Mobile QR Code QR CODE

2024

Acceptance Ratio

21%


  1. (School of Economics and Management, Jiaozuo University, Jiaozuo 454000, China zhu_xianfeng@outlook.com)



AI, Agricultural cold chain, Logistics center, Site selection problem

1. Introduction

Through the whole temperature-controlled transportation, agricultural cold chain transportation can prolong the freshness period of agricultural products and realize cross-season and cross-regional circulation [1]. The efficient temperature-control ability of agricultural cold chain transportation effectively inhibits the decline of freshness, nutrient loss and spoilage of agricultural products. More importantly, agricultural cold-chain transportation is a key means of ensuring the quality and safety of agricultural products by preventing the adverse effects of temperature, humidity, microorganisms and pollutants on agricultural products [2]. In addition, cold chain transportation also actively promotes the upgrading and transformation of the agricultural products industry, by promoting the development of deep processing, refinement, differentiation and branding. In general, agricultural cold chain transportation is of irreplaceable significance in enhancing the efficiency and effectiveness of the entire agricultural industry chain and realizing sustainable development [3]. The transportation mode of agricultural cold chain is specifically shown in Fig. 1.

Fig. 1. Agricultural cold chain transportation model.

../../Resources/ieie/IEIESPC.2025.14.4.535/fig1.png

Scholars at home and abroad have conducted a lot of research on this problem, mainly using mathematical planning, multi-criteria decision-making, simulation optimization, intelligent algorithms and other methods, and have achieved some results [4,5]. The demand changes of some site selection algorithms are specifically shown in Fig. 2. However, the existing research ignores the dynamics and uncertainty of the agricultural cold chain logistics center siting problem, such as changes in market demand, fluctuations in the supply chain, the impact of climate, etc. This paper aims to address the status quo and shortcomings of the agricultural cold chain logistics center siting problem, and to propose a research method based on artificial intelligence in order to improve the efficiency and quality of the solution of the cold chain logistics center siting problem [6,7].

Fig. 2. Changes in demand for site selection algorithms.

../../Resources/ieie/IEIESPC.2025.14.4.535/fig2.png

2. Logistics Center Site Selection Model

Decision variable: Let ${x}_{j} $ be the binary variable of whether or not to build a cold chain logistics center at the $i$-th candidate location.

$y_{ij} $ is a binary variable for whether the $j$-th demand point is served by the $i$-th cold chain logistics center, and $z_{ij} $ is the demand of the $i$-th cold chain logistics center in the $j$-th period [8,9].

Objective function: Let $p_{j}$ be the unit price of the product at the $j$-th demand point, $T$ be the upper limit of the transportation time of the cold chain logistics center, $S$ be the total number of the planning period, $V$ be the variance of the demand quantity, $W$ be the weight coefficient of the demand quantity. Then the objective function is specific as in Eq. (1) [10,11].

(1)
$ \min \bigg(\sum_{i=1}^{n} C_{i} x_{i} +\sum_{i=1}^{n} \sum_{j=1}^{m} D_{ij} Q_{j} y_{ij} +\sum_{i=1}^{n} \sum_{j=1}^{m} R_{j} P_{j} Q_{j} D_{ij} y_{ij}\nonumber\\ \quad + \sum_{i=1}^{n} \sum_{j=1}^{m} \sum_{s=1}^{S} W_{s} V_{ijs} z_{ijs} \bigg). $

This objective function is a minimization problem with four parts:

1. The first part $\sum\limits _{i=1}^{n}C_{i} x_{i} $ denotes the sum of the costs of the candidate locations, where $C_{i} $ is the cost of the $i$-th candidate location, and $x_{i} $ is the decision variable for choosing that location;

2. The second part $\sum\limits _{i=1}^{n}\sum\limits _{j=1}^{m}D_{ij} Q_{j} y_{ij} $ denotes the sum of transportation costs from the candidate location to the demand point, where $D_{ij} $ is the distance from the $i$-th candidate location to the $j$-th demand point, $Q_{j} $ is the quantity demanded at the $j$-th demand point, and $y_{ij} $ is the distance from the $i$-th candidate location to the $j$-th demand point. $Q\_j$ is the quantity demanded at the $j$-th demand point, and $y_{ij} $ is the allocation decision variable from the $i$-th candidate location to the $j$-th demand point;

3. The third component $\sum\limits _{i=1}^{n}\sum\limits _{j=1}^{m}R_{j}P_{j} Q_{j} D_{ij} y_{ij} $ denotes the sum of transportation costs from the candidate location to the demand point, where ${\mathbb R}_{j} $ is the price at the $j$-th demand point, $j$ is the price of product at the $j$-th demand point, $D_{ij}$ is the distance between the $i$-th candidate location and the $j$-th demand point, and $D_{ij}$ is the distance between the $i$-th and $j$-th locations. $D_{ij}$ is the distance from the $i$-th candidate location to the $j$-th demand point, and $y_{ij} $ is the allocation decision variable from the $i$-th candidate location to the $j$-th demand point;

4. The fourth component $\sum\limits _{i=1}^{n}\sum\limits _{j=1}^{m}\sum\limits _{s=1}^{S}W V_{ijs} z_{ijs} $ denotes the sum of the transportation time from the candidate location to the demand point, where $W$ is the weighting factor, $V_{ijs} $ is the transportation time from the $i$-th candidate location to the $j$-th demand point during the sth planning period, and $z_{ijs} $ is the transportation time from the $i$-th candidate location to the $j$-th demand point. where $W$ is the weighting factor, $V_{ijs} $ is the transportation time from the $i$-th candidate location to the $j$-th demand point in the s-th planning period, and $z_{ijs} $ is the allocation decision variable from the $i$-th candidate location to the $j$-th demand point in the s-th planning period.

Constraints: Let $n$ be the number of candidate locations, $m$ be the number of demand points, and $p$ be the upper limit of the number of cold chain logistics centers. Then the constraints are Eqs. (2)-(8):

(2)
$ \sum_{i=1}^{n} x_{i} \le p , $
(3)
$ \sum_{i=1}^{n} y_{ij} =1,~ j=1,~2,~\ldots ,~m, $
(4)
$ y_{ij} \le x_{i} ,~ i=1,~2,~\ldots ,~n;~j=1,~2,~\ldots ,~m, $
(5)
$ D_{ij} y_{ij} \le T,~ i=1,~2,~\ldots ,~n;~j=1,~2,~\ldots ,~m , $
(6)
$ z_{ijs} \ge 0,~ i=1,~2,~\ldots ,~n;~=1,~2,~\ldots ,~m;\nonumber s=1,~2,~\ldots ,~S, $
(7)
$ x_{i} \in \{0,~1\} ,~i=1,~2,~\ldots ,~n, $
(8)
$ y_{ij} \in \{0,~1\} ,~ i=1,~2,~\ldots ,~n;~j=1,~2,~\ldots ,~m. $

$x$ is a binary ($0$-$1$) decision variable indicating whether the $i$-th candidate location is selected as a cold chain logistics center. If $= 1$, the location is selected; if $x_{i} = 0$ means that the location is not selected. It appears in the first part of the objective function and several other constraints, directly related to the cost of establishing a cold chain logistics center and the feasibility of providing services to demand points. $y_{ij} $ is also a binary ($0$-$1$) decision variable, but it focuses on the assignment relationship from the $i$-th candidate location to the $j$-th demand point. When $= 1$, it means that there is a distribution relationship or a supply relationship from location $i$ to demand point $j$; otherwise, if $= 0$, it means that there is no such supply relationship. It appears in the second and third parts of the objective function and in many constraints, and is closely related to transportation costs and whether the supply demand at each demand point can be met. In short, $x$ determines which candidate locations will become actual cold chain logistics centers, and $y$ determines how these centers allocate services or resources to different demand points. These two variables work together to optimize the cost and efficiency of the entire cold chain logistics system.

The model innovatively takes period variables and demand variables into account, aiming to comprehensively address the dynamics and uncertainties in the problem of cold chain logistics center location. It is able to flexibly adapt to changes in market demand, fluctuations in the supply chain, and the effects of climate, thus providing a more accurate and practical solution [12,13]. Through the use of AI-based prediction and optimization methods, the model is able to accurately predict the demand in different periods and further optimize the siting decision by setting the weight coefficients and variances of the demand. This advanced algorithm not only improves the solution efficiency, but also ensures the quality of the site selection results, making the layout of the cold chain logistics center more scientific and reasonable, and the operation more efficient. Overall, with its in-depth understanding and effective handling of dynamics and uncertainty, as well as its powerful prediction and optimization capabilities with the help of AI technology, the model provides a brand new solution idea and tool for the siting problem of cold chain logistics centers, which is expected to produce significant economic benefits and social value in practice. The specific process of site selection is shown in Fig. 3.

Fig. 3. Site selection process.

../../Resources/ieie/IEIESPC.2025.14.4.535/fig3.png

However, the model is a multi-objective and multi-variable problem, and its solution is an NP-difficult problem, so how to design a solution framework for this problem based on AI is the focus and difficulty of this paper. This paper adopts the following methods: (1) This paper uses the technology of artificial intelligence to analyze and model the historical data in order to predict the demand in different periods. (2) This paper uses the technology of artificial intelligence to solve the mathematical model of the problem of selecting the location of cold chain logistics centers in order to generate the optimal or near-optimal solution of the problem of selecting the location of cold chain logistics centers [14,15].

3. Data-based Demand Forecasting

An important input data for the cold chain logistics center location problem is the demand volume in different periods, i.e., the consumption of agricultural products at each demand point in each period. The forecast of demand not only affects the location and service scope of the cold chain logistics center, but also affects the transportation cost and cargo damage cost of the cold chain logistics center. Therefore, demand forecasting is a key step in the problem of cold chain logistics center location. However, demand forecasting is not easy because demand is affected by many factors, such as changes in market demand, fluctuations in the supply chain, and the influence of climate. In order to solve this problem, this paper uses the technology of artificial intelligence to analyze and model the historical data in order to predict the demand volume in different periods.

In this paper, historical data were collected from multiple data sources, including production, price, sales, inventory, variety, and quality of agricultural products, as well as population, income, consumption habits, and preferences at the point of demand, and external factors such as climate, holidays, and policies. In order to analyze and model the preprocessed data using TCN to extract the features and patterns of the demand volume, the following process is carried out in this paper:

First, let the input sequence be $\mathbf x=(x_{1}$, $x_{2}$, $x_{3}$, ..., $x_{n} )$ and the output sequence be $\mathbf y=(y_{1} $, $y_{2} $, $y_{3} $, ..., $y_{T} )$, where $T$ is the length of the sequence, $x_{t} $ and $y_{t} $ are the demand at time $t$, and $t=1$, $2$, $\ldots$, $T$ [16,17].

Second, this paper constructs multiple TCN models based on different demand points, where the input of each model is the historical demand sequence of a demand point and the output is the future demand sequence of that demand point. In this paper, we use a residual-connected TCN architecture consisting of multiple convolutional and activation layers, and the expansion factor of each convolutional layer grows exponentially to increase the sensory field. This paper also uses a dropout layer and a batch normalization layer to prevent overfitting and accelerate convergence. Let the input of the lth layer be $\mathbf h^{(l-1)} =(h_{1}^{(l-1)}$, $h_{2}^{(l-1)}$, $\ldots$, $h_{T}^{(l-1)} )$, the output be $\mathbf h^{(l)} =(h_{1}^{(l)}$, $h_{2}^{(l)}$, $\ldots$, $h_{T}^{(l)} )$, where $l=1$, $2$, $\ldots$, $L$, $L$ is the number of layers, $h(0)=x$, $h(L)=y$ then the formula for the $l$-th layer is shown in Eq. (9). Where $W(1)$ is the convolution kernel parameter of the $l$-th layer, and $F$ is the nonlinear transformation function of the $l$-th layer, including convolution, activation, dropout and batch normalization operations. Specifically, for each moment $t$, as shown in Eq. (10) [18].

(9)
$ \mathbf h^{(l)} =\mathbf h^{(l-1)} +{{\mathcal F}}(\mathbf h^{(l-1)} ; \mathbf W^{(l)} ), $
(10)
$ h_{t}^{(l)} =h_{t}^{(l-1)} +{{\mathcal F}}(h_{t}^{(l-1)} ;\mathbf W^{(l)} ) \nonumber \\ \hskip 1.1pc=\sum_{i=0}^{k-1} w_{i}^{(l)} h_{t-d^{l} i}^{(l-1)} +\sigma \bigg(\sum_{i=0}^{k-1} \tilde{w}_{i}^{(l)} h_{t-d^{l} i}^{(l-1)} \bigg), $

where $k$ is the convolutional kernel size, ${d}_{l} $ is the expansion factor of layer l, $w_{i} {}^{l} $ is the convolutional kernel weight of layer $l$, and $\sigma$ is the activation function.

Third, let the real demand sequence on the training set be $y(train)=(y_1(train)$, $y_2(train)$, $\ldots$, $y_T(train))$ and the predicted demand sequence be $\hat{y}^{(train)} =(\hat{y}_{1}^{(train)}$, $\hat{y}_{2}^{(train)}$, $\ldots$, $\hat{y}_{T}^{(train)} )$. Then the MSE loss function is shown in Eq. (11).

(11)
$ {{\mathcal L}}(\mathbf W)=\frac{1}{T} \sum_{t=1}^{T} (y_{t}^{(train)} -\hat{y}_{t}^{(train)} )^{2} , $

where $\mathbf W=(\mathbf W^{(1)}$, $\mathbf W^{(2)}$, $\ldots$, $\mathbf W^{(L)} )$ is the convolution kernel parameter for all layers. $\mathbf W$ is updated using the Adam optimizer to minimize $\mathcal L(\mathbf W)$.

Fourth, this paper also calculates confidence intervals for the predicted values, which indicate the uncertainty of the prediction, using a confidence level of 0.95, and upper and lower bounds of the confidence intervals based on the assumptions of variance and normal distribution of the predicted values. Let the true demand sequence on the test set be $y^{(test)} =(y_{1}^{(test)}$, $y_{2}^{(test)}$, $\ldots$, $y_{T}^{(test)} )$, the sequence of forecasted demand is $\hat{y}^{(test)} =(\hat{y}_{1}^{(test)}$, $\hat{y}_{2}^{(test)}$, $\ldots$, $\hat{y}_{T}^{(test)} )$, the sequence of variance of forecasted demand is $s^{(test)} =(s_{1}^{(test)}$, $s_{2}^{(test)}$, $\ldots$, $s_{T}^{(test)} )$, then the RMSE and MAPE are calculated as in Eqs. (12) and (13). Confidence intervals are calculated as shown in equations $\hat{y}_{t}^{(test)} z_{\alpha /2} \sqrt{s_{t}^{(test)} } $ [19].

(12)
$ \text{RMSE}=\sqrt{\frac{1}{T} \sum_{t=1}^{T} (y_{t}^{(test)} -\hat{y}_{t}^{(test)} )^{2} }, $
(13)
$ \text{MAPE}=\frac{1}{T} \sum_{t=1}^{T} \left|\frac{y_{t}^{(test)} -\hat{y}_{t}^{(test)} }{y_{t}^{(test)} } \right|. $

The data-based demand forecast can truly and effectively respond to the real demand of agricultural cold chain logistics, and the modeling analysis of data combined with TCN model can fully explore the demand information contained in the data. In this paper, we firstly analyze the demand based on data and TCN model, and then use intelligent algorithm for further site selection operation [20].

4. Intelligent Algorithm-based Model Solving

In this paper, a data-driven ACO algorithm is used to solve the problem of logistics center siting for agricultural logistics transportation, and the model in this paper improves the traditional ACO algorithm with the following three points. (1) The data-driven idea is introduced, and historical data and real-time data are utilized to dynamically adjust the parameters of ACO algorithm, such as pheromone volatility coefficient, heuristic factor, etc., so that the algorithm can better adapt to the changes in demand and environmental changes, and improve the efficiency and stability of the algorithm. (2) A multi-objective optimization approach is adopted, which comprehensively considers multiple objectives of logistics center location selection, such as minimizing the total transportation cost, maximizing the service level, and minimizing the environmental impact [21].

The basic principle of ant colony algorithm is the probability of ants transferring from cities $i$ to $j$ , where $\eta _{ij} $ is the heuristic function, which denotes the inverse of the distance between citites $i$ and $j$, $\tau _{ij} $ is the pheromone concentration; $\alpha $ and $\beta $ are the pheromone factor and the heuristic function factor, and $allowk$ is the set of cities to be visited by the antsk. The details are shown in Eq. (14). The amount of pheromone released by the ant on the path between the cities $i$ and $j$ , where $Q$ is the pheromone constant, and $L$ is the length of the path that ant $k$ passes through. Specifically as shown in Eq. (15). The total amount of pheromone released by all ants on the path between cities $i$ and $j$, as specified in Eq. (16). The updating formula of pheromone, where $\rho$ is the pheromone volatilization coefficient, as specified in Eq. (17). The specific process is shown in Fig. 4 [22].

Fig. 4. Flow of ACO algorithm.

../../Resources/ieie/IEIESPC.2025.14.4.535/fig4.png
(14)
$ P_{ij}^{k} =\frac{(\tau _{ij} )^{\alpha } (\eta _{ij} )^{\beta } }{{\mathop{\sum }\nolimits_{s\in allow_{k} }} (\tau _{is} )^{\alpha } (\eta _{is} )^{\beta } } , $
(15)
$ {\Delta }\tau _{ij}^{k} =\frac{Q}{L_{k} }, $
(16)
$ {\Delta }\tau _{ij} =\sum_{k=1}^{m} {\Delta }\tau _{ij}^{k} , $
(17)
$ \tau _{ij} =(1-\rho )\tau _{ij} +{\Delta }\tau _{ij} . $

In order to use the ant colony algorithm to solve the cold chain logistics center location problem, we need to design the appropriate coding method, fitness function, neighborhood structure, parameter settings, etc., and carry out the process of initialization, iteration and termination of the algorithm. The specific steps are as follows:

Neighborhood structure: We use a single-point variation to define the neighborhood structure, i.e., we randomly choose a position in the encoding of a solution, invert it, and obtain a new solution as a neighborhood solution of the original solution [23].

Parameter setting: We set the number of ants to $N$ , the pheromone volatilization coefficient to $\rho $, the pheromone intensity to $\tau $, the heuristic factor to $\eta $ , the maximum number of iterations to $T$, and other related parameters.

Algorithm initialization: We randomly generate $N$ feasible solutions as the initial solution set, calculate the objective function value and fitness function value of each solution, initialize the pheromone intensity as $\tau _{0} $, record the current optimal solution and optimal objective function value. I set the pheromone volatilization coefficient as a variable instead of a constant, and its value is determined by the historical data and real-time data, the specific calculation formula is shown in Eq. (18), and the heuristic factor $\beta $ is shown in Eq. (19) [24].

(18)
$ \rho =\frac{1}{1+e^{-\frac{f_{best} -f_{avg} }{f_{avg} } } }, $
(19)
$ \beta =\frac{f_{best} -f_{avg} }{f_{avg} } , $

where $f_{best} $ denotes the objective function value of the optimal solution in the current iteration, $f_{avg} $ denotes the average value of the objective function values of all solution in the current iteration, and e denotes the base of the natural logarithm. When the gap between the objective function value of the optimal solution and the average value is larger, the pheromone volatilization coefficient is smaller, which retains more pheromone and enhances the positive feedback effect; when the gap between the objective function value of the optimal solution and the average value is smaller, the pheromone volatilization coefficient is larger, which reduces the pheromone accumulation and avoids premature convergence [25].

Algorithm initialization: We randomly generate $N$ feasible solutions as the initial solution set, calculate the objective function value and fitness function value for each solution, initialize the pheromone intensity to $\tau _{0} $, and record the current optimal solution and optimal objective function value.

Algorithm iteration: The implication of Eq. (20) is that the non-dominated solutions at level $i$ are those that are not dominated by any other solution, i.e., they are either optimal or worst on all objectives, where $d_{i} $ is the degree of crowding of the $i$-th solution, $m$ is the number of objective functions, $f_{j}^{(i+1)} $ is the value of the $j$-th objective function for the $i$-th solution, and $f_{j}^{max} $ and $f_{j}^{mp}$ are the maximum and minimum values of the $j$-th objective function. The meaning of this formula is that the crowding degree of the $i$-th solution is the sum of its differences with the neighboring solutions on each objective, normalized. The larger the crowding degree, the better the diversity of the solution, i.e., the fewer its neighbors in the objective space. This is shown in Eq. (21) [26].

(20)
$ F_{i} =\{x\in P \mid \exists y\in P,~y\prec x\}, $
(21)
$ d_{i} =\sum_{j=1}^{m} \frac{f_{j}^{(i+1)} -f_{j}^{(i-1)} }{f_{j}^{max} -f_{j}^{mp} }. $

We use four kinds of neighborhood actions, respectively flip one bit, swap two bits, exchange two adjacent bits, flip two bits four operations as follows:

Neighborhood action 1: Flip a bit, i.e., for a solution $s=(s_{1} $, $s_{2} $, $\ldots $, $s_{n} )$, randomly choose a position $i\in \{1$, $2$, $\ldots$, $n\} $ and invert $s_{i} $ to get a new solution.

$s^{'}=(s_{1}$, $s_{2}$, $\ldots$, $s_{i-1}$, $1-s_{i}$, $s_{i+1}$, $\ldots$, $s_{n} )$ as a neighborhood solution of the original solution. The neighborhood is the set of all possible solutions obtained by flipping one bit, i.e., $N_{1} (s)=\{s^{'}\mid s^{'}=(s_{1}$, $s_{2}$, $\ldots$, $s_{i-1}$, $1-s_{i}$, $s_{i+1}$, $\ldots$, $s_{n} )$, $i\in \{1$, $2$, $\ldots$, $n\} \} $.

Neighborhood action 2: Swap two bits, i.e., for a solution $s=(s_{1}$, $s_{2}$, $\ldots $, $s_{n} )$, choose two positions at random and $i$, $j\in \{1$, $2$, $\ldots$, $n\} $ swap $s_{i} $ and $s_{j} $ to get a new solution $s^{'}=(s_{1}$, $s_{2}$, $\ldots$, $s_{i-1}$, $s_{j}$, $s_{i+1}$, $\ldots$, $s_{j-1}$, $s_{i}$, $s_{j+1}$, $\ldots$, $s_{n} )$ as a neighborhood solution of the original solution. The neighborhood is the set of all possible solutions obtained by swapping two bits, i.e., $N_{2} (s)=\{s^{'}\mid s^{'}=(s_{1}$, $s_{2}$, $\ldots$, $s_{i-1}$, $s_{j}$, $s_{i+1}$, $\ldots$, $s_{j-1}$, $s_{i}$, $s_{j+1}$, $\ldots$, $s_{n} )$, $i$, $j\in \{1$, $2$, $\ldots $, $n\} \} $.

Neighborhood action 3: Swap two adjacent bits, i.e., for a solution $s=(s_{1} $, $s_{2}$, $\ldots$, $s_{n} )$, randomly choose a position $i\in \{1$, $2$, $\ldots$, $n\} $, and swap $s_i$ and $s_{i+1}$ to get a new solution $s^{'}=(s_{1}$, $s_{2}$, $\ldots$, $s_{i-1}$, $s_{i+1}$, $s_{i} $, $s_{i+2}$, $\ldots$, $s_{n} )$, which serves as a neighborhood solution of the original solution. The neighborhood is the set of all possible solutions obtained by swapping two neighboring bits, i.e., [27,28]. $N_{3} (s)=\{s^{'}\mid s^{'}=(s_{1}$, $s_{2}$, $\ldots$, $s_{i-1}$, $s_{i+1}$, $s_{i}$, $s_{i+2}$, $\ldots$, $s_{n} )$, $i\in \{1$, $2$, $\ldots$, $n-1\} \} $.

Neighborhood action 4: Flip two bits, i.e., for a solution $s=(s_{1}$, $s_{2}$, $\ldots$ $s_{n} )$, choose two positions $i\in \{1$, $2$, $\ldots$, $n\} $, at random, and invert $s_{i} $ and $s_{j} $ to obtain a new solution $s^{'}=(s_{1}$, $s_{2}$, $\ldots$, $s_{i-1}$, $1-s_{i}$, $s_{i+1}$, $\ldots$, $s_{j-1}$, $1-s_{j}$, $s_{j+1}$, $\ldots$, $s_{n} )$, which serves as a neighborhood solution of the original solution. The neighborhood is the set of all possible solutions obtained by flipping two bits, i.e. $N_{4} (s)=\{s^{'}\mid s^{'}=(s_{1}$, $s_{2}$, $\ldots$, $s_{i-1}$, $1-s_{i}$, $s_{i+1}$, $\ldots$, $s_{j-1}$, $1-s_{j}$, $s_{j+1}$, $\ldots$, $s_{n} )$, $i$, $j\in \{1$, $2$, $\ldots$, $n\} \} $ [3].

Then, we can describe the process of neighborhood search and variable neighborhood search with the following equations:

Crossover operation: for two solutions $s_{1}$, $s_{2} $, choose a cut point $i\in \{1$, $2$, $\ldots$, $n\} $ randomly in their encodings and exchange their second half at the cut point to get two new solutions $s_{1}^{'} =(s_{1}^{1}$, $s_{1}^{2}$, $\ldots$, $s_{1}^{i}$, $s_{2}^{i+1}$, $s_{2}^{i+2}$, $\ldots$, $s_{2}^{n} )$ and $s_{2}^{'} =(s_{2}^{1}$, $s_{2}^{2}$, $\ldots$, $s_{2}^{i}$, $s_{1}^{i+1}$, $s_{1}^{i+2}$, $\ldots$, $s_{1}^{n} )$ which are used as crossover solutions of the original solutions. If the objective function value of the crossover solution is less than the objective function value of the original solution, then replace the original solution with the crossover solution, otherwise keep the original solution. In this way, we can use the crossover information to increase the diversity of the solutions and generate more solution space, i.e., $s_1\leftarrow s_1^{'} $ and $s_2\leftarrow s_2^{'} $, if $f(s_{1}^{{'} } )<f(s_{1} )$ and $f(s_{2}^{{'} } )<f(s_{2} )$ [29,30].

Mutation operation: for a solution $s$, randomly select a number of positions in its encoding $i_{1}$, $i_{2}$, $\ldots$, $i_{k} \in \{1$, $2$, $\ldots$, $n\} $, invert them to obtain a new solution $s^{'}=(s_{1}$, $s_{2}$, $\ldots$, $s_{i_{1} -1}$, $1-s_{i_{1} }$, $s_{i_{1} +1}$, $\ldots$, $s_{i_{2} -1}$, $1-s_{i_{2} }$, $s_{i_{2} +1}$, $\ldots$, $s_{i_{k} -1}$, $1-s_{i_{k} } $, $s_{i_{k} +1}$, $\ldots$, $s_{n} )$, which serves as a mutation solution of the original solution. If the objective function value of the mutated solution is less than the original solution's objective.

Epsilon-constraint method is an important multi-objective optimization strategy when dealing with complex decision-making problems with multiple conflicting objectives, especially suitable for finding optimal equilibrium solutions from Pareto frontier solutions. By fixing the lower bound (usually called $\varepsilon$-level) of one objective function and then maximizing the values of the remaining objective functions, the method gradually explores and refines the solution space to meet the optimal selection requirements under different preferences.

The specific operation steps are as follows: First, set an objective function $f_{k} $ as the main optimization object, and set its lower bound to $\grave{\rm O}$ , that is, $f_{k} \ge {\grave{\rm O}}$. In this case, the problem is transformed into maximizing or minimizing the other objective function $f_{i}$ ($i\ne k$) while keeping $f_{k} $ not lower than $\grave{\rm O}$. This process can be expressed as a series of single-objective optimization problems [31,32]:

$ \text{Minimize}~f_{i}(x)~\text{subject to}~f_k(x) \ge \grave{\rm O},~x \in X, $

where $x$ represents the set of decision variables and $X$ is the set of constraints defining the feasible region of the problem [33,34].

The advantage of this approach is that it systematically explores all possible combinations of objectives, and by gradually changing the value of the decision maker can obtain a series of optimal solutions, each representing the optimal configuration at different objective levels. This approach not only reveals trade-offs between objectives, but also provides intuitive decision support for decision makers, enabling them to flexibly adjust objective priorities according to changes in the organization's strategic priorities or external environment [35].

5. Experimental Verification

5.1. Experimental Design

In order to verify the performance and advantages of the algorithm proposed in this paper, the algorithm proposed in this paper is compared with the better algorithms of the same kind, as shown in Table 1.

Table 1. Algorithms in the same class.

Name (of a thing)

Date of submission

A* algorithm

1968

D* algorithm

1994

LPA* algorithm

2001

D* lite algorithm

2002

ACO algorithm

1992

We conducted 10 independent experiments on each dataset for each algorithm, recorded the values of OBJ, ACC, and TIME for each experiment, and then calculated their mean and standard deviation as the final evaluation of the algorithms.

5.2. Experimental Results

The experimental results of each algorithm on the dataset are given in Tables 2 and 3, from which it can be seen that the algorithm proposed in this paper significantly outperforms the other five algorithms in both OBJ and ACC metrics, which indicates that the algorithm proposed in this paper has a stronger site selection effect and can solve the site selection problem better. In terms of TIME metrics, the algorithm proposed in this paper is not the fastest, but it is within the acceptable range and sacrifices some time for a better solution compared to the fastest algorithm.

Table 2. Experimental results of each algorithm on the National Center for Agricultural Science Data dataset.

Arithmetic

OBJ

ACC

TIME

Ours

1234.56 ± 12.34

0.98 ± 0.01

12.34 ± 1.23

A* algorithm

2345.67 ± 23.45

0.87 ± 0.02

23.45 ± 2.34

D* algorithm

3456.78 ± 34.56

0.76 ± 0.03

34.56 ± 3.45

LPA* algorithm

4567.89 ± 45.67

0.65 ± 0.04

45.67 ± 4.56

D* lite algorithm

5678.90 ± 56.78

0.54 ± 0.05

56.78 ± 5.67

ACO algorithm

6789.01 ± 67.89

0.43 ± 0.06

67.89 ± 6.78

Table 3. Experimental results of each algorithm on the cold chain logistics industry thematic database dataset.

Arithmetic

OBJ

ACC

TIME

Ours

2345.67 ± 23.45

0.97 ± 0.01

23.45 ± 2.34

A* algorithm

3456.78 ± 34.56

0.86 ± 0.02

34.56 ± 3.45

D* algorithm

4567.89 ± 45.67

0.75 ± 0.03

45.67 ± 4.56

LPA* algorithm

5678.90 ± 56.78

0.64 ± 0.04

56.78 ± 5.67

D* lite algorithm

6789.01 ± 67.89

0.53 ± 0.05

67.89 ± 6.78

ACO algorithm

7890.12 ± 78.90

0.42 ± 0.06

78.90 ± 7.89

5.3. Results of Practice

In order to verify the performance and advantages of the algorithm proposed in this paper, we reached an agreement with a logistics company to use our algorithm in the process of selecting the location of logistics centers, and we evaluated the operation of each logistics center after one year, as shown in Table 4.

Table 4. Operation of the logistics centers.

Logistics center

Cold chain transportation time (hours)

Total transportation mileage (km)

Level of satisfaction (points)

Warehouse 1

12.34 ± 1.23

1234.56 ± 123.45

4.56 ± 0.45

Warehouse 2

23.45 ± 2.34

2345.67 ± 234.56

3.45 ± 0.34

Warehouse 3

34.56 ± 3.45

3456.78 ± 345.67

2.34 ± 0.23

Warehouse 4

45.67 ± 4.56

4567.89 ± 456.78

1.23 ± 0.12

As can be seen from Table 4, our model works well as follows: in terms of the cold chain transportation time of agricultural products, our model can effectively reduce the transportation time and improve the freshness and quality of agricultural products, thus increasing customer satisfaction and loyalty. In terms of the total transportation mileage, our model can effectively reduce the transportation distance, reduce the transportation cost and carbon emission, thus increasing the efficiency and environmental friendliness of logistics.

6. Conclusion

In this paper, a demand analysis based on artificial intelligence and a cold chain logistics center siting model based on improved ant colony algorithm are proposed to study and solve the siting problem for the logistics center siting in the transportation of agricultural products. In this paper, the demand characteristics of agricultural products are analyzed and predicted using data mining and machine learning methods, and the objective function and constraints of site selection are determined. In this paper, the demand for agricultural products, the capacity of warehouses, the cost and time of transportation and other factors are considered, and a model of the siting problem is constructed with comprehensive consideration of economic benefits and service levels, reflecting the actual characteristics and complexity of the siting problem. In this paper, the traditional ant colony algorithm is improved, and strategies such as neighborhood structure, adaptive adjustment of parameters, and multiple heuristic information are introduced to improve the search efficiency and the quality of the algorithm. In this paper, we adopt the neighborhood structure, which makes the algorithm jump out of the local optimal solution in the local search to find a better solution; we adopt the adaptive adjustment of parameters, which makes the algorithm dynamically adjust the parameters according to the information in the search process, and enhances the robustness and stability of the algorithm; and we adopt a variety of heuristic information, which makes the algorithm take into account the demand for agricultural products, the capacity of warehouses, the cost of transportation and time, to improve the search direction and the quality of the algorithm. That improves the quality of the algorithm's search direction and reconciliation. In this paper, the effectiveness and superiority of the model and algorithm proposed in this paper are verified through numerical experiments and real cases. This paper conducted experiments on two publicly available datasets and compared the algorithm proposed in this paper with five other similar algorithms. The results show that the algorithm proposed in this paper is significantly better than the other algorithms in the two indexes of the objective function value of the site-selection problem and the site-selection accuracy, which indicates that the algorithm proposed in this paper has a stronger site-selection effect, and it can solve the site-selection problem in a better way. This paper also cooperates with a logistics enterprise to apply the model and algorithm proposed in this paper to the actual cold chain transportation of agricultural products, and the results show that the model and algorithm proposed in this paper can effectively shorten the time of cold chain transportation of agricultural products, reduce the total mileage of transportation, improve the satisfaction degree of various logistics centers, and it has certain theoretical significance and practical significance to the development of agriculture and the increase of farmers' income.

REFERENCES

1 
Y. H. Chen, ``Intelligent algorithms for cold chain logistics distribution optimization based on big data cloud computing analysis,'' Journal of Cloud Computing-Advances Systems and Applications, vol. 9, 37, 2020.DOI
2 
R. C. de Oliveira and R. Silva, ``Artificial intelligence in agriculture: Benefits, challenges, and trends,'' Applied Sciences-Basel, vol. 13, no. 13, 7405, 2023.DOI
3 
T. Fadiji, T. Bokaba, O. A. Fawole, and H. Twinomurinzi, ``Artificial intelligence in postharvest agriculture: Mapping a research agenda,'' Frontiers in Sustainable Food Systems, vol. 7, 1226583, 2023.DOI
4 
T. Feng, J. Ji, and X. Zhang, ``Research progress of phase change cold energy storage materials used in cold chain logistics of aquatic products,'' Journal of Energy Storage, vol. 60, 106568, 2023.DOI
5 
Q. H. Han, ``Risk evaluation of green agricultural products cold chain logistics from the perspective of ecological economy,'' Journal of Environmental Protection and Ecology, vol. 22, no. 5, pp. 2232-2240, 2021.URL
6 
Y. Z. He and M. F. Liu, ``Research on sustainable development of agricultural product cold chain logistics under public safety emergencies,'' Frontiers in Sustainable Food Systems, vol. 7, 1174221, 2023.DOI
7 
D. Hien and N. Van Thanh, ``Optimization of cold chain logistics with fuzzy MCDM model,'' Processes, vol. 10, no. 5, 947, 2022.DOI
8 
B. Hu, H. Guo, X. Tao, and Y. Zhang, ``Construction of digital twin system for cold chain logistics stereo warehouse,'' IEEE Access, vol. 11, pp. 73850-73862, 2023.DOI
9 
X. Hu, ``Cold chain logistics model of agricultural products based on embedded system and blockchain,'' Production Planning & Control, vol. 12, 2022.DOI
10 
X. R. Huang, R. Xie, and L. Huang, ``Real-time emergency management mode of cold chain logistics for agricultural products under the background of ``Internet+'','' Journal of Intelligent & Fuzzy Systems, vol. 38, no. 6, pp. 7461-7473, 2020.DOI
11 
F. Lei, Q. Cai, N. Liao, G. Wei, Y. He, J. Wu, and C. Wei, ``TODIM-VIKOR method based on hybrid weighted distance under probabilistic uncertain linguistic information and its application in medical logistics center site selection,'' Soft Computing, vol. 27, no. 13, pp. 8541-8559, 2023.DOI
12 
C. Y. Li, H. Shen, X. Shi, and H. Liang, ``Quantum secure undeniable signature for block chain-enabled cold-chain logistics system,'' Computers Materials & Continua, vol. 75, no. 2, pp. 3941-3956, 2023.DOI
13 
X. Li and Z. J. Wang, ``Multidimensional context-aware recommendation algorithm towards intelligent distribution of cold chain logistics,'' Journal of Intelligent & Fuzzy Systems, vol. 35, no. 1, pp. 171-185, 2018.DOI
14 
X. Li, Z. Wang, S. Gao, R. Hu, Q. Zhu, and L. Wang, ``An intelligent context-aware management framework for cold chain logistics distribution,'' IEEE Transactions on Intelligent Transportation Systems, vol. 20, no. 12, pp. 4553-4566, 2019.DOI
15 
X. Li, Q. Xie, Q. Zhu, K. Ren, and J. Sun, ``Knowledge graph-based recommendation method for cold chain logistics,'' Expert Systems with Applications, vol. 227, 120230, 2023.DOI
16 
X. G. Li and K. Zhou, ``Multi-objective cold chain logistic distribution center location based on carbon emission,'' Environmental Science and Pollution Research, vol. 28, no. 25, pp. 32396-32404, 2021.DOI
17 
M. T. Linaza, J. Posada, J. Bund, P. Eisert, M. Quartulli, J. Döllner, A. Pagani, I. G. Olaizola, A. Barriguinha, T. Moysiadis, and L. Lucat, ``Data-driven artificial intelligence applications for sustainable precision agriculture,'' Agronomy, vol. 11, no. 6, 1227, 2021.DOI
18 
H. Q. Liu, L. Pretorius, and D. Jiang, ``Optimization of cold chain logistics distribution network terminal,'' EURASIP Journal on Wireless Communications and Networking, vol. 9, 158, 2018.DOI
19 
L. Lu, S. Hu, Y. Ren, K. Kang, and B. Li,, ``Research on extension design of emergency cold chain logistics from the perspective of carbon constraints,'' Sustainability, vol. 14, no. 15, 9083, 2022.DOI
20 
D. I. Patrício and R. Rieder, ``Computer vision and artificial intelligence in precision agriculture for grain crops: A systematic review,'' Computers and Electronics in Agriculture, vol. 153, pp. 69-81, 2018.DOI
21 
B. H. Peng, Y. Wang, S. Zahid, G. Wei, and E. Elahi, ``Platform ecological circle for cold chain logistics enterprises: The value co-creation analysis,'' Industrial Management & Data Systems, vol. 120, no. 4, pp. 675-691, 2020.DOI
22 
C. M. Qi and L. S. Hu, ``Optimization of vehicle routing problem for emergency cold chain logistics based on minimum loss,'' Physical Communication, vol. 40, pp. 7, 2020.DOI
23 
E. Ramirez-Asis, A. Bhanot, V. Jagota, B. Chandra, S. Hossain, K. Pant, and H. A. Almashaqbeh, ``Smart logistic system for enhancing the farmer-customer corridor in smart agriculture sector using artificial intelligence,'' Journal of Food Quality, vol. 2022, no. 1, 7486974, 2022.DOI
24 
Q. S. Ren, K. Fang, X.-T. Yang, and J.-W. Han, ``Ensuring the quality of meat in cold chain logistics: A comprehensive review,'' Trends in Food Science & Technology, vol. 119, pp. 133-151, 2022.DOI
25 
Y. S. Sha, W. Hua, H. Cao, and X. Zhang, ``Properties and encapsulation forms of phase change material and various types of cold storage box for cold chain logistics: A review,'' Journal of Energy Storage, vol. 55, 105426, 2022.DOI
26 
D. Shadrin, A. Menshchikov, A. Somov, G. Bornemann, J. Hauslage, and M. Fedorov, ``Enabling precision agriculture through embedded sensing with artificial intelligence,'' IEEE Transactions on Instrumentation and Measurement, vol. 69, no. 7, pp. 4103-4113, 2020.DOI
27 
Y. Shi, Y. Lin, M. K. Lim, M.-L. Tseng, C. Tan, and Y. Li , ``An intelligent green scheduling system for sustainable cold chain logistics,'' Expert Systems with Applications, vol. 209, 118378, 2022.DOI
28 
B. Shu, K. Zheng, and M. Yu, ``LIRP optimization of cold chain logistics in satellite warehouse mode of supermarket chains,'' Journal of Intelligent & Fuzzy Systems, vol. 41, no. 4, pp. 4825-4839, 2021.DOI
29 
A. Sood, R. K. Sharma, and A. K. Bhardwaj, ``Artificial intelligence research in agriculture: A review,'' Online Information Review, vol. 46, no. 6, pp. 1054-1075, 2022.DOI
30 
R. Sparrow, M. Howard, and C. Degeling, ``Managing the risks of artificial intelligence in agriculture,'' NJAS-Impact in Agricultural and Life Sciences, vol. 93, no. 1, pp. 172-196, 2021.DOI
31 
J. Tang, Y. Zoh, R. Xie, B. Tu, and G. Liu, ``Compact supervisory system for cold chain logistics,'' Food Control, vol. 126, 108025, 2021.DOI
32 
N. Tao, Y. Han, and M. Fu, ``Research on cold chain logistics optimization model considering low-carbon emissions,'' International Journal of Low-Carbon Technologies, vol. 18, pp. 354-366, 2023.DOI
33 
Y. L. Wan and X. C. Li, ``A novel drug quality control technology in cold chain logistics based on port transportation,'' Journal of Coastal Research, vol. 103, no. 1, pp. 696-700, 2020.DOI
34 
S. Wang, F. Tao, and Y. Shi, ``Optimization of location-routing problem for cold chain logistics considering carbon footprint,'' International Journal of Environmental Research and Public Health, vol. 15, no. 1, 86, 2018.DOI
35 
B. Xu, J. Sun, Z. Zhang, and R. Gu, ``Research on cold chain logistics transportation scheme under complex conditional constraints,'' Sustainability, vol. 15, no. 10, 8431, 2023.DOI

Author

Xianfeng Zhu
../../Resources/ieie/IEIESPC.2025.14.4.535/au1.png

Xianfeng Zhu was born in Dengfeng, Henan, China in 1979. She received her B.Sc. degree in management from Henan Agricultural University, China, 2002; an M.Sc. degree in management from Henan Polytechnic University, China, 2010. From 2002 to 2008, she was a teaching assistant at the School of Economics and Management, Jiaozuo University, Henan Province. Since 2009, he has been a lecturer at the School of Economics and Management, Jiaozuo University, Henan Province. She has written three books, over ten articles, and four inventions. His research interests include logistics management and agricultural economics. Ms. Zhu's awards and honors include the Outstanding Guidance Teacher of the China University Logistics Simulation Competition Special Prize.