C. Zhu, Y. Xu, Y-G. Wu, M-C. He, C-Q. Zhu, Q-X. Meng, and Y. Lin, “A hybrid artificial
bee colony algorithm and support vector machine for predicting blast-induced ground
vibration,” Earthquake Engineering and Engineering Vibration, Vol. 21, no. 4, pp.
861-876, 2022.
![DOI](../../Resources/images/icon_crossref.png)
J. Sassi, I. Alaya, P. Borne, and M. Tagina, “A decomposition-based artificial bee
colony algorithm for the multi-objective flexible jobshop scheduling problem,” Engineering
Optimization, Vol. 54, no. 3, pp. 524-538, 2022.
![DOI](../../Resources/images/icon_crossref.png)
J. Zan, “Research on robot path perception and optimization technology based on whale
optimization algorithm,” Journal of Computational and Cognitive Engineering, Vol.
1, no. 4, pp. 201-208, 2022.
![DOI](../../Resources/images/icon_crossref.png)
K. Jain, and A. Saxena, “Simulation on supplier side bidding strategy at day-ahead
electricity market using ant lion optimizer,” Journal of Computational and Cognitive
Engineering, Vol. 2, no. 1, pp. 17-27, 2023.
![DOI](../../Resources/images/icon_crossref.png)
Wei Lou, (1973-) obtained his BE in Electric power system and automation from Zhejiang
University in 1995. Heobtained his ME in Electric power system and automation from
Zhejiang Universityin1998.He is working as a senior engineer in Power System Technology
Support Center, East China Branch of State Grid Corporation of China. His areas of
interest are power system automation, relay protection, new energy, urban distribution
network.
Rong Hu(1983-) obtained her BE in Electric power system and automation from Shanghai
Jiao Tong University in 2005.She obtained his ME in Electric power system and automation
from Shanghai Jiao Tong University in 2008.She is working as a senior engineer in
Power System Technology Support Center, East China Branch of State Grid Corporation
of China. Her areas of interest are power system dispatch operation and control, electricity
market.
Gang Luo(1987-), obtained his Eng. D in Electrical Engineering from Huazhong University
of Science and Technology in 2014. He is working as a senior engineer in Power Grid
Business Unit, Beijing Tsintergy Technology Co., Ltd. His areas of interest are power
system operation, analysis and calculation, electricity market.
Rui Yang(1993-), obtained her ME in Electrical Engineering from Huazhong University
of Science and Technology in 2017. She is working as aengineer in Power Grid Business
Unit, Beijing Tsintergy Technology Co., Ltd. . Her areas of interest are electricity
market, overvoltage and insulation coordination.