A coal purchasing and transportation collaborative optimization method and device, electronic equipment, storage medium and program product

Abstract

The present application relates to the technical field of coal supply chain optimization, and discloses a coal purchasing and transportation collaborative optimization method and device, electronic equipment, storage medium and program product, the present application integrates coal purchasing data and transportation data, generates a multivariate price fluctuation random scene by means of the Monte Carlo method simulation, and comprehensively covers various situations that may be caused by market price fluctuations. The sample average approximation method is used to convert the random problem into a deterministic problem, a mixed integer linear programming model is constructed by combining multiple constraint conditions with the minimum comprehensive cost minimization as the target, the optimization direction of the model is ensured to be clear and to conform to the actual business boundary. Based on the iterative solution of multiple decision variables under each random scene, the collaborative relationship between the purchasing and transportation links can be accurately balanced, the purchasing quantity and transportation capacity can be efficiently matched, and the supplier selection, purchasing distribution, and transportation path and mode combination can be dynamically optimized. The final output optimal scheme can effectively reduce the comprehensive cost of coal purchasing and transportation.

Description

Technical Field

[0001] This invention relates to the field of coal supply chain optimization technology, specifically to a method, apparatus, electronic device, storage medium, and program product for the collaborative optimization of coal procurement and transportation. Background Technology

[0002] Against the backdrop of tight coal supply and demand and fierce competition in the electricity market, building a scientific and efficient fuel supply system has become crucial for coal-fired power plants to achieve a dynamic balance between ensuring stable supply and prices and optimizing costs, thereby enhancing their core competitiveness and sustainable development capabilities. Coal procurement and transportation, as core components of the fuel supply system, are deeply intertwined: the geographical distribution of procurement sources determines the transportation network topology, supplier choices trigger differentiated transportation methods, and transportation costs and capacity constraints, in turn, affect the economics and feasibility of procurement plans. Therefore, achieving coordinated optimization of procurement and transportation, and reducing costs and increasing efficiency through refined management and technological innovation, is of significant practical importance for the stable operation and long-term development of coal-fired power plants.

[0003] However, existing optimization methods mainly include statistical forecasting based on historical data and multi-objective linear programming. But none of these methods consider the impact of transportation mode on overall cost. Most focus on optimizing a single link, severing the synergistic relationship between procurement and transportation, and failing to form a chain-wide linkage decision-making mechanism. Or they rely on static data and traditional algorithms, lacking risk response to uncertainties such as market price fluctuations, ultimately causing the total supply chain cost to deviate from the optimal solution, failing to achieve the optimization goal of controllable risk and maximum benefit. Summary of the Invention

[0004] This invention provides a method, apparatus, electronic device, storage medium, and program product for collaborative optimization of coal procurement and transportation, in order to solve the problem that the total supply chain cost in existing technologies deviates from the optimal solution and cannot achieve the optimization goal of controllable risk and maximum benefit.

[0005] In a first aspect, the present invention provides a method for the coordinated optimization of coal procurement and transportation, the method comprising: By combining coal procurement and transportation data with Monte Carlo data, multiple scenarios of coal market price fluctuations were generated. The stochastic procurement-transportation optimization problem is transformed into a deterministic optimization model using a pre-defined sample-average approximate deterministic optimization model. Under multiple constraints, a mixed-integer linear programming model is constructed with the goal of minimizing the comprehensive cost of coal procurement, transportation, and risk management. Based on multiple decision variables, the mixed-integer linear programming model is solved iteratively, and the optimal procurement and transportation plan is determined based on the optimal solution.

[0006] This invention integrates coal procurement and transportation data, and uses Monte Carlo simulation to generate multivariate price fluctuation stochastic scenarios, comprehensively covering various situations that may arise from market price fluctuations. This provides comprehensive and realistic scenario support for subsequent optimization decisions. The random problem is transformed into a deterministic problem using a sample average approximation method. With the goal of minimizing overall cost, a mixed-integer linear programming model is constructed using multiple constraints to ensure that the model's optimization direction is clear and conforms to actual business boundaries. Based on iterative solutions using multiple decision variables under various stochastic scenarios, the collaborative relationship between procurement and transportation can be accurately balanced, procurement volume and transportation capacity can be efficiently matched, and supplier selection, procurement allocation, and combinations of transportation routes and methods can be dynamically optimized. The final optimal solution effectively reduces the overall cost of coal procurement and transportation, improves the scientific nature and flexibility of procurement and transportation decisions, and enhances the supply chain's adaptability to market price fluctuations.

[0007] In one optional implementation, the method of combining coal procurement data and transportation data with Monte Carlo simulations to generate multiple coal market price fluctuation scenarios includes: Obtain coal procurement data, transportation data, risk data, and inventory data; Data preprocessing is performed on the coal procurement data, the transportation data, the risk data, and the inventory data; The Monte Carlo simulation method was used to generate random scenarios, resulting in multiple scenarios of coal market price fluctuations.

[0008] This invention comprehensively acquires four core data categories: coal procurement, transportation, risk, and inventory. Standardized preprocessing ensures the accuracy and consistency of the data. By combining Monte Carlo simulation methods with preset variables, it conducts scenario simulations to generate multiple random price fluctuation scenarios, fully covering various potential situations of market price fluctuations.

[0009] In one optional implementation, the stochastic procurement-transportation optimization problem is transformed into a deterministic optimization model using a sample-averaged approximate deterministic optimization model. Under multiple constraints, a mixed-integer linear programming model is constructed with the objective of minimizing the comprehensive cost of coal procurement, transportation, and risk management. This model includes: By combining preprocessed procurement data, transportation data, risk data, inventory data, and multiple random scenarios of coal market price fluctuations, a sample-averaged approximate deterministic optimization model is constructed. The coal procurement cost is determined based on the procurement costs of medium- and long-term contract units and spot market units in the coal procurement data. The transportation cost is determined using the unit transportation cost per route and the unit transshipment cost per node from the transportation data. The risk management cost is determined based on the conditional value of risk, the risk aversion factor, and the total risk cost of spot procurement; Based on the coal procurement cost, the transportation cost, and the risk management cost, determine the comprehensive cost of coal procurement, transportation, and risk management. The stochastic procurement-transportation optimization problem is transformed into a deterministic optimization model by adopting a sample-averaged approximate deterministic optimization model. Under multiple constraints, a mixed-integer linear programming model is constructed with the goal of minimizing the comprehensive cost of coal procurement, transportation, and risk management.

[0010] This invention leverages a multi-dimensional dataset and constructs a deterministic integer programming optimization model using a sample averaging approximation method. This process integrates key influencing factors across the entire procurement-transportation chain, accurately characterizing the uncertainty of price fluctuations. It precisely breaks down the cost composition of coal procurement and transportation, determining coal procurement costs based on long-term contract unit procurement costs and spot market unit procurement costs. Transportation costs are calculated by combining route unit transportation costs and node unit transshipment costs. Furthermore, risk costs are quantified using conditional value of risk, risk aversion coefficient, and total risk cost of spot procurement, achieving comprehensive and accurate measurement of overall costs. With the goal of minimizing this overall cost, a mixed-integer linear programming model is constructed under multiple constraints. This ensures that the optimization direction focuses on cost control, and through comprehensive cost dimension considerations and scientific model construction, optimization decisions are more aligned with actual business scenarios, effectively improving the efficiency of procurement and transportation resource allocation.

[0011] In an optional implementation, before the step of iteratively solving the mixed-integer linear programming model based on multiple decision variables and determining the optimal procurement and transportation plan based on the optimal solution, the method further includes: Using the coal procurement volume from medium- and long-term contracts and the procurement volume from spot suppliers in the aforementioned coal procurement data, a total procurement volume constraint condition is constructed. Using the maximum supply capacity of a single supplier and the purchase volume of spot suppliers from the coal procurement data, constraints for spot suppliers are constructed. Using the transportation volume and maximum transportation capacity corresponding to the path between two nodes in the transportation data, construct the path transportation constraints between nodes; The flow balance constraints are constructed by using the first flow between the total outflow of coal procurement data and the procurement volume of the supplier, the second flow between the total inflow of coal procurement data and the total outflow of coal procurement data, the third flow between the total inflow of coal procurement data and the total outflow of coal procurement data, and the third flow between the total inflow of coal procurement data received by the power plant and the demand allocated to the power plant. Based on the coal supply, upper and lower limits of safety stock of the power plant, inventory constraints are constructed.

[0012] This invention provides rigorous boundary support for optimizing coal procurement and transportation by constructing multiple targeted constraints. It establishes total procurement constraints based on medium- and long-term contracts and spot market purchase volumes to ensure precise matching of supply and demand; it sets spot supplier constraints based on suppliers' maximum supply capacity to avoid the risk of over-capacity procurement; it constructs inter-node route transportation constraints by combining route transportation volume and maximum transport capacity to ensure compliant and controllable transportation; it constructs flow balance constraints through three types of transportation flow relationships to maintain quantity coordination in procurement, transshipment, and receiving stages; and it constructs inventory constraints based on power plant coal arrivals and upper and lower limits of safe inventory to ensure inventory remains within a safe range. These multiple constraints work together to effectively regulate procurement and transportation behavior and prevent decisions from deviating from actual business boundaries.

[0013] In one optional implementation, the iterative solution of the mixed-integer linear programming model based on multiple decision variables, and the determination of the optimal procurement and transportation plan based on the optimal solution, includes: Based on multiple decision variables, the mixed integer linear programming model is iteratively solved under all the coal market price fluctuation scenarios to obtain the initial procurement and transportation schemes corresponding to each coal market price fluctuation scenario, as well as the comprehensive costs of coal procurement, transportation and risk corresponding to the initial procurement and transportation schemes. Calculate the expected comprehensive cost of the initial procurement and transportation scheme under all the coal market price fluctuation scenarios, and determine whether the difference between the current expected comprehensive cost and the expected comprehensive cost of the previous iteration is less than the preset convergence accuracy threshold. If not, a new set of coal market price fluctuation scenarios will be generated, and the process will jump to the step of iteratively solving the mixed integer linear programming model based on multiple decision variables under all the coal market price fluctuation scenarios to obtain the initial procurement and transportation plan corresponding to each coal market price fluctuation scenario, as well as the comprehensive cost of coal procurement, transportation and risk corresponding to the initial procurement and transportation plan. If so, then accumulate the initial procurement and transportation plans corresponding to each coal market price fluctuation in all convergence rounds, sort the expected comprehensive costs of all the initial procurement and transportation plans, and determine the minimum expected comprehensive cost based on the sorting results; The initial procurement and transportation plan corresponding to the minimum expected overall cost is determined as the optimal procurement and transportation plan.

[0014] This invention is based on iteratively solving a mixed-integer linear programming model with multiple decision variables. It dynamically selects solutions by comparing cost with a preset threshold. If the threshold is not reached, new random scenarios are continuously generated and the solution is repeated to ensure sufficient exploration of the optimization space. Once the threshold is reached, the solutions are accumulated, ranked, and the solution with the minimum overall cost is selected as the optimal solution. This approach covers different market conditions through multi-scenario iteration and accurately identifies the optimal decision based on cost comparison and ranking.

[0015] In an optional implementation, the method further includes: The optimal procurement and transportation plan will be uploaded to the integrated management platform.

[0016] This invention uploads the optimal procurement and transportation solutions to a comprehensive management platform, enabling centralized management and sharing of these solutions. Relevant business departments can easily access unified and standardized optimal decision-making solutions, eliminating the need for repetitive calculations or the transmission of fragmented information, significantly improving the efficiency of solution implementation. Simultaneously, the platform-based presentation makes it easier to view and trace the solutions, facilitating collaboration among various stages and ensuring that procurement and transportation proceed along the optimal path, fully leveraging the solution's role in cost control and process optimization.

[0017] Secondly, the present invention provides a coal procurement and transportation collaborative optimization device, the device comprising: The simulation module is used to generate multiple coal market price fluctuation scenarios by combining coal procurement data and transportation data with Monte Carlo simulation. The module is used to transform the stochastic procurement-transportation optimization problem into a deterministic optimization model using a pre-defined sample-average approximate deterministic optimization model, and to construct a mixed-integer linear programming model under multiple constraints with the objective condition of minimizing the comprehensive cost of coal procurement, transportation and risk management. The solution module is used to iteratively solve the mixed integer linear programming model based on multiple decision variables, and determine the optimal procurement and transportation plan based on the optimal solution.

[0018] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the coal procurement and transportation collaborative optimization method of the first aspect or any corresponding embodiment described above.

[0019] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the coal procurement and transportation collaborative optimization method of the first aspect or any corresponding embodiment described above.

[0020] Fifthly, the present invention provides a computer program product, including computer instructions for causing a computer to execute the coal procurement and transportation collaborative optimization method of the first aspect or any corresponding embodiment described above. Attached Figure Description

[0021] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0022] Figure 1 This is a schematic diagram of the first process of the coal procurement and transportation collaborative optimization method according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the second process of the coal procurement and transportation collaborative optimization method according to an embodiment of the present invention; Figure 3 This is a structural block diagram of a coal procurement and transportation collaborative optimization device according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0025] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0026] This invention provides a method for the coordinated optimization of coal procurement and transportation. By integrating coal procurement and transportation data, and using the Monte Carlo method to generate multivariate price fluctuation stochastic scenarios, it comprehensively covers various situations that may arise from market price fluctuations, providing comprehensive and realistic scenario support for subsequent optimization decisions. Based on the generated scenarios, the stochastic optimization problem is transformed into a deterministic optimization problem using a sample average approximation method. With the goal of minimizing the overall cost, a mixed-integer linear programming model is constructed using multiple constraints to ensure that the model's optimization direction is clear and conforms to the actual business boundaries. Based on iterative solutions using multiple decision variables under various stochastic scenarios, the collaborative relationship between procurement and transportation can be accurately balanced, procurement volume and transportation capacity can be efficiently matched, and supplier selection, procurement allocation, and combinations of transportation routes and modes can be dynamically optimized. The final optimal solution can effectively reduce the overall cost of coal procurement and transportation, thereby improving the scientific nature and flexibility of procurement and transportation decisions and enhancing the supply chain's adaptability to market price fluctuations.

[0027] According to an embodiment of the present invention, a method for collaborative optimization of coal procurement and transportation is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0028] This embodiment provides a method for collaborative optimization of coal procurement and transportation. Figure 1 This is a flowchart of a coal procurement and transportation collaborative optimization method according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps: Step S101: Using coal procurement data and transportation data combined with Monte Carlo methods, multiple coal market price fluctuation scenarios are generated.

[0029] It should be noted that coal procurement data refers to various data related to coal procurement, including medium- and long-term contract prices, the maximum supply capacity of spot suppliers, and the spot price series for the past 12 months.

[0030] Transportation data refers to relevant data involved in the coal transportation process, covering feasible transportation routes for each node pair (supplier, power plant, station) in the transportation network, unit transportation costs for different routes, maximum transportation capacity, and average transshipment costs at transit nodes.

[0031] The Monte Carlo method refers to a numerical computation method based on random sampling and statistical simulation. It can transform complex problems into probabilistic statistical models and obtain numerical results through repeated random sampling.

[0032] Coal market price fluctuation scenarios refer to different scenarios generated by simulating spot price fluctuations in the market environment. Each scenario corresponds to a possible price trend, and the optimization results under different price fluctuations can be quantified.

[0033] In this embodiment of the invention, coal procurement data and transportation data are collected. The coal procurement data includes medium- and long-term contract prices, spot supplier supply capacity, and historical spot price series. The transportation data includes feasible transportation routes between each node pair, unit transportation cost, maximum load, and unit transfer cost of transit nodes. The collected data undergoes outlier truncation, missing value supplementation, and format standardization preprocessing to ensure data quality. Then, based on the Monte Carlo simulation method, random variables are preset with spot prices as the core. By fitting the probability distribution of the random variables, a joint random scenario set is generated, thereby obtaining multiple coal market price fluctuation scenarios.

[0034] Step S102: The stochastic procurement-transportation optimization problem is transformed into a deterministic optimization model using a pre-defined sample average approximate deterministic optimization model. Under multiple constraints, a mixed integer linear programming model is constructed with the goal of minimizing the comprehensive cost of coal procurement, transportation, and risk management.

[0035] It should be noted that constraints refer to the rules that ensure the optimization solution conforms to the actual business boundaries.

[0036] The comprehensive cost of coal procurement and transportation refers to the total expenses incurred throughout the entire process of coal procurement and transportation.

[0037] The Sample Average Approximate Deterministic Optimization Model (SAA Deterministic Optimization Model) refers to the method of using sample average approximation to transform an uncertain optimization problem containing random variables into a deterministic model that can be directly solved.

[0038] Mixed Integer Linear Programming (MILP) model refers to a mathematical optimization model that combines the characteristics of linear programming and integer programming.

[0039] In this embodiment of the invention, multiple constraints are clearly defined, including total procurement volume constraints, spot supplier constraints, inter-node route transportation constraints, flow balance constraints, and inventory constraints. Then, the coal procurement cost is determined based on the medium- and long-term contract unit procurement cost and the spot unit procurement cost in the coal procurement data. The transportation cost is calculated by combining the route unit transportation cost and the node unit transshipment cost in the transportation data. The risk management cost, quantified by the conditional risk value, risk aversion coefficient, and the total risk cost of spot procurement, is superimposed to form the comprehensive cost of coal procurement, transportation, and risk management. Finally, with the minimization of this comprehensive cost as the objective condition, a deterministic optimization model, the above constraints, and the cost composition are integrated to construct a mixed integer linear programming model containing integer variables (such as supplier selection and route selection) and continuous variables (such as procurement volume and transportation volume).

[0040] Step S103: Based on multiple decision variables, iteratively solve the mixed integer linear programming model, and determine the optimal procurement and transportation plan based on the optimal solution.

[0041] It should be noted that decision variables refer to the methods of making optimization decisions based on multiple interrelated decision variables.

[0042] Iterative solution refers to the cyclical process of repeatedly substituting different scenario data, solving the model, and comparing the results.

[0043] The optimal solution refers to the combination of decision variables that satisfies the constraints and minimizes the overall cost of coal procurement and transportation among all the solutions for random scenarios.

[0044] The optimal procurement and transportation plan refers to a feasible and implementable plan based on the optimal solution.

[0045] In this embodiment of the invention, the decision variables covered by the multiple decision variables are clearly defined, including the purchase volume of medium- and long-term contracts, the selection and purchase volume of spot suppliers, the selection of transportation methods and routes, the transportation volume and the transshipment volume of transit nodes, etc. The properties of integer variables and continuous variables are distinguished. Then, the deterministic parameters under the random price fluctuation scenario are substituted into the mixed integer linear programming model. A linear solver is used to iteratively solve each scenario, and the corresponding procurement plan, transportation plan and expected comprehensive cost are output. By comparing the solution results under all scenarios, the solution with the optimal expected comprehensive cost is selected. Then, based on the optimal solution, the optimal procurement and transportation plan including the allocation of medium- and long-term contract purchases, the selection and purchase volume of spot suppliers, the combination of transportation routes and methods, and the transshipment plan are determined.

[0046] This embodiment provides a method for collaborative optimization of coal procurement and transportation. Figure 2 This is a flowchart of a coal procurement and transportation collaborative optimization method according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps: Step S201: Using coal procurement data and transportation data combined with Monte Carlo methods, multiple coal market price fluctuation scenarios are generated.

[0047] Specifically, step S201 includes: Step S2011: Obtain coal procurement data, transportation data, risk data, and inventory data.

[0048] It should be noted that risk data refers to the core parameters related to the quantification and control of price fluctuation risks in the coal procurement process.

[0049] Inventory data refers to data directly related to coal inventory management in power plants.

[0050] In this embodiment of the invention, coal procurement and inventory data of enterprises are extracted. The average price of medium- and long-term contracts over the past three years is extracted and used as a fixed parameter. The maximum supply capacity of each supplier and spot price data for the past 12 months are collected and organized into price series by supplier category for subsequent risk scenario generation. Demand data and safety stock upper and lower limits for each power plant are extracted. The total coal demand is determined based on the power plant's annual coal consumption plan and inventory targets.

[0051] Import transportation data. Identify feasible transportation routes (rail, road, waterway) for all node pairs, recording the unit transportation cost and maximum capacity for each route. Nodes include suppliers, power plants, and stations. For transit nodes, set average transshipment costs and allowed mode-of-transport rules.

[0052] Set risk data. Set the CVaR confidence level (e.g., 95%) and risk aversion coefficient (e.g., 0.5, reflecting the degree of importance attached to price volatility risk).

[0053] Step S2012 involves preprocessing the coal procurement data, transportation data, risk data, and inventory data.

[0054] It should be noted that data preprocessing refers to a series of standardized and cleaned processing operations performed on the collected coal procurement data, transportation data, risk data, and inventory data.

[0055] In this embodiment of the invention, for data with extreme values ​​such as transportation costs and spot prices (e.g., deviations from the mean by more than three standard deviations), a "truncation method" is used to replace them with reasonable boundary values, outputting a cleaned dataset without anomalies. The proportion of missing data for each field is statistically analyzed, and its impact on the model is assessed. If it is core data, supplementary data collection is initiated, outputting a complete dataset without missing data. Data formats and units are standardized to eliminate the influence of units of measurement, and the logical relationships between data are verified to ensure consistency. The preprocessed data is converted into a parameter format that the model can directly call, outputting a model input parameter table (including deterministic and uncertain parameters).

[0056] Step S2013: The Monte Carlo simulation method is used to generate random scenarios, resulting in multiple coal market price fluctuation scenarios.

[0057] It should be noted that the pre-defined random variables refer to uncertain variables that are defined in advance and have a key impact on coal procurement costs.

[0058] Specifically, Monte Carlo simulations are used to generate random scenarios and simulate market price fluctuations. This includes: identifying the core uncertainties affecting purchasing decisions, constructing a probability distribution model to fit a probability distribution to each random variable, using Monte Carlo simulation to generate a joint random scenario Ω, and assigning equal values ​​to each scenario.

[0059] Step S202: The stochastic procurement-transportation optimization problem is transformed into a deterministic optimization model using a pre-defined sample average approximate deterministic optimization model. Under multiple constraints, a mixed integer linear programming model is constructed with the goal of minimizing the comprehensive cost of coal procurement, transportation, and risk management.

[0060] Specifically, step S202 includes: Step S2021: Using preprocessed procurement data, transportation data, risk data, inventory data, and multiple random scenarios of coal market price fluctuations, a sample average approximate deterministic optimization model is constructed.

[0061] In this embodiment of the invention, the spot price of the preprocessed procurement data is used as the core anchor for a preset random variable. The conditional value of risk confidence level and risk aversion coefficient in the preprocessed risk data are incorporated into the model. The basic parameter system of the model is built by combining the unit procurement costs of medium and long-term contracts and spot goods in the procurement data, the route costs and transportation capacity in the transportation data, and the upper and lower limits of safety stock and total demand in the inventory data. That is, the sample average approximate deterministic optimization model. The optimization problem containing price fluctuation uncertainty in the sample average approximate deterministic optimization model is transformed into a deterministic problem through the sample average approximate method. At the same time, the basic constraint logic corresponding to the data is embedded, so that the model can accurately adapt to the collaborative scenario of coal procurement-transportation-inventory-risk.

[0062] It is worth mentioning that, based on the coal demand of power plants, enterprises coordinate and optimize procurement plans and transportation routes to achieve goals such as meeting demand, reducing risk, and optimizing costs. The model's expected cost includes the costs incurred from procurement, transportation, and risk. The task now is to transport each order from its origin to its destination, solving the problem of coordinated optimization of coal procurement and multimodal transport under price fluctuations. This involves deciding on spot suppliers and procurement quantities, selecting transportation routes, and choosing the appropriate transportation mode to minimize overall operating costs. Based on this, the following assumptions are made: 1) The total demand of power plants is known, and the upper and lower limits of inventory for each power plant are known. The medium- and long-term contract prices and supplier supply capacity are deterministic data, and it is assumed that all coal within the supplier's capacity can be supplied.

[0063] 2) Goods cannot be split. During the transportation of the same batch of coal from the supplier to the power plant, the transportation volume remains unchanged. The mode of transportation can only be changed at the transit node.

[0064] 3) Transit nodes are transfer nodes between modes of transportation, simplifying ordinary nodes in the middle of the route. All transportation nodes in the network can be used for transfer operations.

[0065] 4) The transit node's transit capacity can meet the transit demand. Assuming that only transit costs need to be considered, there is no need to impose additional constraints on the maximum transit volume.

[0066] 5) The transportation route for medium- and long-term coal contracts is fixed, and the transportation cost of medium- and long-term contracts equals the purchase quantity and the unit transportation cost, which is known.

[0067] 6) Assume that all coal purchased is thermal coal, and do not consider coal quality parameters such as calorific value and sulfur content, and do not need to consider the cost of blending.

[0068] Based on the above assumptions and the obtained coal procurement, transportation, risk, and inventory data, Table 1 below lists the corresponding parameters of the mixed-integer linear programming model, including sets, parameters, and decision variables. The decision variables cover three core decision categories: procurement, transportation, and transshipment. See Table 1 for details. Table 1. Model parameters and decision variables

[0069] Step S2022: Determine the coal procurement cost based on the procurement costs of medium- and long-term contract units and spot unit procurement costs in the coal procurement data.

[0070] It should be noted that the unit procurement cost of medium- and long-term contracts refers to the unit coal price agreed upon when the enterprise signs a medium- and long-term procurement agreement with the supplier.

[0071] Spot unit purchase cost refers to the real-time unit price of coal purchased from spot suppliers.

[0072] Coal procurement cost refers to the total expenses incurred in the coal procurement process, which is obtained by adding the total cost of medium- and long-term contract procurement to the total cost of spot procurement.

[0073] In this embodiment of the invention, the procurement cost is the price cost of purchasing coal from suppliers, consisting of the procurement cost of long-term contract suppliers and the procurement cost of spot suppliers. The procurement cost of long-term contract suppliers is affected by the purchase volume, while the procurement cost of spot suppliers fluctuates with the price. Coal procurement cost The calculation formula is:

[0074] In the formula, This indicates the procurement cost of units under medium- and long-term contracts; This indicates the volume of coal purchased under medium- and long-term contracts; Indicates spot supplier s In the context The unit purchase price below; Indicates spot supplier s Purchase volume; This indicates the selection of spot suppliers.

[0075] Step S2023: Determine the transportation cost using the unit transportation cost per route and the unit transshipment cost per node from the transportation data.

[0076] It should be noted that the unit transportation cost refers to the transportation cost per unit of coal when it travels along a certain transportation route (such as railway, highway, or waterway).

[0077] Unit transshipment cost refers to the transshipment fee incurred per unit of coal when it is loaded, unloaded, temporarily stored, or transported at transshipment nodes (such as ports and freight stations).

[0078] Transportation cost refers to the total expense incurred in the entire coal transportation process, which is obtained by adding the total cost of the route transportation to the total cost of the node transshipment.

[0079] In this embodiment of the invention, transportation cost refers to the cost of transporting coal from the supplier to the power plant, mainly including the unit transportation cost per route and the unit transshipment cost per node. Transportation cost encompasses three parts: rail transportation, road transportation, and waterway transportation costs, calculated based on transportation volume and unit transportation cost. Transshipment cost is calculated based on transshipment cargo volume and unit transshipment cost, and its calculation formula is as follows:

[0080] In the formula, Represents a node i To the node j The route adopts transportation methods m The unit transportation cost; Indicates from node i By transportation m Inflow node j Coal transportation volume; Represents a node i To the node j Whether to select a transportation method for the route m ; Indicates supplier s The unit transportation cost; Indicates a transit node t The volume of transshipment; Indicates a transit node t Whether to transfer; This indicates the unit transportation cost of coal under medium- and long-term contracts; This indicates the amount of coal purchased under medium- and long-term contracts.

[0081] Step S2024: Determine the risk management cost based on the conditional risk value, risk aversion coefficient, and total risk cost of spot procurement.

[0082] It should be noted that conditional value at risk (VaR) is a quantitative indicator that measures the extreme risk loss that price fluctuations may cause under a pre-set confidence level, reflecting the average loss beyond the value at risk (VaR).

[0083] The risk aversion coefficient is a parameter that reflects a company's tolerance for price volatility risk.

[0084] The total risk cost of spot procurement refers to the total amount of potential losses that may occur in the spot procurement process, calculated based on historical spot price fluctuation data.

[0085] Risk management cost refers to the potential loss cost caused by fluctuations in spot coal prices. It is determined by the risk aversion coefficient, conditional risk value, and the total risk cost of spot procurement.

[0086] In this embodiment of the invention, risk management cost is the potential loss caused by spot price fluctuations, quantified by CVaR (Conditional Value at Risk). Specifically, it is the conditional expected loss when the loss exceeds VaR (the maximum possible loss at a given confidence level), at a given confidence level (e.g., 95%). Risk management cost is based on the risk aversion coefficient. and confidence level The conditional value of risk is calculated using the following formula:

[0087] Among them, the total risk cost of spot purchasing (random variable) The expression is shown in the following formula. For random spot prices, For spot purchase volume:

[0088] In the worst case The average excess loss of spot procurement costs under certain circumstances is calculated using the following formula:

[0089] In the formula, v The risk threshold represents... At the confidence level, the unit purchase cost of spot goods shall not exceed v The probability is ; This indicates that only "costs exceeding" are calculated. v The "part" refers to extreme losses, if the cost is lower than the extreme losses. v The loss is then 0.

[0090] Step S2025: Determine the comprehensive cost of coal procurement, transportation, and risk management based on coal procurement costs, transportation costs, and risk management costs.

[0091] In this embodiment of the invention, the calculated coal procurement cost, transportation cost and risk cost are directly added together to form a comprehensive cost covering the entire procurement and transportation process and price fluctuation risks, namely the comprehensive cost of coal procurement, transportation and risk management.

[0092] Step S2026: The stochastic procurement-transportation optimization problem is transformed into a deterministic optimization model using a sample-averaged approximate deterministic optimization model. Under multiple constraints, a mixed-integer linear programming model is constructed with the goal of minimizing the comprehensive cost of coal procurement, transportation, and risk management.

[0093] In this embodiment of the invention, a sample-averaged approximate deterministic optimization model is used to transform the stochastic procurement-transportation optimization problem into a deterministic optimization model. Based on multiple sets of coal market price fluctuation scenario samples generated by Monte Carlo simulation, the sample mean is used to replace random variables, eliminating the impact of price randomness on the optimization problem. The original procurement-transportation decision problem containing random parameters is transformed into a deterministic problem that can be solved precisely. Then, under the core constraint system of total procurement volume constraints, spot supplier constraints, inter-node path transportation constraints, flow balance constraints, and inventory constraints, a mixed integer linear programming model is constructed with the goal of minimizing the comprehensive cost of coal procurement, transportation, and risk management. The integrated coal procurement cost, transportation cost, and risk management cost accounting formulas are embedded as the objective function, and the attributes and value ranges of integer and continuous decision variables are defined to ensure that the model is both suitable for deterministic solution requirements and meets the full-link business constraints and cost optimization objectives.

[0094] Specifically, the objective function constructed with the goal of minimizing the overall cost of coal procurement, transportation, and risk management is as follows:

[0095] In the formula, This indicates the cost of coal procurement; Indicates transportation costs; This indicates the cost of risk management.

[0096] In some optional implementations, prior to step S203, the method further includes: Step a1: Use the coal purchase volume from medium- and long-term contracts and the purchase volume from spot suppliers in the coal purchase data to construct the total purchase volume constraint.

[0097] It should be noted that the medium- and long-term coal purchase volume refers to the quantity of coal that an enterprise needs to purchase within a certain period, as stipulated in the medium- and long-term coal purchase agreement signed with the supplier.

[0098] The purchase volume of spot suppliers refers to the amount of coal that an enterprise flexibly purchases from spot suppliers without medium- or long-term agreements, based on market prices and actual needs, and can be adjusted according to price fluctuations.

[0099] Total procurement constraints refer to the constraint rules constructed based on procurement demand and actual procurement volume.

[0100] In this embodiment of the invention, the total procurement volume constraint is to meet the supply and demand matching requirement, where the sum of medium- and long-term contract procurement and spot procurement equals the total demand of power plants. D The specific expression is:

[0101] In the formula, This indicates the volume of coal purchased under medium- and long-term contracts; Indicates spot supplier s Purchase volume.

[0102] Step a2: Using the maximum supply capacity of a single supplier and the purchase volume of spot suppliers in the coal procurement data, construct the constraints for spot suppliers.

[0103] It should be noted that the maximum supply capacity of a single supplier refers to the maximum amount of coal that a single spot supplier can stably supply within the optimization period, based on its own production capacity, inventory, and logistics capabilities.

[0104] The purchase volume of spot suppliers refers to the quantity of coal that an enterprise flexibly purchases from spot suppliers.

[0105] Spot supplier constraints refer to the constraint rules constructed based on the spot supplier's supply capacity and purchase volume.

[0106] In this embodiment of the invention, the constraints for spot suppliers are that the purchase volume of a single supplier does not exceed its maximum supply capacity, and only the selected suppliers have purchase volume. For suppliers s The maximum supply capacity. The purchase quantity of each supplier is non-negative, and supplier selection is a 0-1 variable. The constraint expression for spot suppliers is:

[0107]

[0108] In the formula, Indicates the selection of spot suppliers ( Indicates the selection of suppliers , (Indicates no selection); Indicates spot supplier s Purchase quantity (only when) (Value taken at time).

[0109] Step a3: Using the transportation volume and maximum transportation capacity corresponding to the path between two nodes in the transportation data, construct the path transportation constraints between nodes.

[0110] It should be noted that the path between two nodes refers to the passable transportation route between two nodes (supplier, transit node, power plant) in the coal transportation network, including single or combined transport routes such as railway, highway, and waterway.

[0111] Transport volume refers to the amount of coal transported through a certain path between two nodes.

[0112] Maximum transport capacity refers to the maximum amount of coal that a certain path between two nodes can stably transport within an optimization period, based on factors such as route specifications and transport vehicle capacity.

[0113] Inter-node path transportation constraints refer to constraint rules constructed based on path transportation volume and maximum transportation capacity.

[0114] In this embodiment of the invention, the inter-node path transportation constraint is that the transportation volume of the path from node i to j using method m does not exceed the maximum transportation capacity of that path, i.e. Only the selected paths are eligible for transport. The transport volume for each path is non-negative, and path selection is represented by a 0-1 variable. The expression for the inter-node path transport constraints is as follows:

[0115]

[0116] In the formula, Represents a node i To the node j On the route, via transportation m The amount of coal transported (tons). Represents a node i To the node j Whether to select a transportation method for the route ( (Indicates a choice).

[0117] Step a4: Construct flow balance constraints by using the first flow between the total outflow of coal procurement data and the procurement volume of suppliers, the second flow between the total inflow to transit nodes and the total outflow to transit nodes, and the third flow between the total transportation volume received by power plants and the demand allocated to power plants.

[0118] It should be noted that the first transportation flow refers to the transportation flow balance relationship on the supplier side, which is the total outflow transportation volume and corresponding procurement volume of the core related suppliers.

[0119] The second transport flow refers to the transport flow balance relationship of transit nodes, which relates the total transport volume flowing into the transit node to the total transport volume flowing out of the node.

[0120] The third transport flow refers to the balance of transport flows at the power plant end, which relates the total transport volume received by the power plant to the demand allocated to the power plant.

[0121] Flow balance constraints refer to the full-link quantity balance constraint rules constructed based on three types of transport flows.

[0122] In this embodiment of the invention, the flow balance constraint condition is the supplier. s The total outbound transportation volume equals the volume purchased from that supplier and flows into the transit node. t The total transport volume equals the total transport volume leaving this node (goods cannot be split), power plant p The total volume of transported goods received equals the demand allocated to the power plant. The expression for the flow balance constraint is:

[0123]

[0124]

[0125]

[0126] In the formula, Indicates spot supplier s Purchase quantity (only when) (Time value); Indicates from supplier s By transportation m Send to node j Coal transportation volume; Indicates from node i By transportation m Inflow transit node t Coal transportation volume; Indicates from node i By transportation Inflow transit node t Coal transportation volume; Indicates from node i By transportation m Flowing into power plants p Coal transportation volume; D This indicates the total demand for coal procurement.

[0127] Step a5: Based on the power plant's coal supply, the upper and lower limits of safety stock, construct inventory constraints.

[0128] It should be noted that the coal delivery volume refers to the amount of coal that is ultimately delivered to the power plant through the transportation process.

[0129] The upper limit of safety stock refers to the maximum amount of coal that a power plant's storage facilities can hold.

[0130] The lower limit of safety stock refers to the minimum amount of coal inventory required to ensure the normal operation of a power plant.

[0131] Inventory constraints refer to the constraint rules constructed based on the amount of coal delivered to the power plant and the upper and lower limits of the safety inventory.

[0132] In this embodiment of the invention, the amount of coal delivered to the power plant needs to meet the upper and lower limits of the safety stock. The expression for the stock constraint is:

[0133] In the formula, Indicates power plant P The minimum safety stock level; Indicates from node i By transportation m Flowing into power plants p Coal transportation volume; Indicates power plant P The upper limit of safety stock.

[0134] Step S203: Based on multiple decision variables, iteratively solve the mixed integer linear programming model, and determine the optimal procurement and transportation plan based on the optimal solution.

[0135] In some optional implementations, step S203 above includes: Step S2031: Based on multiple decision variables, iteratively solve the mixed integer linear programming model under all coal market price fluctuation scenarios to obtain the initial procurement and transportation plans corresponding to each coal market price fluctuation scenario, as well as the comprehensive costs of coal procurement, transportation, and risks corresponding to the initial procurement and transportation plans.

[0136] It should be noted that the initial procurement and transportation plan refers to the procurement volume allocation, transportation route planning, and inventory allocation plan obtained through model iteration under a single coal market price fluctuation scenario.

[0137] The combined cost of coal procurement, transportation, and risk refers to the combined cost of the initial procurement and transportation plan.

[0138] In this embodiment of the invention, the core decision variables are the purchase volume of medium and long-term contracts, the purchase volume of each spot supplier, and the transportation volume of each route. For each coal market price fluctuation scenario, the variables are substituted into a mixed integer linear programming model for repeated iterative calculations. The values ​​of the decision variables are optimized one by one to approach the minimum comprehensive cost. At the same time, it is verified whether each value meets the constraints of the entire chain and invalid solutions that do not meet the constraints are eliminated. Finally, the initial procurement and transportation plan corresponding to each scenario is obtained, as well as the comprehensive cost of coal procurement, transportation and risk accurately calculated under the plan.

[0139] Step S2032: Calculate the expected comprehensive cost of the initial procurement and transportation schemes under all coal market price fluctuation scenarios, and determine whether the difference between the current expected comprehensive cost and the expected comprehensive cost of the previous iteration is less than the preset convergence accuracy threshold.

[0140] It should be noted that the preset convergence accuracy threshold refers to the quantitative criterion used to determine whether the iterative solution has converged. The stability of the model solution is verified by comparing the relative difference of the expected comprehensive cost obtained from two adjacent iterations.

[0141] In this embodiment of the invention, the expected comprehensive cost of the initial procurement and transportation scheme under each coal market price fluctuation scenario is calculated, and the difference between the current expected comprehensive cost under all scenarios in the current round and the expected comprehensive cost of the previous iteration is calculated, and the difference is compared with the preset convergence accuracy threshold.

[0142] Step S2033: If not, then regenerate a new set of coal market price fluctuation scenarios and jump to execute the step of iteratively solving the mixed integer linear programming model based on multiple decision variables under all coal market price fluctuation scenarios to obtain the initial procurement and transportation schemes corresponding to each coal market price fluctuation scenario, as well as the comprehensive costs of coal procurement, transportation and risk corresponding to the initial procurement and transportation schemes.

[0143] It should be noted that if the expected comprehensive cost under all scenarios in the current round is greater than or equal to the preset convergence accuracy threshold, then the Monte Carlo simulation method is used to regenerate a new coal market price fluctuation scenario, and step S2031 is repeated.

[0144] Step S2034: If yes, then accumulate the initial procurement and transportation plans corresponding to each coal market price fluctuation in all convergence rounds, sort the expected comprehensive costs of all initial procurement and transportation plans, and determine the minimum expected comprehensive cost based on the sorting results.

[0145] It should be noted that the expected total cost minimum refers to the expected total cost value that ranks first after sorting, corresponding to the feasible initial solution with the best cost.

[0146] In this embodiment of the invention, if the current expected comprehensive cost under all scenarios in the current round is less than the preset convergence accuracy threshold, then the initial procurement and transportation schemes corresponding to all scenarios in the current round are accumulated, and all feasible initial schemes that meet the constraints under each scenario are uniformly collected and organized. At the same time, the single-scenario comprehensive cost and the expected comprehensive cost of the whole scenario corresponding to each scheme are recorded. Then, the expected comprehensive costs of all feasible initial schemes are sorted in ascending order, and abnormal cost values ​​appearing in the sorting process are eliminated. Based on the sorting result, the expected comprehensive cost value at the top is locked and determined as the minimum expected comprehensive cost under the whole scenario. The initial procurement and transportation scheme corresponding to the minimum value is taken as the robust optimal procurement and transportation scheme under the whole scenario.

[0147] Step S2035: Determine the initial procurement and transportation plan corresponding to the minimum expected overall cost as the optimal procurement and transportation plan.

[0148] In this embodiment of the invention, the initial procurement and transportation plan corresponding to the minimum expected comprehensive cost is determined as the optimal procurement and transportation plan. Simultaneously, it is verified whether the plan fully meets the constraints of the entire procurement, transportation, inventory and risk chain, ensuring that the plan has both cost optimization and practical feasibility. At the same time, the core parameters of the plan, such as the allocation of medium and long-term contracts and spot procurement volume, transportation route planning and inventory allocation, are integrated to form a standardized plan document.

[0149] Step S204: Upload the optimal procurement and transportation plan to the integrated management platform.

[0150] It should be noted that the integrated management platform refers to an integrated management system that integrates multiple business modules such as coal procurement, transportation, inventory, and cost control.

[0151] In this embodiment of the invention, the optimal procurement and transportation plan is uploaded to the integrated management platform. Core data such as the minimum comprehensive cost, procurement quantity allocation, transportation route planning, inventory control parameters, and constraint verification results corresponding to the plan are uploaded simultaneously to ensure that the information received by the platform is complete and traceable. At the same time, the platform's data synchronization mechanism is triggered to push the optimal plan to the corresponding business modules such as procurement, transportation, and warehousing, so as to facilitate the collaborative implementation of the plan by various departments. The platform also supports real-time monitoring and dynamic tracking of the plan execution process.

[0152] In a specific embodiment, the implementation of this method further includes: (1) Data preprocessing and scene generation 1) Input data The parameters to be determined include long-term contract price, transportation cost, transshipment cost, power plant demand, inventory limit, CVaR confidence level (95%), and risk aversion coefficient (0.5). The random parameters include spot price.

[0153] 2) Monte Carlo scene generation Generate N price scenarios (e.g., N=500), and assign equal probability to each scenario.

[0154] (2) Linearization Introduce auxiliary variables: VaR (risk threshold); Excess loss in a given scenario.

[0155] The linearized objective function is obtained as follows:

[0156] New constraints:

[0157] (3) Constructing a deterministic MILP model Table 2 MILP Model Parameters and Decision Variables

[0158] (4) Solve the model and output the solution Solve the MILP model using linear solvers such as Gurobi and output the optimal decision.

[0159] Table 3 Scheme Output Indicators

[0160] It is worth mentioning that the present invention has the following beneficial effects: This invention enables collaborative optimization across multiple stages of procurement and transportation. By constructing a joint procurement-transportation decision-making model, it integrates the dynamic balancing of medium- and long-term agreements and spot procurement, multimodal transport route optimization, and price fluctuation risk management into a unified framework, forming a closed-loop optimization system. This method overcomes the limitations of isolated optimization of each stage of the traditional supply chain, achieving efficient collaboration between procurement plans and transportation resources. It not only reduces the risk of dependence on a single supplier but also significantly improves procurement flexibility and overall risk resistance, ensuring the stability and economy of the supply chain in complex market environments.

[0161] This invention enables dynamic risk management. It innovatively introduces a CVaR risk quantification model at the procurement end, transforming price fluctuation risk into an adjustable variable in the objective function. Through a risk aversion coefficient, it flexibly balances the stability of long-term supply contracts with the cost elasticity of spot procurement. This mechanism enables the supply chain to dynamically adapt to market fluctuations, effectively controlling extreme price risks while ensuring supply, thereby systematically improving supply chain resilience and reducing the probability of supply disruptions and overall operating costs.

[0162] This embodiment also provides a coal procurement and transportation collaborative optimization device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0163] This embodiment provides a coal procurement and transportation collaborative optimization device, such as... Figure 3 As shown, it includes: Simulation module 301 is used to generate multiple coal market price fluctuation scenarios by using coal procurement data and transportation data and combining them with Monte Carlo simulation. Module 302 is used to transform the stochastic procurement-transportation optimization problem into a deterministic optimization model using a pre-defined sample-average approximate deterministic optimization model, and to construct a mixed-integer linear programming model under multiple constraints with the objective condition of minimizing the comprehensive cost of coal procurement, transportation and risk management. The solver module 303 is used to iteratively solve a mixed-integer linear programming model based on multiple decision variables, and determine the optimal procurement and transportation plan based on the optimal solution.

[0164] In some alternative implementations, simulation module 301 includes: The acquisition unit is used to acquire coal procurement data, transportation data, risk data, and inventory data; The preprocessing unit is used to preprocess coal procurement data, transportation data, risk data, and inventory data. The simulation unit is used to generate random scenarios using the Monte Carlo simulation method, resulting in multiple coal market price fluctuation scenarios.

[0165] In some alternative implementations, the construction module 302 includes: Model units are constructed to combine preprocessed procurement data, transportation data, risk data, inventory data, and multiple random scenarios of coal market price fluctuations to build a sample-averaged approximate deterministic optimization model. The procurement cost unit is used to determine the coal procurement cost based on the procurement costs of medium- and long-term contract units and spot unit procurement costs in the coal procurement data. The transportation cost unit is used to determine the transportation cost by using the line unit transportation cost and node unit transshipment cost in the transportation data. The risk cost unit is used to determine risk management costs based on conditional risk value, risk aversion coefficient, and total risk cost of spot procurement. The comprehensive cost unit is used to determine the comprehensive cost of coal procurement, transportation, and risk management based on coal procurement costs, transportation costs, and risk management costs. The objective condition unit is used to transform the stochastic procurement-transportation optimization problem into a deterministic optimization model using a sample-averaged approximate deterministic optimization model, and to construct a mixed-integer linear programming model under multiple constraints with the objective condition of minimizing the comprehensive cost of coal procurement, transportation and risk management.

[0166] In some alternative embodiments, the device further includes: The first construction subunit is used to construct total procurement constraints by using the medium- and long-term contract coal procurement volume and the spot supplier procurement volume in the coal procurement data. The second construction subunit is used to construct the constraints for spot suppliers by using the maximum supply capacity of a single supplier and the purchase volume of spot suppliers in the coal procurement data. The third construction subunit is used to construct inter-node path transportation constraints by using the transportation volume and maximum transportation capacity corresponding to the path between two nodes in the transportation data. The fourth sub-unit is used to construct flow balance constraints by using the first flow between the total outflow of suppliers and the procurement volume of suppliers in the coal procurement data, the second flow between the total inflow of suppliers to transit nodes and the total outflow of suppliers to transit nodes, and the third flow between the total transportation volume received by power plants and the demand allocated to power plants. The fifth construction sub-unit is used to construct inventory constraints based on the power plant's coal supply, upper and lower limits of safety stock.

[0167] In some alternative implementations, the solver module 303 includes: The solution unit is used to iteratively solve the mixed integer linear programming model based on multiple decision variables under all coal market price fluctuation scenarios, to obtain the initial procurement and transportation plans corresponding to each coal market price fluctuation scenario, as well as the comprehensive costs of coal procurement, transportation and risk corresponding to the initial procurement and transportation plans. The judgment unit is used to calculate the expected comprehensive cost of the initial procurement and transportation plan under all coal market price fluctuation scenarios, and to determine whether the difference between the current expected comprehensive cost and the expected comprehensive cost of the previous iteration is less than the preset convergence accuracy threshold. The jump unit is used to regenerate a new set of coal market price fluctuation scenarios if no, and then jump to execute the steps of iteratively solving the mixed integer linear programming model based on multiple decision variables under all coal market price fluctuation scenarios to obtain the initial procurement and transportation plans corresponding to each coal market price fluctuation scenario, as well as the comprehensive costs of coal procurement, transportation and risk corresponding to the initial procurement and transportation plans. The sorting unit is used to accumulate the initial procurement and transportation plans corresponding to each coal market price fluctuation in all convergence rounds if the conditions are met, sort the expected comprehensive costs of all initial procurement and transportation plans, and determine the minimum expected comprehensive cost based on the sorting results. The optimal solution unit is used to determine the initial procurement and transportation plan corresponding to the minimum expected overall cost as the optimal procurement and transportation plan.

[0168] In some alternative embodiments, the device further includes: The upload unit is used to upload the optimal procurement and transportation plan to the integrated management platform.

[0169] The coal procurement and transportation collaborative optimization device provided in this embodiment of the invention can execute the coal procurement and transportation collaborative optimization method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects for executing the method. Further functional descriptions of the above modules and units are the same as in the corresponding embodiments described above, and will not be repeated here.

[0170] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0171] The following is a detailed reference. Figure 4 This diagram illustrates a structural schematic suitable for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 401, which can perform various appropriate actions and processes based on a program stored in read-only memory (ROM) 402 or a program loaded from memory 408 into random access memory (RAM) 403. RAM 403 also stores various programs and data required for the operation of the electronic device. The processor 401, ROM 402, and RAM 403 are interconnected via bus 404. Input / output (I / O) interface 405 is also connected to bus 404.

[0172] Typically, the following devices can be connected to I / O interface 405: input devices 406 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 407 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 408 including, for example, magnetic tapes, hard disks, etc.; and communication devices 409. Communication device 409 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 4 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0173] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 409, or installed from a memory 408, or installed from a ROM 402. When the computer program is executed by the processor 401, it performs the functions defined in the coal procurement and transportation collaborative optimization method of the embodiments of the present invention.

[0174] Figure 4 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0175] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the coal procurement and transportation collaborative optimization method shown in the above embodiments is implemented.

[0176] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0177] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for collaborative optimization of coal procurement and transportation, characterized in that, The method includes: By combining coal procurement and transportation data with Monte Carlo data, multiple scenarios of coal market price fluctuations were generated. The stochastic procurement-transportation optimization problem is transformed into a deterministic optimization model using a pre-defined sample-average approximate deterministic optimization model. Under multiple constraints, a mixed-integer linear programming model is constructed with the goal of minimizing the comprehensive cost of coal procurement, transportation, and risk management. Based on multiple decision variables, the mixed-integer linear programming model is solved iteratively, and the optimal procurement and transportation plan is determined based on the optimal solution.

2. The method according to claim 1, characterized in that, The method of combining coal procurement data and transportation data with Monte Carlo simulations to generate multiple coal market price fluctuation scenarios includes: Obtain coal procurement data, transportation data, risk data, and inventory data; Data preprocessing is performed on the coal procurement data, the transportation data, the risk data, and the inventory data; The Monte Carlo simulation method was used to generate random scenarios, resulting in multiple scenarios of coal market price fluctuations.

3. The method according to claim 2, characterized in that, The method utilizes a pre-defined sample-average approximate deterministic optimization model to transform the stochastic procurement-transportation optimization problem into a deterministic optimization model. Under multiple constraints, and with the objective of minimizing the comprehensive cost of coal procurement, transportation, and risk management, a mixed-integer linear programming model is constructed, including: By combining preprocessed procurement data, transportation data, risk data, inventory data, and multiple random scenarios of coal market price fluctuations, a sample-averaged approximate deterministic optimization model is constructed. The coal procurement cost is determined based on the procurement costs of medium- and long-term contract units and spot market units in the coal procurement data. The transportation cost is determined using the unit transportation cost per route and the unit transshipment cost per node from the transportation data. The risk management cost is determined based on the conditional value of risk, the risk aversion factor, and the total risk cost of spot procurement; Based on the coal procurement cost, the transportation cost, and the risk management cost, determine the comprehensive cost of coal procurement, transportation, and risk management. The stochastic procurement-transportation optimization problem is transformed into a deterministic optimization model by adopting a sample-averaged approximate deterministic optimization model. Under multiple constraints, a mixed-integer linear programming model is constructed with the goal of minimizing the comprehensive cost of coal procurement, transportation, and risk management.

4. The method according to claim 1, characterized in that, Before the step of iteratively solving the mixed-integer linear programming model based on multiple decision variables and determining the optimal procurement and transportation plan based on the optimal solution, the method further includes: Using the coal procurement volume from medium- and long-term contracts and the procurement volume from spot suppliers in the aforementioned coal procurement data, a total procurement volume constraint condition is constructed. Using the maximum supply capacity of a single supplier and the purchase volume of spot suppliers from the coal procurement data, constraints for spot suppliers are constructed. Using the transportation volume and maximum transportation capacity corresponding to the path between two nodes in the transportation data, construct the path transportation constraints between nodes; The flow balance constraints are constructed by using the first flow between the total outflow of coal procurement data and the procurement volume of the supplier, the second flow between the total inflow of coal procurement data and the total outflow of coal procurement data, the third flow between the total inflow of coal procurement data and the total outflow of coal procurement data, and the third flow between the total inflow of coal procurement data received by the power plant and the demand allocated to the power plant. Based on the coal supply, upper and lower limits of safety stock of the power plant, inventory constraints are constructed.

5. The method according to claim 1, characterized in that, The iterative solution of the mixed-integer linear programming model based on multiple decision variables, and the determination of the optimal procurement and transportation plan based on the optimal solution, includes: Based on multiple decision variables, the mixed integer linear programming model is iteratively solved under all the coal market price fluctuation scenarios to obtain the initial procurement and transportation schemes corresponding to each coal market price fluctuation scenario, as well as the comprehensive costs of coal procurement, transportation and risk corresponding to the initial procurement and transportation schemes. Calculate the expected comprehensive cost of the initial procurement and transportation scheme under all the coal market price fluctuation scenarios, and determine whether the difference between the current expected comprehensive cost and the expected comprehensive cost of the previous iteration is less than the preset convergence accuracy threshold. If not, a new set of coal market price fluctuation scenarios will be generated, and the process will jump to the step of iteratively solving the mixed integer linear programming model based on multiple decision variables under all the coal market price fluctuation scenarios to obtain the initial procurement and transportation plan corresponding to each coal market price fluctuation scenario, as well as the comprehensive cost of coal procurement, transportation and risk corresponding to the initial procurement and transportation plan. If so, then accumulate the initial procurement and transportation plans corresponding to each coal market price fluctuation in all convergence rounds, sort the expected comprehensive costs of all the initial procurement and transportation plans, and determine the minimum expected comprehensive cost based on the sorting results; The initial procurement and transportation plan corresponding to the minimum expected overall cost is determined as the optimal procurement and transportation plan.

6. The method according to claim 1, characterized in that, The method further includes: The optimal procurement and transportation plan will be uploaded to the integrated management platform.

7. A coal procurement and transportation collaborative optimization device, characterized in that, The device includes: The simulation module is used to generate multiple coal market price fluctuation scenarios by combining coal procurement data and transportation data with Monte Carlo simulation. The module is used to transform the stochastic procurement-transportation optimization problem into a deterministic optimization model using a pre-defined sample-average approximate deterministic optimization model, and to construct a mixed-integer linear programming model under multiple constraints with the objective condition of minimizing the comprehensive cost of coal procurement, transportation and risk management. The solution module is used to iteratively solve the mixed integer linear programming model based on multiple decision variables, and determine the optimal procurement and transportation plan based on the optimal solution.

8. An electronic device, characterized in that, include: A memory and a processor are interconnected, the memory storing computer instructions, and the processor executing the computer instructions to perform the coal procurement and transportation collaborative optimization method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the coal procurement and transportation collaborative optimization method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, It includes computer instructions for causing a computer to execute the coal procurement and transportation collaborative optimization method as described in any one of claims 1 to 6.

Images