Fuel resource scheduling optimization method and system

Abstract

The invention discloses a fuel resource scheduling optimization method and system. The method comprises the following steps: acquiring and preprocessing supply data of fuel resources; constructing a supply quantity prediction model based on the supply quantity data, and obtaining supply quantity prediction data according to prediction of the supply quantity prediction model; acquiring the demand quantity of the fuel resources, and determining the supply quantity prediction data and the deviation characteristics thereof; evaluating the supply condition of the fuel resources based on the deviation characteristics to obtain a supply evaluation value; and determining a scheduling optimization coefficient of the fuel resources according to the supply evaluation value, and performing scheduling optimization on the supply amount according to the scheduling optimization coefficient. According to the method, the supply data can be predicted in real time according to analysis and modeling of the supply data of the fuel resources, and the scheduling optimization coefficient of the fuel resources is determined by evaluating the supply prediction data and the deviation characteristics between the supply prediction data, so that the fuel resources are optimized and adjusted, the energy utilization efficiency is improved, and the energy consumption is reduced. The supply and demand contradiction is relieved to a certain extent, and the sustainable development of the energy industry is promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of fuel resource scheduling, and in particular to a fuel resource scheduling optimization method and system. Background Art

[0002] Fuel resource scheduling optimization refers to the fuel resources used in energy production and use. It is widely used in the power industry, petrochemical industry, transportation and other fields. It is a method of rationally arranging and optimizing the supply and distribution of fuel resources with the goal of maximizing benefits and resource utilization efficiency through data analysis, predictive modeling and real-time adjustment. It is of great significance to ensure energy security, reduce energy consumption, and reduce environmental pollution. With the continuous growth of energy demand and the continuous adjustment of energy structure, fuel resource scheduling optimization has become an important topic in the field of energy management, providing strong support for sustainable energy development and intelligent energy management.

[0003] However, traditional fuel resource scheduling methods often rely on experience and rules to make scheduling decisions for fuel resources. This approach may not be able to fully utilize big data and advanced predictive models, resulting in difficulty in optimizing decision-making results. At the same time, traditional methods usually handle fuel resource scheduling in a static manner and are unable to respond to real-time factors such as market changes and supply and demand fluctuations in a timely manner, resulting in insufficient flexibility and adaptability in scheduling plans. Moreover, scheduling decisions made by traditional methods often lack intelligence and adaptability, and cannot be dynamically adjusted based on real-time data and model feedback, making it difficult to cope with the complex and changing energy market environment. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a fuel resource scheduling optimization method and system, including: Obtaining fuel resource supply data and preprocessing the fuel resource supply data; Building a fuel resource supply prediction model based on the supply data, and predicting the supply of the fuel resource according to the fuel resource supply prediction model to obtain fuel resource supply prediction data; Obtaining the demand for fuel resources and determining the deviation characteristics between the supply forecast data and the demand; The supply situation of the fuel resources is evaluated and calculated based on the deviation characteristics to obtain the supply evaluation value of the fuel resources; The scheduling optimization coefficient of the fuel resource is determined according to the supply evaluation value, and the supply quantity of the fuel resource is scheduled and optimized according to the scheduling optimization coefficient.

[0005] Furthermore, the preprocessing of the supply quantity data includes: The supply data is preprocessed, which includes removing abnormal data and overloaded data in the supply data, filling in missing data, and standardizing the supply data.

[0006] Further, the fuel resource supply prediction model is constructed based on the supply data, and the supply of the fuel resource is predicted according to the fuel resource supply prediction model to obtain the fuel resource supply prediction data, including: Constructing a data set based on the supply data, and inputting the data set into a preset neural network model to construct an initial model for predicting the supply of fuel resources; Divide the data set into a training set and a test set according to a certain ratio, and input the training set and the test set into the initial supply forecast model; Training and testing the initial supply forecast model until the initial supply forecast model meets a preset convergence condition, thereby obtaining a fuel resource supply forecast model; The supply forecast data of fuel resources in the future is predicted based on the obtained supply forecast model.

[0007] Furthermore, the obtaining of the demand for fuel resources and determining the deviation characteristics between the supply forecast data and the demand include: Obtain the coal supply demand, and perform a difference calculation between each data in the predicted coal supply data and the coal supply demand to obtain deviation data; The deviation data is plotted into a deviation data curve, and the deviation data curve is analyzed to determine the deviation characteristics between the supply forecast data and the demand.

[0008] Furthermore, the analysis of the deviation data curve to determine the deviation characteristics between the supply forecast data and the demand includes: Obtain peak values ​​and trough values ​​in the deviation data curve, and determine the curve segments from each peak value to the trough value and from each trough value to the peak value; The deviation data average value and the curve segment slope corresponding to each curve segment are calculated, and these deviation data average values ​​and the curve segment slopes are determined as deviation characteristics between the supply quantity forecast data and the demand quantity.

[0009] Furthermore, the supply situation of the fuel resource is evaluated and calculated based on the deviation characteristics to obtain the supply evaluation value of the fuel resource, including: Preset the standard average value of the curve segment, and obtain the average value of the deviation data and the slope of the curve segment corresponding to each curve segment; The average value of the deviation data corresponding to each curve segment is calculated by subtracting the standard average value to obtain the difference value corresponding to each curve segment, and each curve segment is evaluated and valued according to the size of each difference value to obtain the evaluation value of each curve segment; Calculate the average value of the curve segment slopes corresponding to all the curve segments, and calculate the ratio of the curve segment slope corresponding to each curve segment to the average value, and determine the ratio as the weight corresponding to each curve segment; The evaluation value of each curve segment and the weight of each curve segment are weighted and added together to obtain the supply assessment value of the fuel resource.

[0010] Further, determining the scheduling optimization coefficient of the fuel resource according to the supply evaluation value, and performing scheduling optimization on the supply of the fuel resource according to the scheduling optimization coefficient, includes: A scheduling optimization coefficient-supply evaluation value interval correspondence relationship is preset, and the scheduling optimization coefficient-supply evaluation value interval correspondence relationship is associated with a corresponding scheduling optimization coefficient for each supply evaluation value interval; Obtaining a supply evaluation value, and based on a mapping relationship between a supply evaluation value interval to which the supply evaluation value belongs and a corresponding relationship between a scheduling optimization coefficient and a supply evaluation value interval, selecting a scheduling optimization coefficient corresponding to the supply evaluation value interval; The supply of fuel resources is optimized according to the scheduling optimization coefficient.

[0011] The present invention also provides a fuel resource scheduling optimization system, comprising: An acquisition module, used for acquiring the supply quantity data of the fuel resource and preprocessing the supply quantity data of the fuel resource; A prediction module, used to construct a fuel resource supply prediction model based on the supply data, and predict the supply of the fuel resource according to the fuel resource supply prediction model to obtain fuel resource supply prediction data; A determination module is used to obtain the demand for fuel resources and determine the deviation characteristics between the supply forecast data and the demand; An evaluation module, used to evaluate and calculate the supply of fuel resources based on the deviation characteristics to obtain a supply evaluation value of the fuel resources; The optimization module is used to determine the scheduling optimization coefficient of the fuel resource according to the supply evaluation value, and to perform scheduling optimization on the supply of the fuel resource according to the scheduling optimization coefficient.

[0012] Compared with the prior art, the fuel resource scheduling optimization method and system according to the embodiment of the present invention have the following beneficial effects: The present invention establishes a prediction model for fuel resource supply, which can help predict future fuel resource supply conditions and help enterprises or government departments make corresponding decisions and plans; The present invention can better understand the gap between supply and demand by performing feature analysis on the deviation between supply forecast data and demand data, which helps to adjust the supply plan in time; The present invention can objectively evaluate the current fuel resource supply situation by calculating the supply evaluation value, and provide an objective basis for decision-making; The present invention determines the scheduling optimization coefficient of fuel resources, and can formulate a reasonable scheduling plan according to actual conditions to maximize resource utilization efficiency; The present invention can optimize the scheduling of the supply of fuel resources to meet actual needs and maximize benefits, thereby improving resource utilization efficiency and reducing costs, and to a certain extent alleviate the contradiction between supply and demand, which helps to promote the sustainable development of the energy industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 It is a schematic diagram of the flow structure of the fuel resource scheduling optimization method in an embodiment of the present invention; Figure 2 It is a schematic diagram of the composition of the fuel resource scheduling optimization system in an embodiment of the present invention. DETAILED DESCRIPTION

[0014] The specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0015] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the platform or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0016] The terms "second" and "second" are used for descriptive purposes only and should not be understood as indicating or implying a relative degree of importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined with "second" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "multiple" means two or more.

[0017] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technical personnel in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0018] like Figure 1 As shown, in an embodiment of the present application, a fuel resource scheduling optimization method is provided, including: S100: obtaining supply quantity data of fuel resources, and preprocessing the supply quantity data of fuel resources; S200: constructing a supply quantity prediction model of fuel resources based on the supply quantity data, and predicting the supply quantity of fuel resources according to the supply quantity prediction model of fuel resources, to obtain supply quantity prediction data of fuel resources; S300: obtaining the demand for fuel resources, and determining the deviation characteristics between the supply quantity prediction data and the demand; S400: evaluating and calculating the supply situation of fuel resources based on the deviation characteristics, to obtain a supply evaluation value of fuel resources; S500: determining a scheduling optimization coefficient of fuel resources according to the supply evaluation value, and scheduling and optimizing the supply quantity of fuel resources according to the scheduling optimization coefficient.

[0019] Furthermore, the present invention, by establishing a prediction model for the supply of fuel resources, can help predict the future supply of fuel resources, and help enterprises or government departments make corresponding decisions and plans; the present invention, by performing feature analysis on the deviation between the supply forecast data and the demand data, can better understand the gap between supply and demand, and help to adjust the supply plan in time; the present invention, by calculating the supply evaluation value, can objectively evaluate the current supply of fuel resources and provide an objective basis for decision-making; the present invention determines the scheduling optimization coefficient of fuel resources, and can formulate a reasonable scheduling plan according to actual conditions to maximize resource utilization efficiency; the present invention can achieve scheduling optimization of the supply of fuel resources to meet actual needs and maximize benefits, thereby improving resource utilization efficiency and reducing costs, and to a certain extent alleviate the contradiction between supply and demand, and help promote the sustainable development of the energy industry.

[0020] In an embodiment of the present application, a fuel resource scheduling optimization method is provided, wherein the preprocessing of supply quantity data comprises: preprocessing the supply quantity data, the preprocessing comprises removing abnormal data and overloaded data in the supply quantity data and filling missing data, and standardizing the supply quantity data.

[0021] Specifically, to remove erroneous data points and identify and remove outliers, statistical methods (such as mean +- 3 times standard deviation) or specialized anomaly detection algorithms (such as isolation forest algorithm, LOF algorithm, etc.) can be used to identify outliers and remove them from the data set; to fill missing values, for missing data points, interpolation methods (such as linear interpolation, polynomial interpolation) can be used to fill missing values, or they can be filled according to the trend of previous and subsequent values; they can be identified and removed by setting thresholds or using anomaly detection algorithms. Duplicate data may be due to problems with the data collection system and require deduplication; data standardization can be done by performing z-score standardization (also called standard deviation standardization) or minimum-maximum standardization on the data, mapping the data to a standard normal distribution with a mean of 0 and a standard deviation of 1, or mapping it to a range of 0 to 1, in order to eliminate the dimensional effects between different variables and ensure that the data is on a uniform scale.

[0022] In an embodiment of the present application, a fuel resource scheduling optimization method is provided, which constructs a fuel resource supply prediction model based on supply quantity data, and predicts the supply quantity of fuel resources according to the fuel resource supply quantity prediction model to obtain fuel resource supply quantity prediction data, including: constructing a data set based on the supply quantity data, and inputting the data set into a preset neural network model to construct an initial model for fuel resource supply quantity prediction; dividing the data set into a training set and a test set according to a certain ratio, and inputting the training set and the test set into the initial model for supply quantity prediction; training and testing the initial model for supply quantity prediction until the initial model for supply quantity prediction meets the preset convergence conditions to obtain the fuel resource supply quantity prediction model; and predicting the fuel resource supply quantity prediction data for a period of time in the future according to the obtained supply quantity prediction model.

[0023] Specifically, a data set is constructed based on supply data. Data set construction can provide guarantees for data quality, ensure the effectiveness of feature engineering, and provide a high-quality data foundation for subsequent model training; select appropriate neural network structures and architectures, such as multi-layer perceptron (MLP), recurrent neural network (RNN) or long short-term memory network (LSTM), and build a neural network model based on data characteristics; divide the constructed data set into training set and test set according to a certain ratio, with 80% of the data used for training and 20% of the data used for testing. Data set division can ensure the representativeness and independence of the training set and test set, as well as avoid data leakage during model training and testing. Input into the neural network model, and continuously adjust the model parameters through the back propagation algorithm until the model meets the preset convergence conditions, that is, the loss function converges or reaches the specified number of training rounds. The technical effects of model training include the optimization of model parameters, the convergence of loss function, and the fitting effect of the model on the training data. Input the test set into the trained neural network model to evaluate the generalization ability of the model for unseen data, and evaluate it by calculating the error between the predicted result and the actual value; use the trained neural network model to predict the supply of fuel resources in the future period of time, and obtain the predicted data to improve the accuracy, stability and interpretability of the prediction results, as well as the reasonable prediction of the future fuel resource supply situation. The effective execution of these steps can help build an accurate and reliable fuel resource supply prediction model, providing important decision support for resource scheduling and planning in the energy industry.

[0024] In an embodiment of the present application, a fuel resource scheduling optimization method is provided, wherein the demand for fuel resources is obtained and the deviation characteristics between the supply forecast data and the demand are determined, including: obtaining the coal supply demand and performing a difference calculation between each data in the predicted coal supply data and the coal supply demand to obtain deviation data; plotting the deviation data into a deviation data curve, and analyzing the deviation data curve to determine the deviation characteristics between the supply forecast data and the demand.

[0025] Specifically, the actual coal supply demand is obtained, and the predicted coal supply data is subtracted from the actual coal supply demand to obtain the deviation data. The deviation data represents the difference between the predicted value and the actual demand, which can reflect the accuracy and deviation of the prediction model; the deviation data is plotted into a deviation data curve, with time as the horizontal axis and the deviation value as the vertical axis, showing the change of the deviation between the predicted value and the actual demand over time; the deviation data curve is analyzed to determine the deviation characteristics between the supply forecast data and the demand. This step can discover the laws and characteristics of the deviation, analyze the causes of the deviation, evaluate the accuracy and stability of the prediction model, and provide a basis for subsequent model optimization and decision-making.

[0026] In an embodiment of the present application, a fuel resource scheduling optimization method is provided, in which the deviation data curve is analyzed to determine the deviation characteristics between the supply forecast data and the demand, including: obtaining the peak value and the trough value in the deviation data curve, and determining the curve segments from each peak value to the trough value and from each trough value to the peak value; calculating the deviation data average value and the curve segment slope corresponding to each curve segment, and determining these deviation data average values ​​and curve segment slopes as the deviation characteristics between the supply forecast data and the demand.

[0027] Specifically, use signal processing or data analysis methods to identify the peaks and troughs in the deviation data curve; for each interval between the peak and the trough, determine these intervals as curve segments, which represent the local trend changes in the deviation data curve; for each curve segment, calculate the average value of the corresponding deviation data and the slope of the curve segment. The average value of the deviation data represents the overall deviation of the curve segment, and the slope reflects the rate of change of the deviation. These deviation data average values ​​and curve segment slopes are determined as the deviation characteristics between the supply forecast data and the demand. These characteristics can help understand the characteristics and trends of different intervals in the deviation data curve. By identifying the peaks and troughs and analyzing the curve segments, we can understand the local characteristics of the deviation data curve in more detail, discover the law of deviation change, and provide more in-depth information for further model improvement and decision making. The execution of these steps can help to deeply understand the deviation characteristics between the supply forecast data and the demand, and provide more detailed analysis results and basis for subsequent optimization and decision-making.

[0028] In an embodiment of the present application, a fuel resource scheduling optimization method is provided, which evaluates and calculates the supply situation of fuel resources based on deviation characteristics to obtain a supply evaluation value of fuel resources, including: pre-setting a standard average value of a curve segment, obtaining a deviation data average value and a curve segment slope corresponding to each curve segment; performing a difference calculation between the deviation data average value corresponding to each curve segment and the standard average value to obtain a difference value corresponding to each curve segment, and evaluating and taking a value for each curve segment according to the size of each difference value to obtain an evaluation value for each curve segment; calculating the average value of the curve segment slopes corresponding to all curve segments, and calculating the ratio of the curve segment slope corresponding to each curve segment to the average value, and determining the ratio as the weight corresponding to each curve segment; performing a weighted addition calculation on the evaluation value of each curve segment and the weight of each curve segment to obtain a supply evaluation value of fuel resources.

[0029] Specifically, before performing the deviation data curve analysis, it is necessary to pre-set the standard average value of the curve segment. This standard average value can be a predetermined value used as an evaluation standard. For each curve segment, calculate the difference between its corresponding deviation data average value and the standard average value. This difference represents the degree of deviation of the curve segment. According to the size of each difference, evaluate each curve segment. The evaluation can be performed based on the positive and negative values ​​of the difference, the absolute value, and other standards, and each curve segment is classified and rated. Calculate the average value of the curve segment slopes corresponding to all curve segments as a reference value for weight calculation. For each curve segment, calculate the ratio of its corresponding curve segment slope to the average slope as the weight of the curve segment. This ratio can reflect the degree of deviation of the curve segment slope from the overall trend. Perform weighted addition calculation on the evaluation value of each curve segment and the weight to obtain the supply assessment value of the fuel resource. This assessment value can comprehensively consider the deviation and slope characteristics of each curve segment, and provide a comprehensive quantitative indicator for the final supply assessment. By executing these steps, a comprehensive assessment can be made of the deviations and trend characteristics of fuel resource supply, providing more comprehensive information and reference for supply volume decisions.

[0030] In an embodiment of the present application, a fuel resource scheduling optimization method is provided, which determines the scheduling optimization coefficient of the fuel resources according to the supply evaluation value, and schedules and optimizes the supply of the fuel resources according to the scheduling optimization coefficient, including: pre-setting a scheduling optimization coefficient-supply evaluation value interval correspondence relationship, and the scheduling optimization coefficient-supply evaluation value interval correspondence relationship is associated with a corresponding scheduling optimization coefficient for each supply evaluation value interval; obtaining the supply evaluation value, and based on the mapping relationship between the supply evaluation value interval to which the supply evaluation value belongs within the scheduling optimization coefficient-supply evaluation value interval correspondence relationship, selecting the scheduling optimization coefficient corresponding to the supply evaluation value interval; and scheduling and optimizing the supply of the fuel resources according to the scheduling optimization coefficient.

[0031] Specifically, in order to map the supply evaluation value to the scheduling optimization coefficient, it is necessary to pre-set the corresponding relationship between the scheduling optimization coefficient and the supply evaluation value interval; according to the supply evaluation value calculated in the previous step, as the input of the subsequent scheduling optimization, according to the supply evaluation value interval to which the difference belongs, find the corresponding scheduling optimization coefficient in the scheduling optimization coefficient-supply evaluation value interval correspondence relationship, and this mapping relationship can map the supply evaluation value to the corresponding scheduling optimization coefficient according to the pre-set rules; according to the mapped scheduling optimization coefficient, select the scheduling optimization coefficient corresponding to the supply evaluation value interval, and this scheduling optimization coefficient can be used to adjust the supply of fuel resources to achieve the goal of scheduling optimization; according to the selected scheduling optimization coefficient, the supply of fuel resources is scheduled and optimized. Through the execution of these steps, the supply of fuel resources can be scheduled and optimized according to the supply evaluation value to achieve more efficient resource utilization and demand satisfaction.

[0032] like Figure 2 As shown, in an embodiment of the present application, a fuel resource scheduling optimization system is provided, including: an acquisition module, used to acquire supply quantity data of fuel resources and preprocess the supply quantity data of fuel resources; a prediction module, used to construct a supply quantity prediction model of fuel resources based on the supply quantity data, and predict the supply quantity of fuel resources according to the supply quantity prediction model of fuel resources to obtain supply quantity prediction data of fuel resources; a determination module, used to acquire the demand for fuel resources and determine the deviation characteristics between the supply quantity prediction data and the demand; an evaluation module, used to evaluate and calculate the supply situation of fuel resources based on the deviation characteristics to obtain a supply evaluation value of fuel resources; an optimization module, used to determine the scheduling optimization coefficient of fuel resources according to the supply evaluation value, and schedule and optimize the supply of fuel resources according to the scheduling optimization coefficient.

[0033] In summary, an embodiment of the present invention provides a method and system for optimizing the scheduling of fuel resources, which includes: obtaining and preprocessing the supply quantity data of fuel resources; constructing a supply quantity prediction model based on the supply quantity data, and obtaining the supply quantity prediction data according to its prediction; obtaining the demand for fuel resources, and determining the deviation characteristics between the supply quantity prediction data and the supply quantity prediction data; evaluating the supply situation of fuel resources based on the deviation characteristics to obtain a supply evaluation value; determining the scheduling optimization coefficient of fuel resources according to the supply evaluation value, and optimizing the scheduling of the supply according to the scheduling optimization coefficient. The present invention can predict the supply quantity data in real time based on the analysis and modeling of the supply quantity data of fuel resources, and determine the scheduling optimization coefficient of fuel resources by evaluating the deviation characteristics between the supply quantity prediction data and the supply quantity prediction data, so as to optimize and adjust the fuel resources, improve the energy utilization efficiency, and alleviate the contradiction between supply and demand to a certain extent, and promote the sustainable development of the energy industry.

[0034] Finally, it should be noted that: Obviously, a person skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalent technology, the present invention is also intended to include these modifications and variations.

[0035] The above is only an example of implementation of the present invention, but it cannot be used to limit the scope of the present invention. Any structural changes made according to the present invention, as long as they do not lose the essence of the present invention, should be regarded as falling within the scope of protection of the present invention and being restricted. Technical personnel in the relevant technical field can clearly understand that for the convenience and simplicity of description, the specific working process and related instructions of the platform described above can refer to the corresponding process in the aforementioned platform embodiment, and will not be repeated here.

[0036] The term "comprises" or any other similar term is intended to cover a non-exclusive inclusion such that a process, platform, article, or apparatus / platform that includes a list of elements includes not only those elements but also other elements not expressly listed or inherent to such process, platform, article, or apparatus / platform.

[0037] So far, the technical solutions of the present invention have been described in conjunction with the further embodiments shown in the accompanying drawings. However, it is easy for a person skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, a person skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0038] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention.

Claims

1. A method for optimizing fuel resource scheduling, characterized in that: include: Obtaining fuel resource supply data and preprocessing the fuel resource supply data; Building a fuel resource supply prediction model based on the supply data, and predicting the supply of the fuel resource according to the fuel resource supply prediction model to obtain fuel resource supply prediction data; Obtaining the demand for fuel resources and determining the deviation characteristics between the supply forecast data and the demand; The supply situation of the fuel resources is evaluated and calculated based on the deviation characteristics to obtain the supply evaluation value of the fuel resources; The scheduling optimization coefficient of the fuel resource is determined according to the supply evaluation value, and the supply quantity of the fuel resource is scheduled and optimized according to the scheduling optimization coefficient.

2. A fuel resource scheduling optimization method according to claim condition 1, characterized in that: The preprocessing of the supply quantity data includes: The supply data is preprocessed, which includes removing abnormal data and overloaded data in the supply data, filling in missing data, and standardizing the supply data.

3. A fuel resource scheduling optimization method according to claim condition 2, characterized in that: The method of constructing a fuel resource supply prediction model based on the supply data, and predicting the supply of the fuel resource according to the fuel resource supply prediction model to obtain the fuel resource supply prediction data includes: Constructing a data set based on the supply data, and inputting the data set into a preset neural network model to construct an initial model for predicting the supply of fuel resources; Divide the data set into a training set and a test set according to a certain ratio, and input the training set and the test set into the initial supply forecast model; Training and testing the initial supply forecast model until the initial supply forecast model meets a preset convergence condition, thereby obtaining a fuel resource supply forecast model; The supply forecast data of fuel resources in the future is predicted based on the obtained supply forecast model.

4. A fuel resource scheduling optimization method according to claim condition 3, characterized in that: The obtaining of the demand for fuel resources and determining the deviation characteristics between the supply forecast data and the demand include: Obtain the coal supply demand, and perform a difference calculation between each data in the predicted coal supply data and the coal supply demand to obtain deviation data; The deviation data is plotted into a deviation data curve, and the deviation data curve is analyzed to determine the deviation characteristics between the supply forecast data and the demand.

5. A fuel resource scheduling optimization method according to claim condition 4, characterized in that: The analysis of the deviation data curve to determine the deviation characteristics between the supply quantity forecast data and the demand quantity includes: Obtain peak values ​​and trough values ​​in the deviation data curve, and determine the curve segments from each peak value to the trough value and from each trough value to the peak value; The deviation data average value and the curve segment slope corresponding to each curve segment are calculated, and these deviation data average values ​​and the curve segment slopes are determined as deviation characteristics between the supply quantity forecast data and the demand quantity.

6. A method for optimizing fuel resource scheduling according to claim 5, characterized in that: The evaluating and calculating the supply situation of the fuel resources based on the deviation characteristics to obtain the supply evaluation value of the fuel resources includes: Preset the standard average value of the curve segment, and obtain the average value of the deviation data and the slope of the curve segment corresponding to each curve segment; The average value of the deviation data corresponding to each curve segment is calculated by subtracting the standard average value to obtain the difference value corresponding to each curve segment, and each curve segment is evaluated and valued according to the size of each difference value to obtain the evaluation value of each curve segment; Calculate the average value of the curve segment slopes corresponding to all the curve segments, and calculate the ratio of the curve segment slope corresponding to each curve segment to the average value, and determine the ratio as the weight corresponding to each curve segment; The evaluation value of each curve segment and the weight of each curve segment are weighted and added together to obtain the supply assessment value of the fuel resource.

7. A method for optimizing fuel resource scheduling according to claim 6, characterized in that: The step of determining a scheduling optimization coefficient of the fuel resource according to the supply evaluation value, and performing scheduling optimization on the supply of the fuel resource according to the scheduling optimization coefficient, includes: A scheduling optimization coefficient-supply evaluation value interval correspondence relationship is preset, and the scheduling optimization coefficient-supply evaluation value interval correspondence relationship is associated with a corresponding scheduling optimization coefficient for each supply evaluation value interval; Obtaining a supply evaluation value, and based on a mapping relationship between a supply evaluation value interval to which the supply evaluation value belongs and a corresponding relationship between a scheduling optimization coefficient and a supply evaluation value interval, selecting a scheduling optimization coefficient corresponding to the supply evaluation value interval; The supply of fuel resources is optimized according to the scheduling optimization coefficient.

8. A fuel resource scheduling optimization system, characterized in that: include: An acquisition module, used for acquiring the supply quantity data of the fuel resource and preprocessing the supply quantity data of the fuel resource; A prediction module, used to construct a fuel resource supply prediction model based on the supply data, and predict the supply of the fuel resource according to the fuel resource supply prediction model to obtain fuel resource supply prediction data; A determination module is used to obtain the demand for fuel resources and determine the deviation characteristics between the supply forecast data and the demand; An evaluation module, used to evaluate and calculate the supply of fuel resources based on the deviation characteristics to obtain a supply evaluation value of the fuel resources; The optimization module is used to determine the scheduling optimization coefficient of the fuel resource according to the supply evaluation value, and to perform scheduling optimization on the supply of the fuel resource according to the scheduling optimization coefficient.

Images