Power plant fire coal cost control and allocation system

Abstract

The invention discloses a power plant fire coal cost management and control and dispatching system which comprises a data acquisition module, a management and control dispatching module and a data display window. The data acquisition module is used for acquiring power plant real-time load data, power plant fire coal consumption speed, historical fire coal price, inventory period, international energy price index and policy document; and the management and control dispatching module is used for inputting related data integration through a mathematical model, analyzing the market trend and price fluctuation, and predicting and controlling the fire coal cost. Limitations of a traditional fire coal management system can be broken through, complex decision-making elements are quantified through mathematical modeling, dynamic balance of cost and risks is achieved, the response speed and accuracy of a fire coal cost prediction model to market changes can be effectively improved through the method of combining a dynamic threshold value and online learning, and the market development prospect is wide. The enterprise can realize dynamic optimization and risk controllability of cost prediction in uncertainty of coal price fluctuation, transportation delay and the like.

Description

Technical Field

[0001] The present invention relates to the field of coal-fired thermal power control technology, and more specifically, to a power plant coal cost control and dispatching system. Background Art

[0002] Cost control and transportation play an important role in the heat generation process of power plants. In existing technologies, cost control of power plants mainly includes two aspects. One is the cost control of coal-fired power generation based on coal blending, which reduces power generation costs by adjusting the proportion of low-priced coal in the blending model; the other is energy-saving management based on power supply coal consumption and plant power utilization rate, which reduces unit power generation costs through energy-saving optimization and improving unit performance indicators.

[0003] The existing coal cost control and transportation system mainly relies on manual experience or static rules to assist decision-making. It lacks adaptive optimization capabilities based on real-time data and is difficult to dynamically adjust strategies. Summary of the Invention

[0004] The purpose of the present invention is to provide a power plant coal cost control and transportation system.

[0005] In order to achieve the above-mentioned object, the technical solution adopted by the present invention is as follows: a power plant coal cost control and dispatching system, comprising a data acquisition module, a control and dispatching module and a data display window; The data acquisition module is used to collect real-time load data of power plants, coal consumption rates of power plants, historical coal prices, inventory cycles, international energy price indices and policy documents; The control and dispatch module is used to integrate relevant data through mathematical model input, analyze market trends and price fluctuations, predict and control coal costs, and combine historical data to give price trends, monitor and warn real-time costs; The data display window is used to generate cost reports through decision support and reporting functions, and at the same time utilizes integration and visualization functions to integrate with other systems and intuitively display data.

[0006] Preferably, the management and transportation module includes a coal transportation optimization module and a coal cost prediction module, and the mathematical model includes a transportation optimization model and a cost prediction model; The coal transportation optimization module inputs power plant load data through the transportation optimization model, outputs power plant load fluctuation parameters, and dynamically updates the transportation plan according to the power plant load fluctuation; The coal cost prediction module inputs relevant historical data and external variables through the cost prediction model, compares the predicted cost with the actual procurement cost, and automatically adjusts the model parameters when the predicted cost exceeds the threshold, and triggers an early warning.

[0007] Preferably, the objective function of the coal transportation optimization model is ; in, is the purchase price, unit transportation cost, and unit inventory cost of the i-th path; They are purchase quantity, transportation distance and storage time; is the transportation delay risk cost, is the weight coefficient.

[0008] Preferably, the constraints of the coal transportation optimization model are: Supply and demand balance: (meet the needs of power plants); Coal quality constraints: (Heat value, sulfur content, etc. are weighted to meet standards); Capacity restrictions: (Carrier's maximum capacity); Stock capacity: ; The coal dispatch optimization model uses mixed integer programming to handle discrete decisions (such as supplier selection) and continuous variables (such as procurement volume). For large-scale problems, it also uses genetic algorithms (GA) or ant colony algorithms (ACO) to quickly approximate the optimal solution, embeds rolling horizon control, and dynamically updates the dispatch plan based on power plant load fluctuations.

[0009] Preferably, the cost prediction model adopts a time series model, and performs missing value processing and outlier detection by inputting historical data, external variables and real-time data, and sets a dynamic threshold. If the predicted cost exceeds the threshold, an early warning and parameter adjustment are performed.

[0010] Preferably, the historical data includes coal purchase price, purchase quantity, inventory, transportation cost, and coal consumption rate of power plants; The external variables include market coal price index, weather data, policy changes, and exchange rates; The real-time data includes current purchase contract prices and supply chain status.

[0011] Preferably, the missing value processing adopts time series interpolation or external data filling; the outlier detection is based on statistical methods or isolation forest algorithm to identify abnormal purchase prices, and correct or eliminate them.

[0012] Preferably, the algorithm for setting the dynamic threshold is: ; in, is the mean absolute percentage error within the window, is the adjustment coefficient; if If the value is greater than the threshold, parameter adjustment and warning will be triggered.

[0013] Preferably, the parameter adjustment method of the cost prediction model is: adding the latest actual cost data to the training set through the prior learning strategy, and partially updating the model weights. The algorithm is as follows: ; in is the learning rate, which controls the update amplitude.

[0014] Compared with the prior art, the advantages of the present invention are: This invention can break through the limitations of traditional coal management systems, quantify complex decision-making factors through mathematical modeling, and achieve a dynamic balance between cost and risk. By combining dynamic thresholds with online learning, it can effectively improve the response speed and accuracy of the coal cost prediction model to market changes. Enterprises can achieve dynamic optimization of cost forecasts and controllable risks in the face of uncertainties such as coal price fluctuations and transportation delays.

[0015] Compared with the prior art, the advantages of the present invention are: The present invention can break through the limitations of traditional coal management systems. Through dynamic game decision-making, virtual-reality interactive verification and decentralized trust mechanism, the system can achieve ultra-automatic management of the entire life cycle of coal. It has a fast response speed and can make decisions automatically. It not only reconstructs the coal management process, but also creates a new value exchange paradigm, providing a disruptive solution for the digital transformation of traditional thermal power. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 It is a framework diagram of a power plant coal cost control and transportation system of the present invention. DETAILED DESCRIPTION

[0018] The preferred embodiments of the present invention are described in detail below with reference to the accompanying drawings so that the advantages and features of the present invention can be more easily understood by those skilled in the art, thereby making a clearer and more precise definition of the protection scope of the present invention.

[0019] See Figure 1 As shown, the present invention provides a power plant coal cost control and dispatching system, including a data acquisition module, a control and dispatching module and a data display window; The data acquisition module is used to collect real-time load data of power plants, coal consumption rates of power plants, historical coal prices, inventory cycles, international energy price indices and policy documents; The control and dispatch module is used to integrate relevant data through mathematical model input, analyze market trends and price fluctuations, predict and control coal costs, and combine historical data to give price trends, monitor and warn real-time costs; The data display window is used to generate cost reports through decision support and reporting functions, and at the same time utilizes integration and visualization functions to integrate with other systems and intuitively display data.

[0020] In this embodiment, the management and transportation module includes a coal transportation optimization module and a coal cost prediction module, and the mathematical model includes a transportation optimization model and a cost prediction model; The coal transportation optimization module inputs power plant load data through the transportation optimization model, outputs power plant load fluctuation parameters, and dynamically updates the transportation plan according to the power plant load fluctuation; The coal cost prediction module inputs relevant historical data and external variables through the cost prediction model, compares the predicted cost with the actual procurement cost, and automatically adjusts the model parameters when the predicted cost exceeds the threshold, and triggers an early warning.

[0021] In this embodiment, the objective function of the coal transportation optimization model is: ; in, is the purchase price, unit transportation cost, and unit inventory cost of the i-th path; They are purchase quantity, transportation distance and storage time; is the transportation delay risk cost, is the weight coefficient.

[0022] In this embodiment, the constraints of the coal transportation optimization model are: Supply and demand balance: (meet the needs of power plants); Coal quality constraints: (Heat value, sulfur content, etc. are weighted to meet standards); Capacity restrictions: (Carrier's maximum capacity); Stock capacity: ; Reflects the company's risk appetite: High weight (such as ): Prioritize supply continuity and accept higher costs.

[0023] Low weight (such as ): Pursue the ultimate cost and allow a certain risk of out-of-stock.

[0024] For example, if a power plant shifts 30% of its purchases from land transport to water transport during the rainy season, although the transportation cost is reduced by 15%, the inventory buffer needs to be increased by 5%.

[0025] Quantify complex decision-making factors through mathematical modeling to achieve a dynamic balance between cost and risk.

[0026] The coal dispatch optimization model uses mixed integer programming to handle discrete decisions (such as supplier selection) and continuous variables (such as procurement volume). For large-scale problems, it also uses genetic algorithms (GA) or ant colony algorithms (ACO) to quickly approximate the optimal solution, embeds rolling horizon control, and dynamically updates the dispatch plan based on power plant load fluctuations.

[0027] In this embodiment, the cost prediction model adopts a time series model, and performs missing value processing and outlier detection by inputting historical data, external variables and real-time data, and sets a dynamic threshold. If the predicted cost exceeds the threshold, an early warning and parameter adjustment are performed.

[0028] In this embodiment, the historical data includes coal purchase price, purchase quantity, inventory, transportation cost, and power plant coal consumption rate; The external variables include market coal price index, weather data, policy changes, and exchange rates; The real-time data includes current purchase contract prices and supply chain status.

[0029] In this embodiment, the missing value processing adopts time series interpolation or external data filling; the outlier detection is based on statistical methods or isolation forest algorithm to identify abnormal purchase prices and correct or eliminate them.

[0030] In this embodiment, the algorithm for setting the dynamic threshold is: ; in, is the mean absolute percentage error within the window, is the adjustment coefficient; if If the value is greater than the threshold, parameter adjustment and warning will be triggered.

[0031] In this embodiment, the parameter adjustment method of the cost prediction model is: adding the latest actual cost data to the training set through the prior learning strategy, and partially updating the model weights. The algorithm is as follows: ; in The learning rate is used to control the update amplitude. For example, when the coal price increases by more than 10% in a single day, online learning can quickly capture the price signal and adjust the prediction model. Before the winter heating period, the impact of transportation costs (such as an increase in railway freight rates) on the total cost is updated through incremental learning.

[0032] The method that combines dynamic thresholds with online learning can effectively improve the response speed and accuracy of the coal cost forecasting model to market changes. Enterprises can achieve dynamic optimization of cost forecasts and control risks amid uncertainties such as coal price fluctuations and transportation delays.

[0033] Although the embodiments of the present invention are described in conjunction with the accompanying drawings, the patent owner may make various changes or modifications within the scope of the appended claims. As long as they do not exceed the scope of protection described in the claims of the present invention, they should be within the scope of protection of the present invention.

Claims

1. A power plant coal cost control and transportation system, characterized by: Including data collection module, control and dispatch module and data display window; The data acquisition module is used to collect real-time load data of power plants, coal consumption rates of power plants, historical coal prices, inventory cycles, international energy price indices and policy documents; The control and dispatch module is used to integrate relevant data through mathematical model input, analyze market trends and price fluctuations, predict and control coal costs, and combine historical data to give price trends, monitor and warn real-time costs; The data display window is used to generate cost reports through decision support and reporting functions, and at the same time utilizes integration and visualization functions to integrate with other systems and intuitively display data.

2. A power plant coal cost control and transportation system according to claim 1, characterized in that: The management and transportation module includes a coal transportation optimization module and a coal cost prediction module, and the mathematical model includes a transportation optimization model and a cost prediction model; The coal transportation optimization module inputs power plant load data through the transportation optimization model, outputs power plant load fluctuation parameters, and dynamically updates the transportation plan according to the power plant load fluctuation; The coal cost prediction module inputs relevant historical data and external variables through the cost prediction model, compares the predicted cost with the actual procurement cost, and automatically adjusts the model parameters when the predicted cost exceeds the threshold, and triggers an early warning.

3. A power plant coal cost control and transportation system according to claim 2, characterized in that: The objective function of the coal transportation optimization model is: ; in, is the purchase price, unit transportation cost, and unit inventory cost of the i-th path; They are purchase quantity, transportation distance and storage time; is the transportation delay risk cost, is the weight coefficient.

4. A power plant coal cost control and transportation system according to claim 3, characterized in that: The constraints of the coal transportation optimization model are: Supply and demand balance: (meet the needs of power plants); Coal quality constraints: (Heat value, sulfur content, etc. are weighted to meet standards); Capacity restrictions: (Carrier's maximum capacity); Stock capacity: ; The coal dispatch optimization model uses mixed integer programming to handle discrete decisions (such as supplier selection) and continuous variables (such as procurement volume). For large-scale problems, it also uses genetic algorithms (GA) or ant colony algorithms (ACO) to quickly approximate the optimal solution, embeds rolling horizon control, and dynamically updates the dispatch plan based on power plant load fluctuations.

5. The power plant coal cost control and transportation system according to claim 2, characterized in that: The cost prediction model adopts a time series model, and performs missing value processing and outlier detection by inputting historical data, external variables and real-time data, and sets a dynamic threshold. If the predicted cost exceeds the threshold, an early warning and parameter adjustment will be issued.

6. A power plant coal cost control and transportation system according to claim 5, characterized in that: The historical data includes coal purchase price, purchase quantity, inventory, transportation cost, and coal consumption rate of power plants; The external variables include market coal price index, weather data, policy changes, and exchange rates; The real-time data includes current purchase contract prices and supply chain status.

7. The power plant coal cost control and transportation system according to claim 1, characterized in that: The missing value processing adopts time series interpolation or external data filling; the outlier detection is based on statistical methods or isolation forest algorithm to identify abnormal purchase prices, and correct or eliminate them.

8. A power plant coal cost control and transportation system according to claim 1, characterized in that: The algorithm for setting the dynamic threshold is: ; in, is the mean absolute percentage error within the window, is the adjustment coefficient; if If the value is greater than the threshold, parameter adjustment and warning will be triggered.

9. A power plant coal cost control and transportation system according to claim 1, characterized in that: The parameter adjustment method of the cost prediction model is to add the latest actual cost data to the training set through the prior learning strategy and partially update the model weights. The algorithm is as follows: ; in is the learning rate, which controls the update amplitude.

Images