Method and system for evaluating available days of coal storage based on power generation demand prediction

Abstract

The invention discloses a coal storage available day number evaluation method and system based on power generation demand prediction, and relates to the technical field of power dispatching, and the method comprises the steps: evaluating the power generation demand prediction accuracy and coal power generation demand extension prediction accuracy trend; dividing an extension prediction interval and extending power generation demand evaluation; and evaluating the number of available days of coal power. According to the coal storage available day number evaluation method based on power generation demand prediction, the accuracy of coal power generation demand prediction is evaluated based on the historical operation data of the power grid. According to the method, future operation days are divided, different decision bases are provided for all intervals, power grid dispatching is effectively optimized, and the flexibility and response speed of coal power resource allocation are improved. Based on credible, fuzzy and uncertain intervals, a correlation analysis method or a time sequence extrapolation method is adopted to evaluate coal power generation requirements under different intervals, so that the reliability of coal power operation is improved. The method has better effects in the aspects of coal power dispatching and management, power grid operation stability and response capability.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power dispatching, and in particular to a method and system for evaluating the number of days coal reserves can be used based on power generation demand forecasting. Background Art

[0002] The number of days of available coal reserves is an important parameter in the field of fuel management for power dispatching and operation. It is used to reflect the availability of coal reserves in coal-fired power generation. That is, the greater the number of days of available coal reserves, the longer the existing coal reserves can support subsequent power generation operations without subsequent coal supply. This indicator is mainly used to monitor the abundance of coal-fired power fuel reserves. Compared with the coal reserve quantity indicator, the number of days of available coal reserves can more directly reflect the availability of coal reserves in power generation operations and is closer to the actual needs of power grid dispatching and operation. In recent years, as the basic supporting role of coal-fired power generation in power supply has become increasingly prominent, the number of days of available coal reserves has attracted increasing attention.

[0003] The traditional assessment of the number of days of coal storage available essentially does not take into account the actual demand for coal-fired power generation in the future, which will cause a large deviation between the assessment results and the actual demand. Specifically:

[0004] (1) The installed capacity assessment method uses the total installed capacity of coal-fired power as a benchmark to assess the average daily coal consumption in the later period. Since the actual coal-fired power capacity often does not reach its installed capacity, the assessment results are prone to being conservative;

[0005] (2) The historical coal consumption assessment method is more suitable for situations where the power generation trend is relatively stable. If the actual operating boundary changes significantly, the assessment results will be distorted. For example, if the external power transmission plan is adjusted, the demand for coal-fired power generation will change significantly accordingly, and the coal consumption assessment based on historical data will have a large deviation. In recent years, with the rapid development of new energy, the supply and demand of electricity have changed significantly, and the above problems will become more prominent. Summary of the invention

[0006] In view of the above-mentioned problems, the present invention is proposed.

[0007] Therefore, the technical problem solved by the present invention is that the existing method for evaluating the number of days of available coal reserves has the problems that the evaluation results are conservative, the evaluation results are easily distorted, and the evaluation results deviate greatly from the actual demand.

[0008] To solve the above technical problems, the present invention provides the following technical solutions: a method for evaluating the available days of coal reserves based on power generation demand forecast, including evaluating the accuracy of power generation demand forecast and the accuracy trend of extended forecast of coal-fired power generation demand; dividing the extended forecast interval and extending the power generation demand assessment; and evaluating the available days of coal-fired power.

[0009] As a preferred solution of the method for evaluating the number of days of coal storage available based on power generation demand forecasting described in the present invention, wherein: the evaluation of the accuracy of power generation demand forecasting and the extended forecast accuracy trend of coal-fired power generation demand includes that the coal-fired power generation space is determined by the difference between the power demand of the power grid and the power generation of the power source, which is expressed as:

[0010]

[0011] in, represents the coal-fired power generation demand on the operating day, They represent the power demand of the power grid and the power generation of non-coal power sources on the operation day d, and γ represents the power grid loss rate;

[0012] The network loss rate is determined by the structure of the power grid and is based on the statistical mean of the current network loss rate;

[0013] The power demand of the power grid is determined by the power consumption within the province and the power transmission and reception plan between provinces, which can be expressed as:

[0014]

[0015] in, They represent the power consumption within the province and the power transmission and reception plan between provinces respectively;

[0016] The electricity consumption in the province is predicted and output by relevant factors;

[0017] The inter-provincial power transmission and reception plan is determined by the inter-provincial power transmission and reception agreement;

[0018] The power generation of non-coal power sources is generally determined by hydropower and new energy, expressed as:

[0019]

[0020] in, They represent hydropower generation and renewable energy generation respectively;

[0021] The amount of hydropower generation is determined by hydropower dispatch optimization based on water inflow forecasts;

[0022] The output of renewable energy power generation is predicted by relevant factors.

[0023] As a preferred solution of the method for evaluating the number of days of coal storage available based on power generation demand forecasting described in the present invention, wherein: the evaluation of the accuracy of power generation demand forecasting and the accuracy trend of the extended forecasting of coal-fired power generation demand includes calculating the extended forecasting accuracy of coal-fired power generation demand on each operating day in historical data;

[0024] The forecast accuracy of coal-fired power generation demand on operation day d extended to D days refers to the forecast accuracy of coal-fired power generation demand on the Dth day predicted from operation day d, which is expressed as:

[0025]

[0026] in, They respectively represent the predicted coal-fired power generation demand on day d+D and the actual coal-fired power generation demand on day d+D, which is extended to day D according to the difference between the power demand of the power grid and the power generation of the power source. It represents the accuracy of coal-fired power generation demand forecast from operation day d to the next day D.

[0027] As a preferred solution of the method for evaluating the number of days of coal storage available based on power generation demand forecasting described in the present invention, wherein: the evaluation of the accuracy of power generation demand forecasting and the accuracy trend of the extended forecast of coal-fired power generation demand includes fitting the extended forecast accuracy of coal-fired power generation demand to generate a fitting curve of the extended forecast accuracy of coal-fired power generation demand for analyzing the changing trend of the extended forecast accuracy of coal-fired power generation demand;

[0028] The extended D-day coal-fired power generation demand forecast accuracy is calculated. The indicator is used to evaluate the overall level of the extended D-day forecast accuracy of coal-fired power generation demand. It is defined as the average accuracy of the D-day coal-fired power generation demand forecast in the historical data, expressed as:

[0029]

[0030] Among them, η(D) represents the forecast accuracy of coal-fired power generation demand on the extended D day, represents the mean function;

[0031] The least squares method is used to generate the D-day forecast accuracy function of coal-fired power generation demand extension, which is used to analyze the change trend of the accuracy of coal-fired power generation demand extension forecast. The linear function is used as the fitting function, and the fitting function is expressed as:

[0032] η(D)=aD+b

[0033] Where a and b represent the coefficient of the linear term and the constant term of the fitting function respectively, and D represents the extension days.

[0034] As a preferred solution of the method for evaluating the number of days of coal storage available based on power generation demand forecasting described in the present invention, wherein: the division of the extended forecast interval and the extended power generation demand assessment include fitting the curve change trend according to the extended forecast accuracy rate of coal-fired power generation demand, evaluating the impact of the forecast deviation on the number of days of coal storage available, and dividing the subsequent operating days into a credible interval, a fuzzy interval, and an uncertain interval;

[0035] The assessment benchmark daily average coal consumption, that is, the average daily coal consumption for the current period, is expressed as:

[0036]

[0037] in, represents the base daily average coal consumption of operating day d, ND represents the number of operating days in the current period included in the statistical analysis, dd represents any operating day starting from operating day d and counting backwards to ND days, Indicates the actual coal consumption on the operating day dd;

[0038] The impact of the forecast deviation caused by the extended forecast accuracy of coal-fired power generation demand on the number of days of coal storage is evaluated. The impact of the forecast deviation on the number of days of coal storage is equal to the deviation of the number of days of coal storage corresponding to the extended forecast deviation of coal-fired power generation demand on the benchmark daily average coal consumption, which is expressed as:

[0039]

[0040] Among them, ΔDA(D) represents the deviation of the number of days of available coal reserves caused by the deviation of the forecast of coal-fired power generation demand on the extended D day. Under the benchmark daily average coal consumption level, the deviation is equal to the deviation corresponding to the accuracy rate of the extended forecast of coal-fired power generation demand;

[0041] Divide the extended forecast interval into a credible interval, a fuzzy interval and an uncertain interval according to the forecast deviation of the number of days of available coal reserves, including:

[0042] If the deviation of the number of days of available coal reserves caused by the forecast deviation of coal power generation demand on the extended D day does not exceed 0.1 day, it is determined that the operation day belongs to the credible interval. The judgment standard is expressed as:

[0043] ΔDA(D)≤0.1

[0044] If the deviation of the number of days of available coal reserves caused by the forecast deviation of coal-fired power generation demand on the extended D day exceeds 0.1 day, but does not exceed 0.2 day, it is determined that the operation day belongs to the fuzzy interval. The judgment standard is expressed as follows:

[0045] 0.1<ΔDA(D)≤0.2

[0046] If the deviation of the number of days of available coal reserves caused by the forecast deviation of coal power generation demand on the extended D day exceeds 0.2 days, it is determined that the operation day belongs to the uncertainty interval. The judgment standard is expressed as follows:

[0047] 0.2<ΔDA(D).

[0048] As a preferred solution of the method for evaluating the number of days of coal storage available based on power generation demand forecasting described in the present invention, wherein: the division of the extended forecast interval and the extended power generation demand assessment include predicting the coal power generation demand on different operating days according to the deviation of the number of days of coal storage available caused by the deviation of the coal power generation demand forecast under different extended forecast intervals;

[0049] For any operating day, coal-fired power generation demand is predicted using two methods:

[0050] The correlation analysis method predicts the correlation factors of electricity consumption, hydropower generation, and new energy generation in the province based on relevant factors, and then predicts the demand for coal-fired power generation on the operating day, which is expressed as:

[0051]

[0052] in, represents the coal-fired power generation demand on the operating day d calculated by the correlation analysis method, γ represents the grid loss rate, It represents the power consumption within the province and the power transmission and reception plan between provinces. They represent hydropower generation and renewable energy generation respectively;

[0053] The time series extrapolation method uses the average value of the actual coal-fired power generation demand in the previous period as a reference for the coal-fired power generation demand in the later period, which is expressed as:

[0054]

[0055] in, represents the coal-fired power generation demand on operation day d calculated by the time series extrapolation method, ND represents the number of current operation days included in the statistical analysis, dd represents any operation day starting from operation day d and pushing back ND days, represents the actual coal-fired power generation demand on the operating day dd;

[0056] For any operating day, based on the extended forecast interval division and combined with the characteristics of different forecast methods, the coal-fired power generation demand under different forecast intervals is calculated, including:

[0057] If the operating day meets the credible interval judgment criteria, the correlation analysis method is used to evaluate its coal-fired power generation demand, which is expressed as:

[0058]

[0059] in, It represents the forecast result of coal-fired power generation demand on operation day d;

[0060] If the operation day meets the fuzzy interval judgment standard, the coal-fired power generation demand is evaluated by combining the correlation analysis method and the time series extrapolation method, which is expressed as:

[0061]

[0062] Among them, a R,M 、a T,M They represent the weight coefficients of the correlation analysis method and the time series extrapolation method in the fuzzy interval prediction, and should satisfy a R,M +a T,M =1;

[0063] If the operating day meets the uncertainty interval judgment criteria, the coal-fired power generation demand is evaluated by using the correlation analysis method and time series extrapolation method, but the relevant weights should be adjusted in the fuzzy interval, expressed as:

[0064]

[0065] Among them, a R,N 、a T,N Respectively represent the weight coefficients of the correlation analysis method and the time series extrapolation method in the uncertainty interval prediction, satisfying a R,N +a T,N =1.

[0066] As a preferred solution of the method for evaluating the number of days of coal reserves available based on power generation demand forecasting described in the present invention, wherein: the evaluation of the number of days of coal power available includes calculating the number of days of coal reserves available based on the current coal reserves and the coal power generation demand evaluation values ​​of the credible interval, fuzzy interval, and uncertain interval;

[0067] Calculate the amount of coal in stock corresponding to the amount of electricity that can be generated;

[0068] Considering the coal quality level, after converting the coal reserves of coal-fired power generation to standard coal, the available power generation is calculated according to the standard coal consumption rate of the entire network, which is expressed as:

[0069]

[0070] Among them, E GA Indicates the amount of coal stored corresponding to the amount of electricity that can be generated, Q represents the amount of coal stored, α R , α S , S Indicates the calorific value of stored coal, calorific value of standard coal, and coal consumption rate of standard coal;

[0071] The number of days that the coal reserves can be used is the number of days that the coal reserves can generate electricity corresponding to the electricity required to meet the coal-fired power generation demand up to the end of the day, but cannot meet the coal-fired power generation demand on the next day, expressed as:

[0072]

[0073] Among them, DA represents the number of days that coal can be stored. It represents the coal-fired power generation demand on each operating day output by the extended power generation demand assessment.

[0074] Another object of the present invention is to provide a system for evaluating the number of days of coal reserves based on power generation demand forecasting, which can solve the problem that the current method for evaluating the number of days of coal reserves contains a large deviation between the evaluation results and the actual demand by dividing the extended prediction interval and extending the power generation demand evaluation.

[0075] As a preferred solution of the coal storage available days assessment system based on power generation demand forecast described in the present invention, it includes: a power generation demand forecast accuracy assessment module, a coal-fired power generation demand extended forecast accuracy trend assessment module, an extended forecast interval division module, a power generation demand assessment extension module, and a coal-fired power available days assessment module; the power generation demand forecast accuracy assessment module is used to analyze the change trend of the coal-fired power generation demand forecast accuracy rate; the coal-fired power generation demand extended forecast accuracy trend assessment module is used to analyze the change trend of the coal-fired power generation demand extended forecast accuracy rate; the extended forecast interval division module is used to evaluate the impact of the forecast deviation on the coal storage available days according to the change trend of the coal-fired power generation demand extended forecast accuracy fitting curve, and divide the subsequent operating days into a credible interval, a fuzzy interval, and an uncertain interval; the power generation demand assessment extension module is used to predict the coal-fired power generation demand of different operating days according to the deviation of the coal storage available days caused by the coal-fired power generation demand forecast deviation under different extended forecast intervals; the coal-fired power available days assessment module is used to calculate the coal storage available days according to the current coal storage amount and the credible interval, fuzzy interval, and uncertain interval coal-fired power generation demand assessment value.

[0076] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement a method for evaluating the number of days of coal storage available based on power generation demand forecasting.

[0077] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a method for evaluating the number of days coal reserves are available based on power generation demand forecasts.

[0078] Beneficial effects of the present invention: The method for evaluating the number of days of available coal storage based on power generation demand forecast provided by the present invention evaluates the accuracy of coal-fired power generation demand forecast based on the historical operation data of the power grid, utilizes the relationship between the power grid power demand and the power generation of non-coal power sources, and calculates the coal-fired power generation space in combination with influencing factors such as the power grid loss rate, so as to ensure that the coal-fired power generation demand forecast is closer to the actual situation and improve the reliability and accuracy of subsequent evaluation. The least squares method is used to fit the extended D-day forecast accuracy curve, analyze the trend change of forecast accuracy, define the overall level of forecast accuracy, and provide an intuitive representation of the change trend through the fitting curve. The trend fitting provides a mathematical basis for the forecast accuracy for evaluating coal-fired power generation demand, reducing the uncertainty caused by meteorological changes or demand fluctuations. The future operating days are divided into credible intervals, fuzzy intervals and uncertain intervals. Based on the evaluation of the benchmark daily average coal consumption, the influence of the deviation caused by the extended forecast accuracy on the number of days of available coal storage is judged. The degree of assessment deviation is clarified by distinguishing different intervals, thereby determining the forecast reliability during the operating day, providing different decision-making bases for each interval, effectively optimizing the power grid dispatching, and improving the flexibility and response speed of coal-fired power resource allocation. Based on credible, fuzzy and uncertain intervals, correlation analysis or time series extrapolation is used to evaluate the coal-fired power generation demand in different intervals, and the forecast demand of each interval is adapted by adjusting the weights of different methods. The effect achieved is to dynamically adjust the evaluation method to match the actual demand, increase the accuracy of the forecast demand, and provide the power grid with a fine scheduling means under complex power demand, thereby improving the reliability of coal-fired power operation. Comprehensively considering the current coal reserves, extended forecast interval and coal-fired power generation demand assessment value, the number of days of coal reserves available under different circumstances is calculated, and the number of days of power generation is estimated after the coal reserves are converted into standard coal, which enhances the accuracy and practicality of the number of days of coal reserves available for coal-fired power generation, provides a powerful decision-making support tool for the power dispatching department, and improves the management efficiency of coal reserves. The present invention achieves better results in the dispatching and management of coal-fired power, the stability of power grid operation and the responsiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0080] Figure 1 An overall flow chart of a method for evaluating the number of days coal reserves are available based on power generation demand forecasting provided in the first embodiment of the present invention.

[0081] Figure 2An overall flow chart of a system for evaluating the number of days coal reserves are available based on power generation demand forecasting provided in the third embodiment of the present invention. DETAILED DESCRIPTION

[0082] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0083] Example 1, reference Figure 1 , which is an embodiment of the present invention, provides a method for evaluating the number of days of coal storage available based on power generation demand forecast, comprising:

[0084] S1: Assess the accuracy of generation demand forecasts and trends in the accuracy of extended forecasts of coal-fired generation demand.

[0085] Furthermore, the present invention particularly relates to a method for evaluating the number of days of coal reserves available based on power generation demand forecast, which belongs to the field of power dispatching technology. Its characteristic is that a method for evaluating coal-fired power generation demand based on forecast accuracy analysis is proposed. Through historical data analysis, the extended D-day coal-fired power forecast accuracy is used as the judgment standard, and the subsequent operating days are divided into a credible interval and a fuzzy interval, and a method for evaluating coal-fired power generation demand based on forecasts of relevant factors such as meteorology and a method for predicting coal-fired power generation demand based on historical forecasts of the same period are proposed respectively. On this basis, the evaluation of the number of days of coal reserves available based on power generation demand forecast is realized.

[0086] As attached Figure 1 As shown, the implementation points include:

[0087] Step 1: Evaluate the accuracy of generation demand forecasts.

[0088] The purpose of implementing this step is to analyze the changing trend of the accuracy of coal-fired power generation demand forecast based on the historical data of power grid operation.

[0089] Preferably, different provinces and regions have different power grid structures and grid architectures, but overall, the coal-fired power generation space is determined by the difference between the power demand of the grid and the power generation of other power sources, which can be expressed as:

[0090]

[0091] in, represents the coal-fired power generation demand on the operating day, They represent the power demand of the power grid and the power generation of non-coal power sources on the operation day d, and γ represents the power loss rate of the power grid. The power loss rate is determined by the power grid structure and can be determined based on the statistical mean of the current power loss rate. The power demand and power generation of non-coal power sources vary greatly.

[0092] Preferably, the power demand of the power grid is generally determined by the power consumption within the province and the power transmission and reception plan between provinces, which can be expressed as:

[0093]

[0094] in, They represent the power consumption within the province and the power transmission and reception plan between provinces. The power consumption within the province can be predicted by meteorological and other related factors. The power transmission and reception plan between provinces is determined by the power transmission and reception agreement between provinces.

[0095] Preferably, the power generation of non-coal power sources is generally determined by hydropower, new energy, etc., which can be expressed as:

[0096]

[0097] in, They represent hydropower generation and renewable energy generation respectively. Hydropower generation is determined by hydropower dispatch optimization based on water inflow forecast and serves as the execution boundary of power dispatch. Renewable energy generation is predicted by meteorological and other related factors.

[0098] Preferably, the extended forecast accuracy of coal-fired power generation demand on each operating day in the historical data is calculated. Among them, the forecast accuracy of coal-fired power generation demand on operating day d extended to D days refers to the forecast accuracy of coal-fired power generation demand on the Dth day predicted from operating day d, which can be expressed as:

[0099]

[0100] in, They respectively represent the predicted coal-fired power generation demand on day d+D and the actual coal-fired power generation demand on day d+D, which is extended to day D according to the difference between the power demand of the power grid and the power generation of the power source. It represents the accuracy of coal-fired power generation demand forecast from operation day d to the next day D.

[0101] It should be noted that Step 2: Evaluating the accuracy trend of coal-fired power generation demand extension forecast

[0102] The purpose of implementing this step is to fit the extended forecast accuracy of coal-fired power generation demand and generate a fitting curve of the extended forecast accuracy of coal-fired power generation demand, which is used to analyze the changing trend of the extended forecast accuracy of coal-fired power generation demand.

[0103] Preferably, the extended D-day coal-fired power generation demand forecast accuracy is defined and counted. This indicator is used to evaluate the overall level of the extended D-day forecast accuracy of coal-fired power generation demand. It is defined as the mean of the D-day coal-fired power generation demand forecast accuracy in the historical data, which can be expressed as:

[0104]

[0105] Among them, η(D) represents the forecast accuracy of coal-fired power generation demand on the extended D day, Represents the mean function.

[0106] Preferably, the least square method is used to generate the extended D-day forecast accuracy function of coal-fired power generation demand, which is used to analyze the change trend of the extended forecast accuracy of coal-fired power generation demand. In the present invention, a linear function is used as the fitting function, and the fitting function can be expressed as:

[0107] η(D)=aD+b

[0108] Where a and b represent the coefficient of the linear term and the constant term of the fitting function respectively, and D represents the extension days.

[0109] Considering that the least squares fitting method is a relatively mature statistical method, this article will not go into details about its specific implementation process.

[0110] S2: Divide the extended forecast interval and extend the generation demand assessment.

[0111] Going further, step 3: Divide the extended prediction interval

[0112] The purpose of implementing this step is to fit the changing trend of the curve according to the extended forecast accuracy of coal-fired power generation demand, evaluate the impact of forecast deviation on the number of days of available coal reserves, and divide the subsequent operating days into credible intervals, fuzzy intervals, and uncertain intervals.

[0113] Preferably, the evaluation benchmark daily average coal consumption, that is, the current daily average coal consumption, can be expressed as:

[0114]

[0115] in, represents the base daily average coal consumption of operating day d, ND represents the number of operating days in the current period included in the statistical analysis, dd represents any operating day starting from operating day d and counting backwards to ND days, Indicates the actual coal consumption of the operating day dd.

[0116] Preferably, the impact of the forecast deviation caused by the extended forecast accuracy of coal-fired power generation demand on the number of days of coal storage is evaluated. The impact of the forecast deviation on the number of days of coal storage is equal to the deviation of the number of days of coal storage corresponding to the extended forecast deviation of coal-fired power generation demand on the benchmark daily average coal consumption, which can be expressed as:

[0117]

[0118] Among them, ΔDA(D) represents the deviation in the number of days of available coal reserves caused by the deviation in the forecast of coal-fired power generation demand on the extended D day. Under the benchmark daily average coal consumption level, the deviation is equal to the corresponding deviation in the accuracy of the extended forecast of coal-fired power generation demand.

[0119] Preferably, the extended prediction interval is divided into a credible interval, a fuzzy interval and an uncertain interval according to the prediction deviation of the number of days of available coal reserves, and the division method is:

[0120] (1) If the deviation of the number of days of available coal reserves caused by the forecast deviation of coal-fired power generation demand on the extended D day does not exceed 0.1 day, then the operation day is judged to be within the credible interval. The judgment standard can be expressed as:

[0121] ΔDA(D)≤0.1

[0122] (2) If the deviation of the number of days of available coal reserves caused by the forecast deviation of coal-fired power generation demand on the extended D day exceeds 0.1 day but does not exceed 0.2 day, it is determined that the operation day belongs to the fuzzy interval. The judgment standard can be expressed as:

[0123] 0.1<ΔDA(D)≤0.2

[0124] (3) If the deviation of the number of days of available coal reserves caused by the forecast deviation of coal-fired power generation demand on the extended D day exceeds 0.2 days, it is determined that the operation day belongs to the uncertainty interval. The judgment standard can be expressed as:

[0125] 0.2<ΔDA(D).

[0126] It should be noted that Step 4: Extended Generation Demand Assessment

[0127] The purpose of implementing this step is to predict the coal-fired power generation demand on different operating days based on the deviation in the number of days of available coal reserves caused by the deviation in the forecast of coal-fired power generation demand under different extended forecast intervals.

[0128] Preferably, for any operating day, the coal-fired power generation demand can be predicted using two methods, including:

[0129] (1) Correlation analysis method, that is, based on meteorological and other related factors, the correlation factors such as electricity consumption, hydropower generation, and new energy generation in the province are predicted, and then the coal-fired power generation demand on the operating day is predicted, which can be expressed as:

[0130]

[0131] in, represents the coal-fired power generation demand on the operating day d calculated by the correlation analysis method, γ represents the grid loss rate, It represents the power consumption within the province and the power transmission and reception plan between provinces. They represent hydropower generation and renewable energy generation respectively.

[0132] (2) Time series extrapolation method, that is, taking the average value of actual coal-fired power generation demand in the previous period as a reference for the coal-fired power generation demand in the later period, which can be expressed as:

[0133]

[0134] in, represents the coal-fired power generation demand on operation day d calculated by the time series extrapolation method, ND represents the number of current operation days included in the statistical analysis, dd represents any operation day starting from operation day d and pushing back ND days, Represents the actual coal-fired power generation demand on the operating day dd.

[0135] Compared with the above two methods, the correlation analysis method fully considers the impact of changes in boundary factors such as meteorology on related factors such as provincial electricity consumption, hydropower generation, and new energy generation, and can better show the dynamic changes in daily coal-fired power generation demand. However, as the prediction period increases, the accuracy of boundary factors such as meteorology decreases, which may lead to a decrease in the accuracy of coal-fired power generation demand. The time series extrapolation method fully considers the overall situation of coal-fired power generation demand in the previous period, and can show the overall level of coal-fired power generation demand, but cannot show the dynamic changes in daily coal-fired power generation demand.

[0136] Preferably, a single operation day is selected, based on the extended forecast interval division in step 3, and combined with the characteristics of different forecasting methods, the coal-fired power generation demand under different forecasting intervals is calculated. The specific method includes:

[0137] (1) If the operating day satisfies formula (9), that is, it belongs to the credible interval, the correlation analysis method is used to evaluate its coal-fired power generation demand, which can be expressed as:

[0138]

[0139] in, It represents the forecast result of coal-fired power generation demand on the operating day d.

[0140] (2) If the operating day satisfies formula (10), that is, it belongs to the fuzzy interval, then the coal-fired power generation demand is evaluated by combining the correlation analysis method and the time series extrapolation method, which can be expressed as:

[0141]

[0142] Among them, a R,M 、a T,M They represent the weight coefficients of the correlation analysis method and the time series extrapolation method in the fuzzy interval prediction, and should satisfy a R,M +a T,M =1. The present invention recommends a R,M =0.5, a T,M =0.5.

[0143] (3) If the operation day satisfies formula (11), that is, it belongs to the uncertain interval, then the correlation analysis method and time series extrapolation method are used to evaluate its coal-fired power generation demand, but the relevant weights should be adjusted in the fuzzy interval, which can be expressed as:

[0144]

[0145] Among them, a R,N 、a T,N Respectively represent the weight coefficients of the correlation analysis method and the time series extrapolation method in the uncertainty interval prediction, satisfying a R,N +a T,N =1 Compared with the fuzzy interval, the weight coefficient of the time series extrapolation method should be increased, and correspondingly, the weight coefficient of the correlation analysis method should be reduced. The present invention recommends a R,N =0.2, a T,N =0.8.

[0146] S3: Assess the number of days coal power is available.

[0147] Going further, step 5: Assessment of the number of days coal power can be used

[0148] The purpose of implementing this step is to calculate the number of days that coal reserves can be used based on the current coal reserves and the coal-fired power generation demand assessment values ​​within the credible interval, fuzzy interval, and uncertain interval.

[0149] Preferably, the amount of coal stored is calculated to correspond to the amount of electricity that can be generated. Considering the coal quality level, the amount of coal stored in coal-fired power plants is converted to standard coal, and the amount of electricity that can be generated is calculated according to the standard coal consumption rate of the entire network, which can be expressed as:

[0150]

[0151] Among them, E GA Indicates the amount of coal stored corresponding to the amount of electricity that can be generated, Q represents the amount of coal stored, α R , α S , S Indicates the calorific value of stock coal, calorific value of standard coal, and coal consumption rate of standard coal.

[0152] Preferably, the number of days that the coal reserve can be used is the number of days that the coal reserve corresponds to the available power generation that can just cover the coal-fired power generation demand up to that day, but cannot meet the coal-fired power generation demand on the next day, which can be expressed as:

[0153]

[0154] Among them, DA represents the number of days that coal can be stored. It represents the coal-fired power generation demand on each operating day output by the extended power generation demand assessment.

[0155] Example 2, an embodiment of the present invention, provides a method for evaluating the number of days of coal storage available based on power generation demand forecast. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0156] First, based on the historical data of power grid operation, the prediction accuracy of coal-fired power generation demand is analyzed, and the prediction time is divided into credible interval, fuzzy interval and uncertain interval with the extended prediction days (D-day) as the standard, and different coal-fired power generation demand prediction methods are used respectively. On the basis of the prediction, the number of days of coal storage available on different dates is further calculated to prove the advantages of the present invention in improving the evaluation accuracy and adaptability.

[0157] The experiment was conducted in a provincial power grid system. The test data included historical data within three months, covering the province's electricity demand data, inter-provincial power transmission plan data, hydropower and new energy power generation data, and coal-fired power unit operation data. The following are the specific steps:

[0158] Evaluate the accuracy of power generation demand forecast: First, collect three months of grid power demand and coal-fired power generation space data, and consider various relevant factors (such as the impact of meteorological factors on power demand). Select a standard daily average coal consumption and calculate the accuracy of coal-fired power generation demand on each operating day.

[0159] Forecast accuracy trend fitting: The least squares method is used to fit the forecast accuracy curve to obtain the forecast accuracy change trend of the extended D-day. Through fitting analysis, different forecast intervals are further distinguished, and the forecast deviation under different extended days is calculated.

[0160] Divide the prediction interval: According to the trend of prediction accuracy, determine the credible interval, fuzzy interval and uncertainty interval. The specific standards are as follows: the prediction deviation of the credible interval is less than 0.1 day, the fuzzy interval deviation is between 0.1 and 0.2 days, and the uncertainty interval deviation exceeds 0.2 days. The divided intervals will be used to select different prediction methods.

[0161] Extended power generation demand assessment: The power generation demand for each operating day is predicted. The credible interval uses the correlation analysis method to make a detailed prediction. The fuzzy interval and the uncertain interval use a combination of correlation analysis and time series extrapolation to improve the adaptability of the prediction.

[0162] Calculation of the number of days of coal reserves available: Based on the current coal reserves and the predicted coal-fired power generation demand within the credible interval, fuzzy interval, and uncertain interval, the corresponding number of days of coal reserves available is estimated. The coal quality and the standard coal consumption rate of the entire network are taken into account during the calculation, and the results are compared with the actual operation to verify the accuracy and adaptability of the prediction.

[0163] Table 1 Experimental data table

[0164]

[0165] By comparing the data in the table, it can be clearly seen that the accuracy advantage of the present invention in coal-fired power generation demand forecasting. The analysis is as follows:

[0166] Improve forecast accuracy: As can be seen from the table data, the present invention reduces the deviation caused by changes in electricity demand by extending the forecast accuracy analysis and dividing different forecast dates into credible, fuzzy and uncertain intervals. For example, in the data from 2024-01-01 to 2024-01-07, it can be seen that the daily changes in coal-fired power generation demand and the number of days of available coal storage have obvious regularity. This shows that by using methods such as the correlation analysis method of credible intervals and the comprehensive method of fuzzy intervals, the present invention can effectively improve the accuracy of daily coal-fired power generation demand forecasts, especially when external factors such as meteorology are uncertain and still maintain a high forecast accuracy.

[0167] Innovative interval division: Compared with the prior art, the present invention introduces the division of prediction intervals, so that when facing operating days with high uncertainty, the system can flexibly switch prediction methods and reduce prediction errors. For example, the number of days of available coal reserves on 2024-01-03 and 2024-01-04 did not change much, indicating that the use of hybrid prediction methods within the fuzzy interval can effectively balance the error, while maintaining a high prediction accuracy in the credible interval. This innovative interval division significantly improves the reliability of the assessment of the number of days of available coal reserves, enabling the power dispatching department to allocate coal-fired power resources more reasonably.

[0168] Strongly adaptable demand assessment: In the table data, from 2024-01-01 to 2024-01-07, the electricity demand and non-coal power generation on different operating days vary greatly. The present invention improves the prediction accuracy when meteorological factors change drastically by associating hydropower generation, renewable energy generation and meteorological factors. For example, due to weather changes on 2024-01-05 and 2024-01-06, renewable energy generation fluctuated, but because the present invention uses correlation analysis to evaluate power generation demand, the stability and adaptability of the prediction are guaranteed.

[0169] The rationality of coal storage management is improved: the number of days of coal storage shown in the table shows a gradual downward trend as the demand for coal-fired power generation changes, but the change range is small, indicating that the present invention can effectively control the forecast deviation within a reasonable range. This is of great significance for the dynamic management of coal storage, which can effectively avoid the problem of insufficient or excessive coal storage caused by excessive forecast errors and improve the stability of the power system.

[0170] In summary, the present invention achieves accurate assessment of the number of days coal can be stored through scientific prediction accuracy analysis and reasonable interval division, which is significantly innovative and practical. This method is particularly applicable in scenarios where power generation demand fluctuates greatly and power dispatching demand is complex, and can significantly improve the resource allocation and emergency dispatching capabilities of the power system.

[0171] Example 3, reference Figure 2 , which is an embodiment of the present invention, provides a system for evaluating the number of days of coal reserves based on power generation demand forecast, including a power generation demand forecast accuracy evaluation module, a coal-fired power generation demand extended forecast accuracy trend evaluation module, an extended forecast interval division module, a power generation demand assessment extension module, and a coal-fired power available days evaluation module.

[0172] Among them, the power generation demand forecast accuracy assessment module is used to analyze the changing trend of the accuracy of coal-fired power generation demand forecast, the coal-fired power generation demand extended forecast accuracy trend assessment module is used to analyze the changing trend of the extended forecast accuracy of coal-fired power generation demand, the extended forecast interval division module is used to fit the changing trend of the curve of the extended forecast accuracy of coal-fired power generation demand, evaluate the impact of the forecast deviation on the number of days of available coal reserves, and divide the subsequent operating days into credible intervals, fuzzy intervals, and uncertain intervals. The power generation demand assessment extension module is used to predict the coal-fired power generation demand on different operating days according to the deviation in the number of days of available coal reserves caused by the coal-fired power generation demand forecast deviation under different extended forecast intervals. The coal-fired power available days assessment module is used to calculate the number of days of available coal reserves based on the current coal reserves and the credible interval, fuzzy interval, and uncertain interval coal-fired power generation demand assessment values.

[0173] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0174] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0175] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0176] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and are not limited. Although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

[0177] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for evaluating the number of days of coal storage available based on power generation demand forecast, characterized in that: include: Assess the accuracy of generation demand forecasts and trends in the accuracy of extended forecasts of coal-fired generation demand; Delineate extended forecast intervals and extend generation demand assessment; Assess the number of days coal-fired power is available.

2. The method for evaluating the number of days of coal storage available based on power generation demand forecasting according to claim 1, characterized in that: The evaluation of the accuracy of power generation demand forecast and the extended forecast accuracy trend of coal-fired power generation demand includes that the coal-fired power generation space is determined by the difference between the power demand of the power grid and the power generation of the power source, which is expressed as: in, represents the coal-fired power generation demand on the operating day, They represent the power demand of the power grid and the power generation of non-coal power sources on the operation day d, and γ represents the power grid loss rate; The network loss rate is determined by the grid structure and is based on the statistical mean of the current network loss rate; The power demand of the power grid is determined by the power consumption within the province and the power transmission and reception plan between provinces, which can be expressed as: in, They represent the power consumption within the province and the power transmission and reception plan between provinces respectively; The electricity consumption in the province is predicted and output by relevant factors; The inter-provincial power transmission and reception plan is determined by the inter-provincial power transmission and reception agreement; The power generation of non-coal power sources is generally determined by hydropower and new energy, expressed as: in, They represent hydropower generation and renewable energy generation respectively; The hydropower generation is determined by hydropower dispatch optimization based on the water inflow forecast; The output of renewable energy power generation is predicted by relevant factors.

3. The method for evaluating the number of days of coal storage available based on power generation demand forecasting according to claim 2, characterized in that: The evaluation of the accuracy of power generation demand forecast and the trend of the accuracy of the extended forecast of coal-fired power generation demand includes calculating the accuracy of the extended forecast of coal-fired power generation demand on each operating day in the historical data; The forecast accuracy of coal-fired power generation demand on operation day d extended to D days refers to the forecast accuracy of coal-fired power generation demand on the Dth day predicted from operation day d, which is expressed as: in, They respectively represent the predicted coal-fired power generation demand on day d+D and the actual coal-fired power generation demand on day d+D, which is extended to day D according to the difference between the power demand of the power grid and the power generation of the power source. It represents the accuracy of coal-fired power generation demand forecast from operation day d to the next day D.

4. The method for evaluating the number of days of coal storage available based on power generation demand forecasting according to claim 3, characterized in that: The evaluating of the accuracy of power generation demand forecast and the trend of the accuracy of the extended forecast of coal-fired power generation demand includes fitting the accuracy of the extended forecast of coal-fired power generation demand to generate a fitting curve of the accuracy of the extended forecast of coal-fired power generation demand for analyzing the trend of the change of the accuracy of the extended forecast of coal-fired power generation demand; The extended D-day coal-fired power generation demand forecast accuracy is calculated. The indicator is used to evaluate the overall level of the extended D-day forecast accuracy of coal-fired power generation demand. It is defined as the average accuracy of the D-day coal-fired power generation demand forecast in the historical data, expressed as: Among them, η(D) represents the forecast accuracy of coal-fired power generation demand on the extended D day, represents the mean function; The least squares method is used to generate the D-day forecast accuracy function of coal-fired power generation demand extension, which is used to analyze the change trend of the accuracy of coal-fired power generation demand extension forecast. The linear function is used as the fitting function, and the fitting function is expressed as: η(D)=aD+b Where a and b represent the coefficient of the linear term and the constant term of the fitting function respectively, and D represents the extension days.

5. The method for evaluating the number of days of coal storage available based on power generation demand forecasting according to claim 4, characterized in that: The division of the extended prediction interval and the extension of the power generation demand assessment include fitting the curve change trend according to the extended prediction accuracy of the coal-fired power generation demand, assessing the impact of the prediction deviation on the number of days of coal storage, and dividing the subsequent operation days into a credible interval, a fuzzy interval, and an uncertain interval; The assessment benchmark daily average coal consumption, that is, the average daily coal consumption for the current period, is expressed as: in, represents the base daily average coal consumption of operating day d, ND represents the number of operating days in the current period included in the statistical analysis, dd represents any operating day starting from operating day d and counting backwards to ND days, Indicates the actual coal consumption on the operating day dd; The impact of the forecast deviation caused by the extended forecast accuracy of coal-fired power generation demand on the number of days of coal storage is evaluated. The impact of the forecast deviation on the number of days of coal storage is equal to the deviation of the number of days of coal storage corresponding to the extended forecast deviation of coal-fired power generation demand on the benchmark daily average coal consumption, which is expressed as: Among them, ΔDA(D) represents the deviation of the number of days of available coal reserves caused by the deviation of the forecast of coal-fired power generation demand on the extended D day. Under the benchmark daily average coal consumption level, the deviation is equal to the deviation corresponding to the accuracy rate of the extended forecast of coal-fired power generation demand; Divide the extended forecast interval into a credible interval, a fuzzy interval and an uncertain interval according to the forecast deviation of the number of days of available coal reserves, including: If the deviation of the number of days of available coal reserves caused by the forecast deviation of coal-fired power generation demand on the extended D day does not exceed 0.1 day, it is determined that the operation day belongs to the credible interval. The judgment standard is expressed as: ΔDA(D)≤0.1 If the deviation of the number of days of available coal reserves caused by the forecast deviation of coal power generation demand on the extended D day exceeds 0.1 day, but does not exceed 0.2 day, it is determined that the operation day belongs to the fuzzy interval. The judgment standard is expressed as follows: 0.1<ΔDA(D)≤0.2 If the deviation of the number of days of available coal reserves caused by the forecast deviation of coal power generation demand on the extended D day exceeds 0.2 days, it is determined that the operation day belongs to the uncertain interval. The judgment standard is expressed as follows: 0.2<ΔDA(D).

6. The method for evaluating the number of days of coal storage available based on power generation demand forecast according to claim 5, characterized in that: The division of the extended forecast interval and the extended power generation demand assessment includes predicting the coal power generation demand on different operating days according to the deviation of the number of days of available coal storage caused by the deviation of the coal power generation demand forecast under different extended forecast intervals; For any operating day, coal-fired power generation demand is predicted using two methods: The correlation analysis method predicts the correlation factors of electricity consumption, hydropower generation, and new energy generation in the province based on relevant factors, and then predicts the demand for coal-fired power generation on the operating day, which is expressed as: in, represents the coal-fired power generation demand on the operating day d calculated by the correlation analysis method, γ represents the grid loss rate, It represents the power consumption within the province and the power transmission and reception plan between provinces. They represent hydropower generation and renewable energy generation respectively; The time series extrapolation method uses the average value of the actual coal-fired power generation demand in the previous period as a reference for the coal-fired power generation demand in the later period, which is expressed as: in, represents the coal-fired power generation demand on operation day d calculated by the time series extrapolation method, ND represents the number of current operation days included in the statistical analysis, dd represents any operation day starting from operation day d and pushing back ND days, represents the actual coal-fired power generation demand on the operating day dd; For any operating day, based on the extended forecast interval division and combined with the characteristics of different forecast methods, the coal-fired power generation demand under different forecast intervals is calculated, including: If the operation day meets the credible interval judgment criteria, the correlation analysis method is used to evaluate its coal-fired power generation demand, which is expressed as: in, It represents the forecast result of coal-fired power generation demand on operation day d; If the operation day meets the fuzzy interval judgment standard, the coal-fired power generation demand is evaluated by combining the correlation analysis method and the time series extrapolation method, which is expressed as: Among them, a R,M 、a T,M They represent the weight coefficients of the correlation analysis method and the time series extrapolation method in the fuzzy interval prediction, and should satisfy a R,M +a T,M =1; If the operating day meets the uncertainty interval judgment criteria, the coal-fired power generation demand is evaluated by using the correlation analysis method and time series extrapolation method, but the relevant weights should be adjusted in the fuzzy interval, expressed as: Among them, a R,N 、a T,N Respectively represent the weight coefficients of the correlation analysis method and the time series extrapolation method in the uncertainty interval prediction, satisfying a R,N +a T,N =1.

7. The method for evaluating the number of days of coal storage available based on power generation demand forecast according to claim 6, characterized in that: The evaluation of the number of days coal power is available includes calculating the number of days coal is available based on the current coal reserves and the coal power generation demand evaluation values ​​of the credible interval, fuzzy interval, and uncertain interval; Calculate the amount of coal in stock corresponding to the amount of electricity that can be generated; Considering the coal quality level, after converting the coal reserves of coal-fired power generation to standard coal, the available power generation is calculated according to the standard coal consumption rate of the entire network, which is expressed as: Among them, E GA Indicates the amount of coal stored corresponding to the amount of electricity that can be generated, Q represents the amount of coal stored, α R , α S , S Indicates the calorific value of stored coal, calorific value of standard coal, and coal consumption rate of standard coal; The number of days that the coal reserves can be used is the number of days that the coal reserves can generate electricity corresponding to the electricity required to meet the coal-fired power generation demand up to the end of the day, but cannot meet the coal-fired power generation demand on the next day, expressed as: Among them, DA represents the number of days that coal can be stored. It represents the coal-fired power generation demand on each operating day output by the extended power generation demand assessment.

8. A system using the method for evaluating the number of days of coal storage available based on power generation demand forecast as claimed in any one of claims 1 to 7, characterized in that: It includes power generation demand forecast accuracy assessment module, coal-fired power generation demand extended forecast accuracy trend assessment module, extended forecast interval division module, power generation demand assessment extension module, and coal-fired power available days assessment module; The power generation demand forecast accuracy evaluation module is used to analyze the change trend of the coal-fired power generation demand forecast accuracy; The coal-fired power generation demand extension forecast accuracy trend assessment module is used to analyze the coal-fired power generation demand extension forecast accuracy change trend; The extended prediction interval division module is used to fit the curve change trend according to the extended prediction accuracy rate of coal-fired power generation demand, evaluate the impact of prediction deviation on the number of days of coal storage, and divide the subsequent operation days into a credible interval, a fuzzy interval, and an uncertain interval; The power generation demand assessment extension module is used to predict the coal-fired power generation demand on different operating days according to the deviation of the number of days of available coal storage caused by the prediction deviation of the coal-fired power generation demand under different extended prediction intervals; The coal-fired power available days assessment module is used to calculate the available days of coal reserves based on the current coal reserves and the coal-fired power generation demand assessment values ​​of the credible interval, fuzzy interval, and uncertain interval.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for evaluating the available days of coal storage based on power generation demand forecast described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for evaluating the available days of coal storage based on power generation demand forecast described in any one of claims 1 to 7 are implemented.

Images