Clean heat supply system load prediction method based on big data

Abstract

The invention relates to the technical field of data prediction, in particular to a clean heat supply system load prediction method based on big data, and the method comprises the steps: obtaining daily gas supply data and various meteorological data in a plurality of historical days; grouping the gas supply amount data; analyzing the correlation between the various meteorological data and the gas supply amount data, and determining the influence degree of the various meteorological data on the gas supply amount demand; on the basis of distribution of all the day gas supply data with the same meteorological data and in combination with the influence degree, theoretical gas supply data and errors of all the gas supply data in all the groups are determined; determining the certainty degree that preset position data in each group can be predicted by other data and the feasibility of each group; and integrating the gas supply amount data in all groups and the feasibility, determining a weighted likelihood function, and constructing an AR model for predicting the gas supply demand. The invention aims to improve the prediction accuracy of the gas supply demand.

Description

Technical Field

[0001] The present application relates to the technical field of data prediction, and in particular to a method for predicting the load of a clean heating system based on big data. Background Art

[0002] At present, cities in my country are actively promoting the transformation to clean heating. After the transformation to clean heating, it is necessary to rely on upstream companies to adjust the gas supply to match the demand of heat users. If the supply is insufficient, the transformation will fail. When there is an oversupply, the gas storage risk is greater. Therefore, it is very important to accurately predict the gas supply demand to achieve gas allocation.

[0003] At present, the autoregressive model (AR model) is usually used to predict the future gas supply based on the historical gas supply. Among them, the construction of the AR model is the key. The existing technology generally calculates the autoregressive coefficient based on the historical gas supply data. However, due to the influence of factors such as natural disasters or public health emergencies, some historical gas supply data are not obtained by the combined influence of multiple weather factors. The core of the change in gas supply demand is to respond to meteorological changes. Therefore, the deviation of the autoregressive coefficient is large, which leads to a large prediction error of the gas supply demand. Summary of the invention

[0004] In view of the above, it is necessary to provide a clean heating system load forecasting method based on big data, which improves the accuracy of gas supply demand forecasting compared with traditional clean heating system load forecasting methods.

[0005] A clean heating system load prediction method based on big data in this application adopts the following technical solution: An embodiment of the present application provides a clean heating system load prediction method based on big data, the method comprising the following steps: Obtain daily gas supply data and various meteorological data for multiple historical days; Determine the order of the AR model based on the autocorrelation of all the acquired air supply volume data, and group the air supply volume data based on the order; Analyze the correlation between various meteorological data and gas supply data, and determine the impact of various meteorological data on gas supply demand; Based on the distribution of the air supply data on all days with the same meteorological data, and in combination with the degree of influence, determine the theoretical air supply data of each air supply data in each group; based on the difference between each air supply data in each group and its theoretical air supply data, determine the error of each air supply data in each group; Based on the errors and order of each gas supply volume data in each group, determining the confidence that the preset position data in each group can be predicted by the remaining data; Determining the feasibility of each grouping based on the confidence level and the error of the gas supply volume data of the preset position in each grouping; The gas supply volume data in all groups and the feasibility are comprehensively considered to determine a weighted likelihood function; and an AR model for predicting gas supply demand is constructed based on the likelihood function.

[0006] In one embodiment, the method for grouping the gas supply volume data is: using the autocorrelation function graph to determine the order p of the AR model, and taking every p+1 consecutive gas supply volume data adjacent in time as a group.

[0007] In one embodiment, the process of determining the impact degree is as follows: Arrange the collected meteorological data in time sequence to form meteorological sequences; Arrange all the collected gas supply volume data in time sequence to form a gas supply volume sequence; Calculate the correlation coefficient between each meteorological series and the gas supply series; Based on the distribution of the correlation coefficients, the influence of various meteorological data on the gas supply demand is determined.

[0008] In one embodiment, the influence degree is the proportion of each correlation coefficient in the sum of all correlation coefficients.

[0009] In one embodiment, the expression of the theoretical air supply data is: ; In the formula, represents the theoretical gas supply data of the vth gas supply data in the uth group; k represents the type of meteorological data; Indicates the degree of influence of the i-th meteorological data on the gas demand; the i-th meteorological data on the same day as the v-th gas supply data in the u-th group is recorded as I, Represents the average value of the gas supply volume data of all days that are numerically equal to the above I.

[0010] In one embodiment, the confidence is proportional to the order of the remaining data in each group, and inversely proportional to the error of the remaining data.

[0011] In one embodiment, the feasibility is proportional to the confidence and inversely proportional to the error of the last gas supply volume data in each group.

[0012] In one embodiment, the feasibility expression is: ; In the formula, represents the feasibility of the u-th group; norm[] represents the normalization function; Indicates the confidence that the last data in the u-th group can be predicted by the remaining data; Indicates the error of the p+1th gas supply data in the uth group; Indicates a preset value greater than 0.

[0013] In one embodiment, the weighted likelihood function is determined as follows: ; In the formula, represents the weighted likelihood function; n represents the total number of gas supply data; p represents the order of the AR model; express The probability density function of is obtained by predicting the dependent variable formula; Indicates the feasibility of the u-th group; Among them, the expression of the prediction dependent variable formula is: ; In the formula, represents the row vector composed of all data except the last data in the u-th group; θ represents the row vector composed of p unknown autoregressive coefficients; T represents the transposition operation; represents the unknown constant term; Indicates the p+1th gas supply volume data in the uth group.

[0014] In one embodiment, the method for constructing the AR model for predicting gas supply demand is: Based on the weighted likelihood function, the maximum likelihood estimation method is used to obtain the optimal autoregressive coefficient and constant term; The expression of AR model is: ; represents the gas supply data on day t; represents the vth optimal autoregressive coefficient; Indicates the gas supply data for day tv; represents the value of white noise on day t; Represents a constant term.

[0015] This application has at least the following beneficial effects: The present application analyzes the correlation between various meteorological data and gas supply data, determines the degree of influence of various meteorological data on gas supply demand, and highlights the degree of influence of various meteorological data on gas supply demand by comparing the correlation between different types of meteorological data and gas supply; further, combined with the joint effect of various meteorological data on gas supply, calculates the difference between the gas supply actually caused by weather changes and the actual gas supply, so as to avoid the interference of historical gas supply caused by natural disasters or public health emergencies in the process of calculating the autocorrelation coefficient using historical gas supply data; and analyzes the reliability of gas supply data in each group for prediction, and when constructing the likelihood function, weights it according to the reliability, and uses the weighted likelihood function to obtain the optimal autoregressive parameters, thereby improving the accuracy of the calculated autoregressive coefficient; on this basis, constructs an AR model to predict future gas supply demand, thereby improving the accuracy of gas supply demand prediction, and reducing the problem of transformation failure caused by insufficient gas supply or the greater risk of gas storage caused by oversupply. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0017] Figure 1 A flow chart of the steps of a clean heating system load prediction method based on big data provided in this application; Figure 2 Schematic diagram of the process for determining the degree of impact. DETAILED DESCRIPTION

[0018] In the description of the embodiments of the present application, words such as "exemplary", "or", "for example" and the like are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "or", "for example" and the like is intended to present related concepts in a concrete manner.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art in the present application. The terms used in the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. It should be understood that, unless otherwise specified, " / " means or.

[0020] It should also be noted that the terms "first" and "second" in the present application are used to distinguish similar objects rather than to describe a specific order or sequence.

[0021] The following is a detailed description of a specific scheme of a clean heating system load prediction method based on big data provided by the present application in conjunction with the accompanying drawings.

[0022] An embodiment of the present application provides a method for predicting the load of a clean heating system based on big data. Specifically, the following method for predicting the load of a clean heating system based on big data is provided. Figure 1 , the method comprises the following steps: Step 1: Obtain daily gas supply data and various meteorological data for multiple historical days.

[0023] Under the condition of ensuring sufficient gas supply, collect the gas supply volume for each of the consecutive n days including the current day, in units of ; and obtain various meteorological data for each of the n consecutive days including the current day through the weather log of the weather station, including temperature, humidity, wind speed, atmospheric pressure and precipitation, with units of ℃, %, km / h, hPa and mm respectively. Among them, temperature is the average value of all temperatures that appear in a day, humidity is the average value of all humidity that appears in a day, wind speed is the average value of all wind speeds that appear in a day, and atmospheric pressure is the average value of all atmospheric pressures that appear in a day.

[0024] In this embodiment, the value of n is 50. The value of n is preset manually and can be set by the implementer. This application does not impose any special restrictions.

[0025] Step 2: determine the order of the AR model based on the autocorrelation of all the acquired air supply volume data, and group the air supply volume data based on the order.

[0026] Since this application needs to establish an AR model based on historical gas supply data and identify the trend change of gas supply demand through the AR model, the gas supply data needs to be processed as follows before establishing the AR model: (1) Determine the order p of the AR model using the autocorrelation function (ACF) diagram based on the historical gas supply data collected; wherein, determining the order of the AR model using the ACF diagram is a well-known technique and will not be described in detail in this application; (2) Group the gas supply data. Since the order p of the AR model has been determined, the gas supply data of every p days can predict the gas supply demand of the p+1 day. Therefore, the gas supply data of every p+1 consecutive days in time are taken as a group of gas supply data. The example is as follows: ; Among them, there are np groups in total, They are a group respectively. They are the 1st, 2nd, 3rd, pth, p+1th, p+2th, npth, n-p+1th, n-1th, and nth gas supply data respectively.

[0027] Step 3: Analyze the correlation between various meteorological data and gas supply data to determine the impact of various meteorological data on gas supply demand.

[0028] Since the demand for gas supply is closely related to outdoor meteorological conditions, temperature, humidity, wind speed, atmospheric pressure and precipitation affect people's daily activities and comfort in different ways, and therefore have different degrees of impact on the demand for gas supply.

[0029] Since the collected meteorological data are all obtained under the condition of maintaining sufficient gas supply, the stronger the positive correlation between one type of meteorological data and the gas supply data, the greater the impact of this type of meteorological data on the gas supply demand.

[0030] Based on the above analysis, the correlation between various meteorological data and gas supply data is analyzed to determine the influence of various meteorological data on gas supply demand. The expression is: ; In the formula, Indicates the impact of the i-th meteorological data on the gas supply demand; represents the operation of calculating the correlation coefficient; k represents the type of meteorological data, and in this embodiment, k=5; It represents a meteorological sequence composed of all the i-th meteorological data collected in time series; E represents a gas supply sequence composed of all the gas supply data collected in time series; ω represents a constant preset greater than 0, the purpose of which is to avoid the denominator being 0. The value of ω is preset manually and can be set by the implementer. In this embodiment, the value of ω is 0.001.

[0031] In this embodiment, the correlation coefficient between the meteorological sequence and the gas supply sequence is the Pearson correlation coefficient. As other implementation methods, on the basis of being able to measure the correlation between the meteorological sequence and the gas supply sequence, the implementer may adopt other existing technologies to measure the correlation between the meteorological sequence and the gas supply sequence, such as the Spearman correlation coefficient, the Kendall rank correlation coefficient, etc., and this application does not impose any special restrictions.

[0032] It should be noted that the larger the calculated impact value is, the greater the impact of the i-th meteorological data on the gas supply demand is compared with other meteorological data. Figure 2 shown.

[0033] Step 4, based on the distribution of gas supply data on all days with the same meteorological data and combined with the degree of influence, determine the theoretical gas supply data of each gas supply data in each group; based on the difference between each gas supply data in each group and its theoretical gas supply data, determine the error of each gas supply data in each group.

[0034] The core of the change in gas supply demand is to respond to meteorological changes. For each group, each gas supply data in each group may be formed due to the influence of factors such as natural disasters or public health emergencies, and is not obtained by the combined influence of multiple meteorological data. Therefore, it is necessary to calculate the error of each gas supply data relative to the gas supply data actually caused by weather factors.

[0035] Based on the above analysis, it is assumed that the v-th gas supply data in the u-th group is only affected by the i-th meteorological data, and the influence of other meteorological data on the gas supply is temporarily ignored. The day on which the v-th gas supply data in the u-th group is collected is recorded as the a-th day, the i-th meteorological data on the a-th day is recorded as I, and the average value of the gas supply data of all days with the same value as I is recorded as , then the gas supply on day a should be The gas supply volume is equal to the demand volume of various meteorological data, but the gas supply volume is affected by a variety of meteorological data. Therefore, the influence of various meteorological data on the gas supply demand is combined, and the theoretical gas supply volume data caused by meteorological data is obtained by weighting. The expression is: ; In the formula, represents the theoretical gas supply data of the vth gas supply data in the uth group; k represents the type of meteorological data; Indicates the impact of the i-th meteorological data on the gas supply demand; Represents the average value of the gas supply volume data of all days that are numerically equal to the above I.

[0036] Furthermore, the difference between each gas supply volume data in each group and its theoretical gas supply volume data is taken as the error of each gas supply volume data in each group.

[0037] In this embodiment, the difference between each gas supply volume data and its theoretical gas supply volume data is the absolute value of the difference. As other implementation methods, on the basis of being able to measure the difference between each gas supply volume data and its theoretical gas supply volume data, the implementer may adopt other calculation methods for measurement, such as ratio, square of difference, etc., and this application does not impose any special restrictions.

[0038] Step 5: Based on the error and order of each gas supply volume data in each group, determine the confidence that the preset position data in each group can be predicted by the remaining data.

[0039] For the p+1 gas supply volume data in each group, in order to make the first p gas supply volume data can accurately predict the p+1th gas supply volume data, the error of the first p gas supply volume data should be as small as possible, and on this basis, since there is autocorrelation between the gas supply volume data, that is, the gas supply volume data of any day is related to the gas supply volume data of the previous day or days, the closer the gas supply volume data among the first p gas supply volume data is to the p+1th gas supply volume data in time, the more correlated it is with the p+1th gas supply volume data.

[0040] Based on the above analysis, based on the order and error of each gas supply volume data in each group, the confidence that the last data in each group can be predicted by the remaining data is determined, and the expression is: ; represents the confidence that the last data in the u-th group can be predicted by the remaining data; p represents the order of the AR model; v represents the order of the gas supply data in the group; represents the error of the vth gas supply data in the uth group; norm[] represents the normalization function; Indicates that the value is preset to be greater than 0, in order to avoid the denominator being 0. The value of is preset by humans and can be set by the implementer. The value of is 0.001.

[0041] In this embodiment, the Min-Max normalization method is used to Normalization is performed, as another implementation method, in which On the basis of normalization processing, the implementer may adopt other existing technologies, such as Z-Score normalization method, decimal calibration normalization method, etc., and this application does not impose any special restrictions.

[0042] It should be noted that: when calculating the confidence, v is used as a weight, and a higher weight is assigned to the gas supply volume data that is closer in time to the p+1th gas supply volume data.

[0043] Step 6: Determine the feasibility of each grouping based on the confidence level and the error of the gas supply volume data of the preset position in each grouping.

[0044] This application uses all groups to calculate the autoregressive coefficient and constant term of the AR model, analyzes each group, and uses the first p gas supply data to predict the p+1th gas supply data. If the p+1th gas supply data is caused by weather factors, the error of the p+1th gas supply data is small. Since the p+1th gas supply data can be regarded as the prediction result of the first p gas supply data, if this group of gas supply data is feasible in data prediction, then on the basis of the small error of the prediction result, the confidence that the p+1th gas supply data can be predicted by the first p gas supply data should also be high.

[0045] Based on the above analysis, the feasibility of each grouping is determined based on the confidence that the last data in each grouping can be predicted by the remaining data, and the error of the last gas supply data. The expression is: ; In the formula, represents the feasibility of the u-th group; norm[] represents the normalization function; Indicates the confidence that the last data in the u-th group can be predicted by the remaining data; Indicates the error of the p+1th gas supply data in the uth group; Indicates that the value is preset to be greater than 0, in order to avoid the denominator being 0. The value of is preset by humans and can be set by the implementer. The value of is 0.001.

[0046] In this embodiment, the Min-Max normalization method is used to Normalization is performed, as another implementation method, in which On the basis of normalization processing, the implementer may adopt other existing technologies, such as Z-Score normalization method, decimal calibration normalization method, etc., and this application does not impose any special restrictions.

[0047] Step 7, comprehensively considering the gas supply volume data in all groups and the feasibility, and determining a weighted likelihood function; and constructing an AR model for predicting gas supply demand based on the likelihood function.

[0048] For each group, the first p gas supply data can be used as an independent variable for a prediction sample, and the p+1th gas supply data can be used as a dependent variable for a prediction sample. The independent variable and the p unknown autoregression coefficients , and the unknown constant term μ can be combined to form a prediction formula for the dependent variable, expressed as: ; In the formula, Represents a row vector consisting of all data except the last data in the u-th group. The specific expression is ,in They represent the first, second, and pth gas supply data in the uth group respectively; θ represents a row vector composed of p unknown autoregressive coefficients. The specific expression is: ,in Respectively represent the first, second, and pth autoregressive coefficients; T represents the transposition operation; Indicates the p+1th gas supply data in the uth group; represents the unknown constant term; p represents the order of the AR model.

[0049] The existing technology generally adopts The likelihood function is constructed by the method of represents the likelihood function; n represents the total number of gas supply data; p represents the order of the AR model; express The probability density function of is obtained by predicting the dependent variable formula; however, this method of constructing the likelihood function essentially regards the feasibility of different groups as the same, but the feasibility of different groups obtained through calculation is different. In order to make the contribution of the group with higher feasibility higher and the contribution of the group with lower feasibility lower, in the process of determining multiple unknown parameters using the maximum likelihood estimation method, the likelihood function can be constructed by the weighted method to achieve parameter optimization.

[0050] Based on the above analysis, the feasibility of each group and the prediction dependent variable formula, the weighted likelihood function is determined, and the expression is: ; In the formula, represents the weighted likelihood function; n represents the total number of gas supply data; p represents the order of the AR model; express The probability density function of is obtained by predicting the dependent variable formula; It indicates the feasibility of the u-th group. It is a well-known technology to obtain the probability density function by predicting the dependent variable formula, which will not be described in detail in this application.

[0051] The partial derivative of the weighted likelihood function is calculated, and the optimal autoregressive coefficient and constant term are obtained by solving the equations using the gradient descent method. The calculation of the partial derivative and the solution of the equations using the gradient descent method are both well-known techniques and will not be described in detail in this application.

[0052] According to the optimal autoregressive coefficient, constant term and random disturbance term, the AR model is constructed, and the expression is: ; represents the gas supply data on day t; represents the constant term; p represents the order of the AR model; represents the vth optimal autoregressive coefficient; Indicates the gas supply data for day tv; represents the value of white noise on the tth day, where white noise is a random disturbance term.

[0053] The AR model is used to predict future gas supply based on historical gas supply data. With the predicted gas supply, gas supply companies can dynamically adjust gas supply strategies based on real-time changes, plan and manage supply chains in advance, reduce transformation failures caused by insufficient supply or greater gas storage risks caused by oversupply, and enable the city's actively promoted clean heating transformation goals to be achieved smoothly.

[0054] To summarize, the present application analyzes the correlation between various meteorological data and gas supply data, determines the degree of influence of various meteorological data on gas supply demand, and highlights the degree of influence of various meteorological data on gas supply demand by comparing the correlation between different types of meteorological data and gas supply; further, combined with the joint effect of various meteorological factors on gas supply, the difference between the gas supply actually caused by weather changes and the actual gas supply is calculated to avoid interference from historical gas supply caused by factors such as natural disasters or public health emergencies in the process of calculating the autocorrelation coefficient using historical gas supply data; and analyzes the reliability of gas supply data in each group for prediction. When constructing the likelihood function, it is weighted according to the reliability, and the weighted likelihood function is used to obtain the optimal autoregressive parameters, thereby improving the accuracy of the calculated autoregressive coefficient; on this basis, an AR model is constructed to predict future gas supply demand, thereby improving the accuracy of gas supply demand prediction and reducing the problem of transformation failure caused by insufficient gas supply or greater gas storage risk caused by oversupply.

[0055] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

[0056] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the basic features of the present application. Therefore, no matter from which point of view, the above embodiments of the present application should be regarded as exemplary and non-restrictive.

Claims

1. A clean heating system load prediction method based on big data, characterized in that: The method comprises the following steps: Obtain daily gas supply data and various meteorological data for multiple historical days; Determine the order of the AR model based on the autocorrelation of all the acquired air supply volume data, and group the air supply volume data based on the order; Analyze the correlation between various meteorological data and gas supply data, and determine the impact of various meteorological data on gas supply demand; Based on the distribution of the air supply data on all days with the same meteorological data, and in combination with the degree of influence, determine the theoretical air supply data of each air supply data in each group; based on the difference between each air supply data in each group and its theoretical air supply data, determine the error of each air supply data in each group; Based on the errors and order of each gas supply volume data in each group, determining the confidence that the preset position data in each group can be predicted by the remaining data; Determining the feasibility of each grouping based on the confidence level and the error of the gas supply volume data of the preset position in each grouping; The gas supply volume data in all groups and the feasibility are comprehensively considered to determine a weighted likelihood function; and an AR model for predicting gas supply demand is constructed based on the likelihood function.

2. A clean heating system load prediction method based on big data as claimed in claim 1, characterized in that: The method for grouping the gas supply volume data is: using the autocorrelation function graph to determine the order p of the AR model, and taking each p+1 consecutive gas supply volume data in time as a group.

3. A clean heating system load prediction method based on big data as claimed in claim 1, characterized in that: The process of determining the degree of impact is as follows: Arrange the collected meteorological data in time sequence to form meteorological sequences; Arrange all the collected gas supply volume data in time sequence to form a gas supply volume sequence; Calculate the correlation coefficient between each meteorological series and the gas supply series; Based on the distribution of the correlation coefficients, the influence of various meteorological data on the gas supply demand is determined.

4. A method for predicting clean heating system load based on big data as claimed in claim 3, characterized in that: The influence degree is the proportion of each correlation coefficient in the sum of all correlation coefficients.

5. The method for load prediction of clean heating system based on big data according to claim 1, characterized in that: The expression of the theoretical air supply data is: ; In the formula, represents the theoretical gas supply data of the vth gas supply data in the uth group; k represents the type of meteorological data; Indicates the degree of influence of the i-th meteorological data on the gas demand; the i-th meteorological data on the same day as the v-th gas supply data in the u-th group is recorded as I, Represents the average value of the gas supply volume data of all days that are numerically equal to the above I.

6. A clean heating system load prediction method based on big data as claimed in claim 1, characterized in that: The confidence level is proportional to the order of the remaining data in each group, and inversely proportional to the error of the remaining data.

7. A clean heating system load prediction method based on big data as claimed in claim 1, characterized in that: The feasibility is proportional to the confidence and inversely proportional to the error of the last gas supply volume data in each group.

8. A method for predicting clean heating system load based on big data as claimed in claim 7, characterized in that: The feasibility expression is: ; In the formula, represents the feasibility of the u-th group; norm[] represents the normalization function; Indicates the confidence that the last data in the u-th group can be predicted by the remaining data; Indicates the error of the p+1th gas supply data in the uth group; Indicates a preset value greater than 0.

9. A clean heating system load prediction method based on big data as claimed in claim 1, characterized in that: The determination process of the weighted likelihood function is: ; In the formula, represents the weighted likelihood function; n represents the total number of gas supply data; p represents the order of the AR model; express The probability density function of is obtained by predicting the dependent variable formula; Indicates the feasibility of the u-th group; Among them, the expression of the prediction dependent variable formula is: ; In the formula, represents the row vector composed of all data except the last data in the u-th group; θ represents the row vector composed of p unknown autoregressive coefficients; T represents the transposition operation; represents the unknown constant term; Indicates the p+1th gas supply volume data in the uth group.

10. A clean heating system load prediction method based on big data as claimed in claim 9, characterized in that: The method for constructing the AR model for predicting gas supply demand is: Based on the weighted likelihood function, the maximum likelihood estimation method is used to obtain the optimal autoregressive coefficient and constant term; The expression of AR model is: ; represents the gas supply data on day t; represents the vth optimal autoregressive coefficient; Indicates the gas supply data for day tv; represents the value of white noise on day t; Represents a constant term.

Images