Research on Optimization of Cold Chain Logistics Network of Fresh
Agricultural Products Based on Genetic Algorithm
Xudong Xing, Huihui Li, Hui Yao, Na Liu and Chen Du
Shandong Institute of Commerce and Technology, Jinan, Shandong, China
Keywords: Natural Evolution Theory, Genetic Algorithm, Logistics Network Optimization Problems, Cold Chain,
Logistics, Fresh Produce.
Abstract: The problem of logistics network optimization plays an important role in the cold chain logistics network of
fresh agricultural products, but there is the problem of inaccurate optimization positioning. The traditional
particle swarm algorithm cannot solve the network optimization problem in the cold chain logistics network
of fresh agricultural products, and the effect is not satisfactory. In today's globalized trade, the circulation of
fresh agricultural products is no longer limited to the local market. As consumer demand for fresh, healthy
food increases, it becomes even more important to ensure the freshness and safety of these products during
transportation. As an important means to ensure food quality, the optimization of cold chain logistics is of
great significance to reduce energy consumption, reduce costs and improve customer satisfaction. The
purpose of this paper is to explore how to use advanced genetic algorithm (GA) to optimize the cold chain
logistics network of fresh agricultural products, in order to achieve a win-win situation of logistics efficiency
and economic benefits.
1 INTRODUCTION
Genetic algorithm is a search heuristic that simulates
the principles of natural selection and genetics, which
solves optimization problems by simulating the
process of biological evolution in nature (Shen,
2023). In the optimization of the cold chain logistics
network for fresh agricultural products, we are faced
with a series of complex decision variables, such as
the location of the warehouse, the choice of
transportation routes (Lin, 2021), and the strategy of
goods distribution. Genetic algorithms continuously
evolve to obtain approximate optimal solutions by
randomly generating initial populations (solution
sets) and then generating new generation populations
through selection (replication), crossover
(recombination), and mutation (random change)
operations (Wang, 2021).
2 RELATED CONCEPTS
2.1 Mathematical Description of the
Genetic Algorithm
Specific to the optimization of cold chain logistics
network, genetic algorithm can be applied to the
following aspects: Route optimization: use GA to
determine the shortest or most economical
distribution route, reducing transit time and costs
while maintaining product freshness (Cao and Wang,
2021);
1
lim( ) max( 2)
2
iij ij ij
x
yt y t
→∞
⋅= ≥ ÷
(1
)
Among them, the judgment of outliers is shown in
Equation (2).
2
max( ) ( 2 ) ( 4)
ij ij ij ij
tttmeant=Γ + ⋅ +


M
(2
)
Xing, X., Li, H., Yao, H., Liu, N. and Du, C.
Research on Optimization of Cold Chain Logistics Network of Fresh Agricultural Products Based on Genetic Algorithm.
DOI: 10.5220/0013537600004664
Paper published under CC license (CC BY-NC-ND 4.0)
In Proceedings of the 3rd International Conference on Futuristic Technology (INCOFT 2025) - Volume 1, pages 171-176
ISBN: 978-989-758-763-4
Proceedings Copyright © 2025 by SCITEPRESS – Science and Technology Publications, Lda.
171

Vehicle scheduling: use GA for vehicle
scheduling, reasonably arrange the use of
transportation vehicles, reduce the empty driving rate
and improve transportation efficiency (Zeng and
Wang, et al. 2021).
The strength of the genetic algorithm lies in its
flexibility and global search capabilities. It is not
limited by the size of the problem and can handle
nonlinear, multi-objective, and high-dimensional
optimization problems (Zhang Nan, 2023). In a cold
chain logistics network for fresh produce, this means
that we are able to consider multiple objectives at the
same time, such as minimising costs, maximizing
customer satisfaction and minimising environmental
impact (Pan and Li, et al. 2023).
() 2 7
ii i
Fd t y ξ =Ο ⋅ → ⋅





(3)
2.2 Selection of Logistics Network
Optimization Problem Scheme
There are still some challenges in the application of
genetic algorithms in practice, such as parameter
setting, determination of algorithm termination
conditions, and stability of the solution process.
()= ( )
ii i i
dy
gt x z Fd w
dx
⋅−Ε
∏

(4)
Based on assumptions I and II, the comprehensive
function of the logistics network optimization
problem can be obtained, and the result is shown in
Equation (5).
lim ( ) ( ) max( )
ii ij
x
gt Fd t
→∞
+≤

(5)
Inventory management: Optimize inventory
levels through GA, reduce the risk of over-storage or
stock-outs, and ensure the efficient operation of the
supply chain (Jia and Sun, 2022); Facility layout: GA
is applied to determine the optimal location of
warehouses and distribution centers, as well as how
they are connected to each other, thereby improving
the efficiency of the entire logistics network;.

() ( ) ( 4)
ii ij
gt Fd mean t+↔ +

(6
)
2.3 Analysis of Logistics Network
Optimization Problem Scheme
However, in order to realize the potential of genetic
algorithms, we need precise mathematical models to
describe the behavior of cold chain logistics systems
(Wei and Zhang, 2023). This includes understanding
every step of the product from field to fork: post-
harvest handling, refrigerated storage, temperature
control during transit, distribution center operations,
final retail display, etc (Qi and Tai, 2021). In addition,
a large amount of data needs to be collected for
algorithm analysis, such as shipping time, cost,
temperature change, product loss rate, etc.

()
() ( )
!
()
(4)!!
ii
i
ij
gt Fd
n
No t
mean t r n r
+
=
+−

(7
)
The choice of parameters such as crossover rate
and mutation rate will directly affect the performance
of the algorithm, and the termination condition should
ensure that the algorithm can find a good solution and
avoid unnecessary computational waste (Zhan and
Zhang, 2022). Stability is about the consistency of the
results produced by the algorithm in different runs.

() [ () ( )]
iii
Z
ht gt F d=+


(8
)
In summary, genetic algorithms provide a
powerful tool for solving complex problems of cold
chain logistics network optimization of fresh
agricultural products. By simulating biological
evolution, it is able to find an effective approximate
optimal solution in a large solution space (Li and Wu,
2021). Although detailed modeling, accurate data,
and appropriate parameter setting are required in the
application, the potential of genetic algorithms is
huge, and it is worthy of further exploration and
application in the industry (Chen and Li, et al. 2022).
With the improvement of computing power and the
advancement of intelligent algorithms, we can expect
that genetic algorithms will help us find more
economical, green and efficient solutions in the field
of fresh agricultural product logistics in the future.


min[ ( ) ( )]
()
() ( )
ii
i
ii
gt Fd
accur t
gt Fd
+
=Λ
+


(9
)
Consumers are paying more and more attention to
the quality of fresh agricultural products, and cold
INCOFT 2025 - International Conference on Futuristic Technology
172

chain logistics to ensure the freshness of food from
the field to the table is particularly important.
Algorithmic optimization plays a pivotal role in this
process, not only to improve logistics efficiency, but
also to ensure the freshness and safety of agricultural
products. In this article, we will take a closer look at
how algorithmic optimization can improve the
performance of cold chain logistics and analyze its
indispensable value in the modern fresh produce
supply chain.


min[ ( ) ( )]
()
() ( )
ii
i
ii
gt Fd
accur t
gt Fd
+
=Φ
+


(10)
First and foremost, it is crucial to understand the
core of cold chain logistics. Cold chain logistics refers
to a service system that continuously provides a low-
temperature environment in the whole process of
production, storage, transportation, sales and
consumption. In the case of fresh produce, this
process must be temperature-controlled to prevent
food spoilage and bacterial growth. Therefore,
precise temperature control and real-time monitoring
are essential.
3 OPTIMIZATION STRATEGY
FOR LOGISTICS NETWORK
OPTIMIZATION PROBLEMS
Algorithmic optimization plays an important role
here. By collecting data from each node of
agricultural products from the origin to the consumer,
a comprehensive logistics information network can
be built. In this network, advanced algorithms, such
as machine learning and artificial intelligence, can be
used to optimize the configuration of logistics routes,
transportation methods, and storage conditions.
These algorithms can predict traffic conditions, avoid
congested road sections, calculate optimal loading
scenarios to reduce transportation costs, and even
adjust transportation plans to harsh weather
conditions based on weather forecasts.
3.1 Introduction to Logistics Network
Optimization Issues
In addition to route and transportation optimization,
algorithms can also automate inventory management
without sacrificing food safety. For example, by
monitoring the condition of agricultural products in
real time and predicting their shelf life, the system can
notify retailers in time to reduce losses and prevent
expired products, allowing for accurate inventory
allocation and renewal.
Table 1: Logistics network optimization problem
requirements
Scope of
application
Grade Accura
cy
Logistics
network
optimization
issues
Cargo flow
time
I 85.00 78.86
II 81.97 78.45
Cargo I 83.81 81.31
II 83.34 78.19
Sustainable
development
I 79.56 81.99
II 79.10 80.11
The logistics network optimization problem
process in Table 1 is shown in Figure 1,
Logistics
network
Analysis
Fresh agricultural
products
Genetic
algorithm
Cold chain
Natural
evolution
Logistics
Figure 1: The analysis process of logistics network
optimization problems
In practical applications, algorithm optimization
has achieved remarkable results. Taking a large
supermarket chain as an example, the company has
realized real-time monitoring and management of the
temperature of the whole chain of agricultural
products by deploying an advanced cold chain
monitoring system and intelligent algorithms. The
results are impressive: a significant reduction in
attrition rates and a significant increase in customer
satisfaction, all thanks to algorithms' accurate
interpretation of data and immediate responses.
3.2 Logistics Network Optimization
Problems
Of course, to fully realize the potential of algorithm
optimization in cold chain logistics, all parties in the
industry need to work together. From farms to
Research on Optimization of Cold Chain Logistics Network of Fresh Agricultural Products Based on Genetic Algorithm
173

wholesalers to retailers, every step of the way requires
contributing data, sharing information, and
leveraging algorithmic tools to make quick decisions.
At the same time, technological progress and
innovation are also key drivers driving the
development of this field.
Table 2: Overall picture of the logistics network
optimization problem scenario
Category Random
data
Reliability Analysis
rate
Cargo flow
time
85.32 85.90 83.95
Car
g
o 86.36 82.51 84.29
Sustainable
develo
p
ment
84.16 84.92 83.68
Mean 86.84 84.85 84.40
X6 83.04 86.03 84.32
P=1.249
3.3 Logistics Network Optimization
Problems and Stability
With the continuous advancement of technology,
algorithms have quietly become an indispensable part
of our daily life and work.
Figure 2: Logistics network optimization problem with
different algorithms
Sum up, algorithm optimization has brought
revolutionary changes to cold chain logistics. It not
only improves logistics efficiency and reduces
operating costs, but also ensures the high quality and
safety of food. In the future, with the continuous
development and innovation of technology, algorithm
optimization will continue to play a key role in the
cold chain logistics of fresh agricultural products,
bringing more efficient, reliable and intelligent
solutions to global food supply chain management.
Table 3: Comparison of accuracy of logistics network
optimization problems of different methods
Algorith
m
Surve
y data
Logistics
network
optimizatio
n issues
Magnitud
e of
change
Error
Genetic
algorith
m
85.33 85.15 82.88 84.9
5
Particle
swarm
arithmeti
c
85.20 83.41 86.01 85.7
5
P 87.17 87.62 84.48 86.9
7
Especially in the field of cold chain logistics of
agricultural products, algorithm optimization not only
improves efficiency, but also ensures the safety and
quality of food. This article will deeply analyze the
key role of algorithm optimization in the cold chain
logistics of agricultural products, and discuss its
future development direction.
Figure 3: Logistics network optimization problem of
genetic algorithm
First of all, we must understand what "cold chain
logistics" is. To put it simply, cold chain logistics
refers to the temperature-controlled transportation
and storage of temperature-sensitive products such as
fresh agricultural products and frozen foods
throughout the supply chain. This process is essential
to ensure food safety and reduce wastage. However,
traditional cold chain logistics management often has
problems such as information lag and low efficiency.
Algorithm optimization technology is the key to
solving these problems.
INCOFT 2025 - International Conference on Futuristic Technology
174

3.4 Rationality of Logistics Network
Optimization Problems
The role of algorithm optimization in the cold chain
logistics of agricultural products is mainly reflected
in the following aspects.
Figure 4: Logistics network optimization problem with
different algorithms
Route optimization: By analyzing the optimal
distribution route through algorithms, transportation
time can be reduced, energy consumption can be
reduced, and the freshness of agricultural products
can be ensured. This is especially important for
geographically dispersed farms and markets.
Inventory management: Algorithms can predict
market demand based on historical data, helping
enterprises to plan inventory reasonably, avoid excess
or shortage, and reduce waste. Real-time monitoring:
Intelligent algorithms combined with Internet of
Things (IoT) technology can monitor the temperature
and humidity of agricultural products in real time, and
adjust environmental conditions in time to ensure
product quality.
3.5 Effectiveness of Logistics Network
Optimization Problems
In order to verify the effectiveness of the genetic
algorithm, the logistics network optimization
problem scheme is comprised with the particle swarm
algorithm, and the logistics network optimization
problem scheme is shown in Figure 5 shown.
Figure 5: Logistics network optimization problems with
different algorithms
Risk management: Using big data analysis and
prediction algorithms, potential risk factors, such as
weather changes, traffic delays, etc., can be assessed
and coping strategies can be formulated. Cost
savings: By optimizing transportation, storage and
other links, algorithms can help enterprises
effectively control costs and improve profit margins.
Table 4: Comparison of the effectiveness of logistics
network optimization problems of different methods
Algorith
m
Surve
y data
Logistics
network
optimizatio
n issues
Magnitud
e of
change
Error
Genetic
al
g
orith
m
82.21 85.92 84.59 82.8
5
Particle
swarm
arithmeti
c
83.73 84.23 84.41 83.5
5
P 84.20 87.39 84.76 83.9
0
For example, an agricultural products company
introduced a machine learning-based forecasting
model that accurately predicted seasonal demand
fluctuations and achieved precise control of inventory,
thereby significantly reducing wastage while
maintaining high customer satisfaction.
Research on Optimization of Cold Chain Logistics Network of Fresh Agricultural Products Based on Genetic Algorithm
175

Figure 6: Genetic algorithm logistics network optimization
problem
In the future, with the continuous development of
artificial intelligence and big data technology, the
application of algorithm optimization in the cold
chain logistics of agricultural products will be more
extensive. For example, deep learning technology can
further improve the accuracy of predictive models,
blockchain technology can enhance the transparency
and traceability of supply chains, and drones and
autonomous vehicles can be combined to achieve
more efficient logistics and distribution.
4 CONCLUSIONS
In short, algorithm optimization has become a force
to be reckoned with in the field of cold chain logistics
of agricultural products. It not only improves logistics
efficiency and ensures food safety, but also brings
considerable economic benefits to enterprises. With
the continuous advancement of technology, the cold
chain logistics of agricultural products will become
more intelligent and automated in the future, bringing
consumers higher quality food enjoyment.
In this data-driven era, mastering algorithm
optimization technology is equivalent to mastering
the future of the industry. Therefore, whether it is the
government, enterprises or scientific research
institutions, they should increase investment to
promote the in-depth research and extensive
application of algorithm optimization technology in
the cold chain logistics of agricultural products. Only
in this way can we find the perfect balance between
food safety and supply chain efficiency to create
greater value for society.
REFERENCES
Shen Jiaming. (2023). Research on intelligent scheduling
mode of fresh agricultural products cold chain logistics
in high-speed service isas under digitalization. Jiangsu
Business Review(1), 35-39.
Lin Diansheng. (2021). Research on optimization of low-
carbon cold chain logistics network for fresh
agricultural products. (Doctoral dissertation, South
China University of Technology).
Wang Hong. (2021). Research on the development
problems of fresh agricultural products cold chain
logistics in Henan Province based on SWOT analysis.
Journal of Hebei Softwis Vocational and Technical
College, 23(2), 4.
Cao Wenbin, Wang Ting. (2021). Research on optimization
of fresh cold chain distribution path considering
freshness constraint. Logistics Technology, 44(7), 7.
Zeng Mingang, Wang Xiuhui, Li Jianyu. (2021). Research
on cold chain logistics network planning considering
node interruption and carbon emissions. Journal of
South China University of Technology: Social Sciences
Edition, 23(4), 12.
Zhang Nan. (2023). Multi-objective optimization method
for location selection of cold chain logistics distribution
sharing wishouse under low-carbon constraint.
Automation and Instrumentation.
Pan Weiqiang, Li Beihua, Lu Yiqin, Qin Jiancheng, Wang
Meng, Wang Haihan. (2023). A multi-objective
optimization scheduling method for hybrid
transmission in time-sensitive networks.
CN116389289A.
Jia Xin, Sun Tongtong. (2022). Research hotspots and
frontier evolution of cold chain logistics based on
scientific knowledge graph. Science and Technology
and Industry, 22(9), 26-34.
Wei Ziqiu, Zhang Xin. (2023). Optimization of cold chain
distribution path considering soft time window.
Logistics Technology, 42(1), 69-73.
Qi Yuxuan, Tai Qiuyue. (2021). Research on demand
forecasting of fresh agricultural products cold chain
logistics based on grey neural network. Commercial
Modernization(16), 3.
Zhan Chenlin, Zhang Yanfu. (2022). Optimization research
on individual business farmer's market cold chain
logistics under green concept. Value Engineering,
41(21), 56-59.
Li Kang, Wu Daqing. (2021). Research on evolution and
integrated optimization of fresh agricultural products
cold chain logistics system. Lixin Accounting Press.
Chen Xinying, Li Yilin, Xiao Siyi. (2022). Optimization of
fresh agricultural products logistics distribution path
based on improved genetic algorithm. Journal of Dalian
Jiaotong University, 43(5), 97-102.
INCOFT 2025 - International Conference on Futuristic Technology
176