A fuel optimization scheduling method based on coal supply chain forecasting

Abstract

This invention provides a fuel optimization scheduling method based on coal supply chain forecasting, belonging to the field of supply chain management technology. The method includes collecting relevant historical data on the coal supply chain based on the fuel optimization objective, performing supply and demand analysis on this historical data to obtain supply and demand datasets, and then deriving supply and demand characteristics. These characteristics are then fused to form a comprehensive feature set, and a forecasting model of the coal supply chain's supply and demand relationship is constructed based on this comprehensive feature set. According to the forecast results, a scheduling model is constructed, a fuel scheduling plan is output, fuel scheduling is performed, and the actual scheduling results are obtained. The actual scheduling results are compared with the forecast results to obtain a supply and demand comparison result, and the forecasting model is optimized based on this comparison result. This method effectively solves problems such as information lag, inaccurate forecasting, and inflexible scheduling, enhancing the adaptability and efficiency of the supply chain.

Description

Technical Field

[0001] This invention relates to the field of supply chain management technology, and in particular to a fuel optimization scheduling method based on coal supply chain forecasting. Background Technology

[0002] In the coal supply chain, fluctuations in energy demand and the complexity of the supply chain make accurate supply and demand forecasting and scheduling crucial. Traditional supply chain management techniques often suffer from information lag, insufficient forecast accuracy, and inflexible scheduling. Similarly, rigid scheduling strategies are unable to cope with sudden changes in demand or supply, limiting the flexibility and responsiveness of the supply chain.

[0003] Therefore, this invention provides a fuel optimization scheduling method based on coal supply chain forecasting. Summary of the Invention

[0004] This invention provides a fuel optimization scheduling method based on coal supply chain forecasting. By collecting and analyzing historical data of the coal supply chain, extracting supply and demand characteristics, and integrating them to construct a forecasting model, the accuracy and flexibility of supply and demand forecasting are improved. The model is optimized through feedback from actual results, enabling more dynamic scheduling decisions, improving the supply chain response speed, effectively solving problems such as information lag, inaccurate forecasting, and inflexible scheduling, and enhancing the adaptability and efficiency of the supply chain.

[0005] This invention provides a fuel optimization scheduling method based on coal supply chain forecasting, comprising:

[0006] Step 1: Based on the goal of fuel optimization, collect relevant historical data on the coal supply chain, and conduct supply and demand analysis on the relevant historical data of the coal supply chain to obtain supply datasets and demand datasets;

[0007] Step 2: Extract supply features from the supply dataset and demand features from the demand dataset. Merge the supply and demand features to form a comprehensive feature set. Construct a predictive model of the supply and demand relationship in the coal supply chain based on the comprehensive feature set.

[0008] Step 3: Based on the prediction results output by the prediction model, construct a scheduling model, output a fuel scheduling scheme, perform fuel scheduling, and obtain the actual scheduling results;

[0009] Step 4: Compare the actual scheduling results with the predicted results to obtain the supply and demand comparison results, and optimize the prediction model based on the supply and demand comparison results.

[0010] This invention provides a fuel optimization scheduling method based on coal supply chain forecasting. It collects relevant historical data about the coal supply chain based on the fuel optimization objectives, and performs supply and demand analysis on this historical data to derive supply and demand datasets, including:

[0011] The goal of fuel optimization is to be obtained, relevant historical data is collected based on the goal of fuel optimization, and the relevant historical data of the coal supply chain is classified to obtain external historical data and internal historical data.

[0012] Supply analysis is performed on external historical data to obtain a first supply set, and supply analysis is performed on internal historical data to obtain a second supply set. The first supply set and the second supply set are combined to obtain a supply dataset.

[0013] Analyze the external historical data to obtain the first set of requirements, analyze the internal historical dataset to obtain the second set of requirements, and combine the first set of requirements with the second set of requirements to obtain the requirement dataset.

[0014] This invention provides a fuel optimization scheduling method based on coal supply chain forecasting. It extracts supply features from the supply dataset and demand features from the demand dataset, fuses the supply and demand features to form a comprehensive feature set, and constructs a forecasting model of the supply and demand relationship in the coal supply chain based on this comprehensive feature set.

[0015] Data structure analysis is performed on the supply dataset to determine the first key field of the supply dataset. The first key field is extracted as the first supply feature. Based on the first supply feature, feature derivation is performed to obtain the second supply feature. The first supply feature and the second supply feature are combined to determine the supply feature set.

[0016] Data structure analysis is performed on the demand dataset to determine the second key field of the demand dataset. The second key field is extracted as the first demand feature. Based on the first demand feature, feature derivation is performed to obtain the second demand feature. The first demand feature and the second demand feature are combined to determine the demand feature set.

[0017] Logical analysis is performed on the target objectives of fuel optimization to derive the target logic. Based on the target logic, the demand characteristics and supply characteristics are combined to form a comprehensive feature set. Based on the comprehensive feature set, a predictive model for the supply and demand relationship of the coal supply chain is constructed.

[0018] This invention provides a fuel optimization scheduling method based on coal supply chain forecasting. Based on the forecast results output by the forecasting model, a scheduling model is constructed to output a fuel scheduling scheme for fuel scheduling, including:

[0019] The prediction results of fuel demand are extracted from the prediction model. At the same time, based on the fuel optimization target, relevant factors affecting the scheduling process are identified, and the constraints in the scheduling process are determined based on the relevant factors. Based on the prediction results and constraints, an optimization algorithm is selected to construct the scheduling model.

[0020] The fuel scheduling scheme is output based on the scheduling model, and the fuel scheduling scheme is executed to obtain the actual scheduling result.

[0021] This invention provides a fuel optimization scheduling method based on coal supply chain forecasting. The method selects an optimization algorithm based on the forecast results and constraints, and constructs a scheduling model, including:

[0022] Based on the objective to be achieved through fuel optimization, an objective function is determined. Initial solutions are randomly generated according to the constraints and prediction results. The objective function value of each initial solution is calculated, and a dynamic threshold is set to determine the excellence of the objective function value of each initial solution, thereby obtaining an excellent solution.

[0023] Extract the excellent features of the excellent solution, set the perturbation range, and perform a local search on the excellent solution based on the perturbation range to generate multiple candidate solutions. Calculate the objective function value of the candidate solutions, and determine the objective function value of the candidate solutions according to a dynamic threshold to obtain the final solution.

[0024] A scheduling model is constructed based on the final solution.

[0025] This invention provides a fuel optimization scheduling method based on coal supply chain forecasting, and sets a dynamic threshold to determine the excellence of the objective function value, including:

[0026] ,in, Indicates time t The dynamic threshold; Indicates a point in history The objective function is the value function; Indicates the current time point t The objective function is the value function; Indicates the current time point t Distribution function of the objective function value; Indicates the current time point t The dynamic threshold at the previous time point; Indicates a historical point in time; t Indicates the current time point; Indicates time period Inner i1 The objective function values ​​of the initial solutions; Indicates time period Inner i2 The objective function values ​​of the initial solutions;k1 Indicates from Total number of steps taken to backtrack forward; k2 Indicates from t Total number of steps taken to backtrack forward; j1 Indicates from Looking back at the first time j1 step; j2 Indicates from t Looking back at the first time j2 step; Indicates a point in time The number of initial solutions at time step; Indicates a point in time The number of initial solutions at time step; This represents the adjustment factor for the mean change of the objective function value; The factor representing the influence of the objective function value at a historical time point on the objective function value at the current time point; This represents the rate of change factor of the objective function value; This represents the adjustment factor for changes in the distribution function; This represents the acceleration adjustment factor for the change in the distribution function;

[0027] If the objective function value of the initial solution at the same time point is higher than the dynamic threshold, then the corresponding initial solution is an excellent solution.

[0028] This invention provides a fuel optimization scheduling method based on coal supply chain forecasting. It compares actual scheduling results with forecast results to derive a supply-demand comparison result, and optimizes the forecasting model based on this comparison result. The method includes:

[0029] Error analysis is performed between the actual scheduling results and the predicted results to determine the error situation at each stage of the fuel scheduling scheme, and the supply and demand comparison results are derived based on the error situation.

[0030] The supply and demand comparison results are analyzed to identify potential patterns in supply and demand changes, and the prediction model is optimized based on these potential patterns.

[0031] This invention provides a fuel optimization scheduling method based on coal supply chain forecasting. It analyzes the supply and demand comparison results to determine potential patterns in supply and demand changes, and optimizes the forecasting model based on these potential patterns. The method includes:

[0032] Anomalies are identified in the supply and demand comparison results, anomalies are determined, and the causes of the anomalies are traced. Based on the anomalies and the traced causes, potential rules for supply and demand changes are summarized.

[0033] The potential patterns and outliers are incorporated into the prediction model, and the prediction model is then optimized.

[0034] Compared with existing technologies, the beneficial effects of this application are as follows: by collecting and analyzing historical data of the coal supply chain, extracting supply and demand characteristics, and integrating them to construct a predictive model, the accuracy and flexibility of supply and demand forecasting are improved. The model is optimized through feedback from actual results, enabling more dynamic scheduling decisions, improving the supply chain response speed, effectively solving problems such as information lag, inaccurate forecasting, and inflexible scheduling, and enhancing the adaptability and efficiency of the supply chain.

[0035] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings.

[0036] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0037] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0038] Figure 1 This is a schematic flowchart of a fuel optimization scheduling method based on coal supply chain forecasting provided in an embodiment of the present invention. Detailed Implementation

[0039] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0040] Example 1:

[0041] This invention provides a fuel optimization scheduling method based on coal supply chain forecasting, such as... Figure 1 As shown, it includes:

[0042] Step 1: Based on the goal of fuel optimization, collect relevant historical data on the coal supply chain, and conduct supply and demand analysis on the relevant historical data of the coal supply chain to obtain supply datasets and demand datasets;

[0043] Step 2: Extract supply features from the supply dataset and demand features from the demand dataset. Merge the supply and demand features to form a comprehensive feature set. Construct a predictive model of the supply and demand relationship in the coal supply chain based on the comprehensive feature set.

[0044] Step 3: Based on the prediction results output by the prediction model, construct a scheduling model, output a fuel scheduling scheme, perform fuel scheduling, and obtain the actual scheduling results;

[0045] Step 4: Compare the actual scheduling results with the predicted results to obtain the supply and demand comparison results, and optimize the prediction model based on the supply and demand comparison results.

[0046] In this embodiment, the objective to be achieved refers to the specific goals that are desired to be achieved in the process of optimizing the coal supply chain, such as cost minimization: reducing the total cost of coal procurement, transportation and storage; and efficiency maximization: improving the efficiency of coal transportation and distribution, and reducing idle and waiting time.

[0047] In this embodiment, relevant historical data refers to historical information that needs to be analyzed during the optimization process, such as transportation cost data: cost records of different transportation methods in the past year; and inventory level data: monthly coal inventory and its changes.

[0048] In this embodiment, supply analysis is an evaluation of supply data to understand the capabilities and efficiency of the supply chain. For example, external supplier evaluation: analyzing the delivery time and quality of different external suppliers; transportation efficiency analysis: evaluating the cost and time of different transportation routes.

[0049] In this embodiment, demand analysis is the evaluation of demand data, with the aim of understanding the patterns and changes in customer demand. For example, demand trend analysis: analyzing seasonal demand changes over the past few years; customer preference analysis: identifying the demand characteristics and changes of key customers.

[0050] In this embodiment, the supply dataset is a comprehensive dataset that combines the first supply dataset and the second supply dataset. For example, comprehensive supply information is the integrated data of external supplier quotations and internal coal mine production capacity.

[0051] In this embodiment, the demand dataset is a comprehensive dataset that combines the first demand set and the second demand set. For example, comprehensive demand information is integrated data of external market demand and internal customer demand.

[0052] In this embodiment, the data fusion process involves analyzing the supply dataset to determine the first key field (such as supply quantity and supply time) and extracting it as the first supply feature; analyzing the demand dataset to determine the second key field (such as demand quantity and demand time) and extracting it as the first demand feature; in the feature derivation stage, relevant information (such as supply volatility) is extracted based on the first supply feature to form the second supply feature; relevant information (such as demand growth rate) is extracted based on the first demand feature to form the second demand feature; and a complete set of supply and demand features is constructed.

[0053] In this embodiment, the input to the prediction model is all features in the comprehensive feature set, such as "customer-supplier matching degree", "demand volatility", and "supply stability"; the output of the prediction model refers to the results generated by the model, such as the forecast of coal demand in the future; the training set is a feature set containing historical demand and supply data, which is used to train the model to identify patterns and relationships.

[0054] In this embodiment, the supply and demand relationship in the coal supply chain refers to the interaction and dependence between suppliers (such as coal mines and producers) and demanders (such as power plants and industrial users) during the coal production, transportation, storage, and consumption process. For example, suppliers include: production capacity (the mining capacity and production efficiency of coal mines), transportation capacity (the transportation methods and efficiency from coal mines to consumption sites), and inventory management (the storage and inventory levels of coal to ensure the continuity of supply).

[0055] In this embodiment, the forecast results include supply forecast results, demand forecast results, and supply balance forecast results. For example, the supply balance forecast results indicate that the total demand is expected to be 600 tons and the total supply is 450 tons in the coming week, resulting in a shortage of 150 tons. If the inventory is 200 tons, there is a risk of supply shortage during the peak demand period (such as Wednesday).

[0056] In this embodiment, the input to the scheduling model is the fuel demand forecast, relevant factors, constraints, current inventory levels, transportation capacity, etc., such as the current inventory (e.g., 300 tons) and the demand forecast for the next week (e.g., 100 tons per day); the output is the specific arrangement of the fuel scheduling plan, such as the daily delivery volume, transportation route, delivery time, etc., for example, 100 tons of fuel are scheduled to be delivered every day, divided into two deliveries, one in the morning and one in the afternoon.

[0057] In this embodiment, the fuel scheduling scheme is a specific scheduling plan that includes the delivery time, quantity, and method. For example, 100 tons are delivered every day from Monday to Friday, and the delivery volume is adjusted according to changes in demand on weekends.

[0058] In this embodiment, the actual scheduling result is the actual amount of fuel delivered, the time, and any deviations after the scheduling plan is executed. For example, the actual delivery is 95 tons delivered on Monday and 105 tons delivered on Tuesday. Deviations (such as delivery delays due to traffic delays) are recorded.

[0059] In this embodiment, the supply and demand comparison result is based on the difference between actual supply and demand derived from error analysis. For example, if the actual supply is 1,100 tons and the actual demand is 1,200 tons in a certain period of time, the supply and demand comparison result is a supply and demand gap of 100 tons.

[0060] In this embodiment, by identifying anomalies in the supply and demand comparison results, identifying anomalies and tracing their causes, the potential patterns of supply and demand changes are summarized, and these patterns and anomalies are incorporated into the prediction model to optimize the model parameters.

[0061] The working principle and beneficial effects of the above technical solution are as follows: by collecting and analyzing historical data of the coal supply chain, extracting supply and demand characteristics, and integrating them to build a predictive model, the accuracy and flexibility of supply and demand forecasting are improved. The model is optimized through feedback from actual results, enabling more dynamic scheduling decisions, improving the supply chain response speed, effectively solving problems such as information lag, inaccurate forecasting, and inflexible scheduling, and enhancing the adaptability and efficiency of the supply chain.

[0062] Example 2:

[0063] This invention provides a fuel optimization scheduling method based on coal supply chain forecasting. It collects relevant historical data about the coal supply chain based on the fuel optimization objective, and performs supply and demand analysis on this historical data to derive supply and demand datasets, including:

[0064] The goal of fuel optimization is to be obtained, relevant historical data is collected based on the goal of fuel optimization, and the relevant historical data of the coal supply chain is classified to obtain external historical data and internal historical data.

[0065] Supply analysis is performed on external historical data to obtain a first supply set, and supply analysis is performed on internal historical data to obtain a second supply set. The first supply set and the second supply set are combined to obtain a supply dataset.

[0066] Analyze the external historical data to obtain the first set of requirements, analyze the internal historical dataset to obtain the second set of requirements, and combine the first set of requirements with the second set of requirements to obtain the requirement dataset.

[0067] In this embodiment, external historical data refers to data collected from the market and environment, such as market price data: records of market price fluctuations in coal; competitor analysis data: prices and supply of other coal suppliers.

[0068] In this embodiment, internal historical data refers to data collected internally by the enterprise, such as sales records: the company's internal coal sales volume and customer information; inventory records: the coal inventory status recorded in the company's inventory management system; and production records: the coal mine's production efficiency and equipment maintenance records.

[0069] In this embodiment, the first supply set is a set derived from supply analysis based on external historical data, such as the supply capacity and price of external suppliers, such as a large coal mine or a local small coal mine; the second supply set is a set derived from supply analysis based on internal historical data, such as the production capacity and inventory of the company's own coal mines.

[0070] In this embodiment, the first demand set is a set derived from demand analysis based on external historical data, such as market demand data, like the coal demand in a certain region and its changing trends; the second demand set is a set derived from demand analysis based on internal historical data, such as internal customer demand, like the coal demand records of various departments within the company.

[0071] The working principle and beneficial effects of the above technical solution are as follows: By determining the target of fuel optimization, historical data of the coal supply chain is classified and collected, divided into external and internal data. Supply and demand analysis is performed on the external and internal data respectively, resulting in multiple supply and demand sets. Finally, these sets are integrated to form supply datasets and demand datasets, providing a foundation for accurate supply and demand forecasting, improving the accuracy and reliability of supply and demand forecasting, enhancing scheduling flexibility, and reducing information lag.

[0072] Example 3:

[0073] This invention provides a fuel optimization scheduling method based on coal supply chain forecasting. The method extracts supply features from the supply dataset and demand features from the demand dataset, fuses the supply and demand features to form a comprehensive feature set, and constructs a forecasting model of the supply and demand relationship in the coal supply chain based on this comprehensive feature set.

[0074] Data structure analysis is performed on the supply dataset to determine the first key field of the supply dataset. The first key field is extracted as the first supply feature. Based on the first supply feature, feature derivation is performed to obtain the second supply feature. The first supply feature and the second supply feature are combined to determine the supply feature set.

[0075] Data structure analysis is performed on the demand dataset to determine the second key field of the demand dataset. The second key field is extracted as the first demand feature. Based on the first demand feature, feature derivation is performed to obtain the second demand feature. The first demand feature and the second demand feature are combined to determine the demand feature set.

[0076] Logical analysis is performed on the target objectives of fuel optimization to derive the target logic. Based on the target logic, the demand characteristics and supply characteristics are combined to form a comprehensive feature set. Based on the comprehensive feature set, a predictive model for the supply and demand relationship of the coal supply chain is constructed.

[0077] In this embodiment, data structure analysis is the understanding and evaluation of the composition, format, and various fields of the dataset. The purpose is to identify the relationships between key fields and data. For example, analyzing the supply dataset can help identify fields such as "supplier ID", "supply quantity", "price", and "delivery time".

[0078] In this embodiment, the first key field refers to the field that can uniquely identify a record in the supply dataset, such as supplier ID: a unique identifier for each supplier; the first supply feature is a feature extracted from the first key field for subsequent analysis, such as supplier type: such as "local supplier" or "external supplier"; the second supply feature is a new feature derived from the first supply feature, such as supply stability: a measure of the degree of fluctuation in supply.

[0079] In this embodiment, the feature derivation process refers to the process of generating new features based on existing features. For example, the "supply stability" feature is derived from the "supply quantity" field, and the standard deviation of supply quantity over the past few months is calculated.

[0080] In this embodiment, the second key field refers to a field that can uniquely identify a record in the demand dataset, such as customer ID: a unique identifier for each customer; the first demand feature is a feature extracted from the second key field, such as customer type: such as "industrial customer" or "retail customer"; the second demand feature is a new feature derived from the first demand feature, such as demand volatility: a measure of the degree of change in customer demand; the demand feature set is a feature set that combines the first demand feature and the second demand feature, such as a feature set that includes "customer type" and "demand volatility".

[0081] In this embodiment, target logic refers to the analysis of logical relationships and priorities among the goals to be achieved in fuel optimization, such as the trade-off between cost minimization and service level improvement.

[0082] In this embodiment, the logical analysis process involves systematically analyzing the goals to be achieved in order to determine the relationships and impacts between the goals. For example, it involves analyzing how to reduce costs by optimizing supply chain management without affecting delivery time.

[0083] In this embodiment, the combination process involves combining demand characteristics with supply characteristics to form a comprehensive feature set. For example, combining "customer type" and "supplier type" to form the "customer-supplier matching degree" feature.

[0084] The working principle and beneficial effects of the above technical solution are as follows: By performing structural analysis on the supply and demand dataset of the coal supply chain, key fields are identified and features are derived to form a comprehensive feature set. Based on the target logic and combined with the characteristics of demand and supply, a prediction model is constructed to achieve accurate supply and demand forecasting and flexible scheduling, thereby improving supply chain efficiency.

[0085] Example 4:

[0086] This invention provides a fuel optimization scheduling method based on coal supply chain forecasting. Based on the forecast results output by the forecasting model, a scheduling model is constructed to output a fuel scheduling scheme, and fuel scheduling is performed. The method includes:

[0087] The prediction results of fuel demand are extracted from the prediction model. At the same time, based on the fuel optimization target, relevant factors affecting the scheduling process are identified, and the constraints in the scheduling process are determined based on the relevant factors. Based on the prediction results and constraints, an optimization algorithm is selected to construct the scheduling model.

[0088] The fuel scheduling scheme is output based on the scheduling model, and the fuel scheduling scheme is executed to obtain the actual scheduling result.

[0089] In this embodiment, the relevant factors include external and internal factors that affect scheduling, such as changes in market demand, supply capacity, transportation capacity, inventory levels, and weather factors. For example, seasonal changes in market demand (such as increased demand for heating in winter) and transportation capacity (such as the number of transportation vehicles that can be scheduled each day).

[0090] In this embodiment, the constraints are limitations that must be followed during the scheduling process, such as maximum inventory capacity, minimum delivery quantity, transportation time limits, supplier delivery capabilities, etc. For example, maximum inventory capacity (e.g., a warehouse can store a maximum of 500 tons of fuel).

[0091] The working principle and beneficial effects of the above technical solution are as follows: extract fuel demand forecast results from the forecast model, identify relevant factors affecting scheduling and determine constraints, select optimization algorithms based on these constraints to construct a scheduling model, output fuel scheduling schemes and execute them, and finally obtain actual scheduling results to achieve efficient fuel scheduling and resource allocation. Based on real-time data and forecast results, the scientificity and accuracy of scheduling decisions are enhanced.

[0092] Example 5:

[0093] This invention provides a fuel optimization scheduling method based on coal supply chain forecasting, which selects an optimization algorithm based on the forecast results and constraints, and constructs a scheduling model, including:

[0094] Based on the objective to be achieved through fuel optimization, an objective function is determined. Initial solutions are randomly generated according to the constraints and prediction results. The objective function value of each initial solution is calculated, and a dynamic threshold is set to determine the excellence of the objective function value of each initial solution, thereby obtaining an excellent solution.

[0095] Extract the excellent features of the excellent solution, set the perturbation range, and perform a local search on the excellent solution based on the perturbation range to generate multiple candidate solutions. Calculate the objective function value of the candidate solutions, and determine the objective function value of the candidate solutions according to a dynamic threshold to obtain the final solution.

[0096] A scheduling model is constructed based on the final solution.

[0097] In this embodiment, the objective function is a performance indicator of the quantification scheduling scheme, which typically includes cost, efficiency, supply and demand balance, such as minimizing total transportation cost and maximizing supply chain response speed.

[0098] In this embodiment, the initial solution is a scheduling scheme randomly generated during the optimization process, which is used for subsequent evaluation and improvement, such as a scheme that randomly allocates fuel supply to different demand points.

[0099] In this embodiment, the process of determining excellence involves comparing the objective function value of the initial solution with a dynamic threshold. If the objective function value is lower than the threshold, the solution is determined to be excellent.

[0100] In this embodiment, the process of setting the disturbance range is to analyze the characteristics of the excellent solution (such as supply and demand) and determine the appropriate upper and lower fluctuation ranges to maintain the feasibility of the solution. The disturbance range is a variable range set on the basis of the excellent solution to generate new candidate solutions, such as fluctuating by 10% above and below a specific fuel allocation.

[0101] In this embodiment, local search is a process of meticulously exploring the vicinity of a good solution to find a better one. Within the perturbation range, the good solution is slightly adjusted, the objective function value of the adjusted new solution is calculated, and its quality is judged.

[0102] In this embodiment, candidate solutions are multiple new scheduling schemes generated through local search, which are to be further evaluated. For example, different fuel allocation schemes are formed by adjusting the excellent solutions. The final solution is determined by evaluating and screening the optimal scheduling scheme. The solution with the best performance is selected by calculating the objective function value of all candidate solutions and judging according to the dynamic threshold.

[0103] In this embodiment, the dynamic threshold is a judgment standard that is dynamically adjusted based on the current market conditions, historical data, and forecast results. For example, the threshold may be more stringent during peak demand periods, and relaxed when supply is sufficient.

[0104] The working principle and beneficial effects of the above technical solution are as follows: By setting an objective function and constraints, an initial solution is randomly generated and its objective function value is calculated. Excellent solutions are selected using a dynamic threshold. Based on the characteristics of these excellent solutions, a local search is performed to generate candidate solutions and evaluate their performance, thereby obtaining the final solution. This ultimately constructs an efficient scheduling model, improving the accuracy and flexibility of fuel scheduling.

[0105] Example 6:

[0106] This invention provides a fuel optimization scheduling method based on coal supply chain forecasting, and sets a dynamic threshold to determine the excellence of the objective function value, including:

[0107] ,in, Indicates time t The dynamic threshold; Indicates a point in history The objective function is the value function; Indicates the current time point t The objective function is the value function; Indicates the current time point t Distribution function of the objective function value; Indicates the current time point t The dynamic threshold at the previous time point; Indicates a historical point in time; t Indicates the current time point; Indicates time period Inner i1 The objective function values ​​of the initial solutions; Indicates time period Inner i2 The objective function values ​​of the initial solutions; k1 Indicates from Total number of steps taken to backtrack forward; k2 Indicates from t Total number of steps taken to backtrack forward; j1 Indicates from Looking back at the first time j1 step; j2 Indicates from t Looking back at the first time j2 step; Indicates a point in time The number of initial solutions at time step; Indicates a point in time The number of initial solutions at time step; This represents the adjustment factor for the mean change of the objective function value; The factor representing the influence of the objective function value at a historical time point on the objective function value at the current time point; This represents the rate of change factor of the objective function value; This represents the adjustment factor for changes in the distribution function; This represents the acceleration adjustment factor for the change in the distribution function;

[0108] If the objective function value of the initial solution at the same time point is higher than the dynamic threshold, then the corresponding initial solution is an excellent solution.

[0109] The working principle and beneficial effects of the above technical solution are as follows: the excellence of the initial solution is determined by setting a dynamic threshold. The threshold is dynamically adjusted by combining historical objective function values ​​and current objective function values ​​to reflect changes in energy demand and supply. When the objective function value of the initial solution at the same time point is higher than the dynamic threshold, the solution is determined to be an excellent solution, thereby optimizing the scheduling strategy and improving the flexibility and responsiveness of the supply chain.

[0110] Example 7:

[0111] This invention provides a fuel optimization scheduling method based on coal supply chain forecasting. The method compares actual scheduling results with forecast results to obtain a supply-demand comparison result, and optimizes the forecasting model based on this comparison result. The method includes:

[0112] Error analysis is performed between the actual scheduling results and the predicted results to determine the error situation at each stage of the fuel scheduling scheme, and the supply and demand comparison results are derived based on the error situation.

[0113] The supply and demand comparison results are analyzed to identify potential patterns in supply and demand changes, and the prediction model is optimized based on these potential patterns.

[0114] In this embodiment, error analysis is a process of systematically evaluating the difference between the actual scheduling result and the predicted result. For example, if the predicted coal demand for a certain period is 1,000 tons, while the actual demand is 1,200 tons, then the error is 200 tons.

[0115] In this embodiment, the error refers to the degree of deviation between actual demand and predicted demand at different stages (such as day, week, month). For example, in a month, the actual demand in a certain week is 1,500 tons, while the predicted demand is 1,300 tons, with an error of +200 tons; while in another week, the actual demand is 900 tons, while the predicted demand is 1,000 tons, with an error of -100 tons.

[0116] In this embodiment, pattern analysis involves in-depth study of the supply and demand comparison results to identify trends and patterns in supply and demand changes. For example, the analysis may find that demand typically increases in winter while supply decreases during the summer peak season, and this seasonal variation can be considered a pattern.

[0117] In this embodiment, the potential patterns of supply and demand changes refer to the factors and trends that influence supply and demand fluctuations discovered through long-term observation. For example, historical data shows that economic growth rate is positively correlated with coal demand, and weather changes also affect demand; for instance, cold weather leads to increased demand.

[0118] In this embodiment, the parameters or algorithms of the prediction model are adjusted based on the potential patterns of supply and demand changes to more accurately reflect future supply and demand conditions. For example, if it is found that cold weather will increase coal demand, weather factors can be added as variables to the prediction model and trained using machine learning algorithms to improve the accuracy of the prediction.

[0119] The working principle and beneficial effects of the above technical solution are as follows: by performing error analysis on the actual scheduling results and the forecast results, the supply and demand differences at each stage are identified. Based on these errors, the potential patterns of supply and demand changes are further analyzed, and the forecast model is optimized accordingly, thereby improving the accuracy and flexibility of future scheduling and adapting to the ever-changing market demands in the coal supply chain.

[0120] Example 8:

[0121] This invention provides a fuel optimization scheduling method based on coal supply chain forecasting. The method involves analyzing the supply and demand comparison results to determine potential patterns in supply and demand changes, and optimizing the forecasting model based on these potential patterns. The method includes:

[0122] Anomalies are identified in the supply and demand comparison results, anomalies are determined, and the causes of the anomalies are traced. Based on the anomalies and the traced causes, potential rules for supply and demand changes are summarized.

[0123] The potential patterns and outliers are incorporated into the prediction model, and the prediction model is then optimized.

[0124] In this embodiment, outliers refer to situations in the supply and demand comparison results that deviate significantly from the normal range or expected value. These points usually manifest as significant differences between actual demand or supply and the predicted value. For example, if the actual coal demand in a certain week is 2,000 tons, while the forecast is only 1,200 tons, then the demand data for that week can be regarded as an outlier because its deviation exceeds the normal fluctuation range.

[0125] In this embodiment, cause tracing involves conducting in-depth analysis of identified anomalies to determine the specific factors or causes leading to the anomalies. This typically involves investigating relevant data and background information. For example, after identifying an anomaly in demand during a particular week, factors such as weather data, economic activities, and policy changes may be analyzed to discover that the abnormal demand was due to extreme cold weather during that week, leading to a surge in coal demand. Through this analysis, the specific cause can be traced, thus providing a reference for subsequent forecasting and scheduling.

[0126] The working principle and beneficial effects of the above technical solution are as follows: by identifying anomalies in the supply and demand comparison results, determining the anomalies and tracing their causes, summarizing the potential patterns of supply and demand changes, incorporating these patterns and anomalies into the prediction model, and optimizing the model parameters, the accuracy and responsiveness of future supply and demand forecasts can be improved, thereby enhancing the flexibility of the coal supply chain, incorporating potential patterns into the model, and improving the accuracy and reliability of forecasts.

[0127] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A fuel optimization scheduling method based on coal supply chain forecasting, characterized in that, include: Step 1: Based on the goal of fuel optimization, collect relevant historical data on the coal supply chain, and conduct supply and demand analysis on the relevant historical data of the coal supply chain to obtain supply datasets and demand datasets; Step 2: Extract supply features from the supply dataset and demand features from the demand dataset. Merge the supply and demand features to form a comprehensive feature set. Construct a predictive model of the supply and demand relationship in the coal supply chain based on the comprehensive feature set. Step 3: Based on the prediction results output by the prediction model, construct a scheduling model, output a fuel scheduling scheme, perform fuel scheduling, and obtain the actual scheduling results; Step 4: Compare the actual scheduling results with the predicted results to obtain the supply and demand comparison results, and optimize the prediction model based on the supply and demand comparison results; Based on the prediction results output by the prediction model, a scheduling model is constructed to output a fuel scheduling scheme, and fuel scheduling is performed, including: The prediction results of fuel demand are extracted from the prediction model. At the same time, based on the fuel optimization target, relevant factors affecting the scheduling process are identified, and the constraints in the scheduling process are determined based on the relevant factors. Based on the prediction results and constraints, an optimization algorithm is selected to construct the scheduling model. The fuel scheduling scheme is output based on the scheduling model, and the fuel scheduling scheme is executed to obtain the actual scheduling result; Based on the prediction results and constraints, an optimization algorithm is selected, and a scheduling model is constructed, including: Based on the objective to be achieved through fuel optimization, an objective function is determined. Initial solutions are randomly generated according to the constraints and prediction results. The objective function value of each initial solution is calculated, and a dynamic threshold is set to determine the excellence of the objective function value of each initial solution, thereby obtaining an excellent solution. Extract the excellent features of the excellent solution, set the perturbation range, and perform a local search on the excellent solution based on the perturbation range to generate multiple candidate solutions. Calculate the objective function value of the candidate solutions, and determine the objective function value of the candidate solutions according to a dynamic threshold to obtain the final solution. A scheduling model is constructed based on the final solution.

2. The fuel optimization scheduling method based on coal supply chain forecasting according to claim 1, characterized in that, Based on the goal of fuel optimization, relevant historical data on the coal supply chain were collected, and supply and demand analyses were performed on this historical data to derive supply and demand datasets, including: The goal of fuel optimization is to be obtained, and relevant historical data of the coal supply chain is collected based on the goal of fuel optimization. The relevant historical data of the coal supply chain is classified to obtain external historical data and internal historical data. Supply analysis is performed on external historical data to obtain a first supply set, and supply analysis is performed on internal historical data to obtain a second supply set. The first supply set and the second supply set are combined to obtain a supply dataset. Analyze the external historical data to obtain the first set of requirements, analyze the internal historical dataset to obtain the second set of requirements, and combine the first set of requirements with the second set of requirements to obtain the requirement dataset.

3. The fuel optimization scheduling method based on coal supply chain forecasting according to claim 1, characterized in that, Supply features are extracted from the supply dataset, and demand features are extracted from the demand dataset. The supply and demand features are then fused to form a comprehensive feature set. Based on this comprehensive feature set, a predictive model for the supply and demand relationship in the coal supply chain is constructed, including: Data structure analysis is performed on the supply dataset to determine the first key field of the supply dataset. The first key field is extracted as the first supply feature. Based on the first supply feature, feature derivation is performed to obtain the second supply feature. The first supply feature and the second supply feature are combined to determine the supply feature set. Data structure analysis is performed on the demand dataset to determine the second key field of the demand dataset. The second key field is extracted as the first demand feature. Based on the first demand feature, feature derivation is performed to obtain the second demand feature. The first demand feature and the second demand feature are combined to determine the demand feature set. Logical analysis is performed on the target objectives of fuel optimization to derive the target logic. Based on the target logic, the demand characteristics and supply characteristics are combined to form a comprehensive feature set. Based on the comprehensive feature set, a predictive model for the supply and demand relationship of the coal supply chain is constructed.

4. The fuel optimization scheduling method based on coal supply chain forecasting according to claim 1, characterized in that, A dynamic threshold is set to determine the excellence of the objective function value, including: ,in, This represents the dynamic threshold at time t; Indicates a point in history The objective function is the value function; This represents the objective function value at the current time point t. This represents the distribution function of the objective function value at the current time point t; This represents the dynamic threshold at the current time point t. t represents a historical point in time; t represents the current point in time. Indicates time period The objective function value of the i1th initial solution; Indicates time period The objective function value of the i2th initial solution; k1 represents the value of the objective function from the i2th initial solution; The total number of steps for backtracking forward; k2 represents the total number of steps for backtracking forward from t; j1 represents the total number of steps for backtracking backward from t. j1 represents the j1st step of backtracking from t; j2 represents the j2nd step of backtracking from t. Indicates a point in time The number of initial solutions at time step; Indicates a point in time The number of initial solutions at time step; This represents the adjustment factor for the mean change of the objective function value; The factor representing the influence of the objective function value at a historical time point on the objective function value at the current time point; This represents the rate of change factor of the objective function value; This represents the adjustment factor for changes in the distribution function; This represents the acceleration adjustment factor for the change in the distribution function; If the objective function value of the initial solution at the same time point is higher than the dynamic threshold, then the corresponding initial solution is an excellent solution.

5. The fuel optimization scheduling method based on coal supply chain forecasting according to claim 1, characterized in that, The actual scheduling results are compared with the predicted results to obtain a supply and demand comparison result. Based on the supply and demand comparison result, the prediction model is optimized, including: Error analysis is performed between the actual scheduling results and the predicted results to determine the error situation at each stage of the fuel scheduling scheme, and the supply and demand comparison results are derived based on the error situation. The supply and demand comparison results are analyzed to identify potential patterns in supply and demand changes, and the prediction model is optimized based on these potential patterns.

6. The fuel optimization scheduling method based on coal supply chain forecasting according to claim 1, characterized in that, The supply and demand comparison results are analyzed for patterns to determine potential patterns of supply and demand changes. Based on these potential patterns, the prediction model is optimized, including: Anomalies are identified in the supply and demand comparison results, anomalies are determined, and the causes of the anomalies are traced. Based on the anomalies and the traced causes, potential rules for supply and demand changes are summarized. The potential patterns and outliers are incorporated into the prediction model, and the prediction model is then optimized.

Images