A multi-energy coupling heating control system and intelligent scheduling method

Abstract

The present invention discloses a multi-energy coupling heating control system and intelligent scheduling method, including: collecting temperature data, drawing a dynamic width histogram, determining the probability density of data in each dimension, determining the first abnormal degree of the temperature data at the current moment according to the probability density; determining the second abnormal degree of the temperature data at the current moment; correcting the first abnormal degree according to the second abnormal degree to obtain a comprehensive abnormal degree; correcting the temperature data at the current moment according to the comprehensive abnormal degree, determining the heat demand according to the corrected temperature data, and selecting a heating mode for heating. The present invention has an excellent correction effect on temperature data, eliminates the interference of abnormal temperature data on heat demand calculation, and can improve the accuracy of heating system scheduling.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology. More specifically, the present invention relates to a multi-energy coupling heating control system and an intelligent scheduling method. Background Art

[0002] The temperature data in the heating system directly affects the heating effect and energy consumption. The temperature data collected by the sensor may be affected by various factors such as electromagnetic interference and may be abnormal. Therefore, it is necessary to correct the collected temperature data to prevent abnormal temperature data from interfering with the selection of heating methods and affecting the heating effect.

[0003] Exponential smoothing method can realize the correction of temperature data to a certain extent, but the smoothing coefficient in exponential smoothing method is set manually. When the smoothing coefficient is set too large, the correction effect on abnormal data is poor. When the smoothing coefficient is set too small, it may be over-corrected, affecting the accuracy of the correction result, thereby affecting the choice of heating method and causing the heating effect to deteriorate. Summary of the invention

[0004] To solve the technical problem that improper setting of the smoothing coefficient of the above-mentioned exponential smoothing method affects the heating effect, the present invention provides solutions in the following aspects.

[0005] In a first aspect, the present invention provides a multi-energy coupled heating intelligent scheduling method, comprising:

[0006] Collect temperature data, including ambient temperature, outlet water temperature of the heating system, and return water temperature;

[0007] Draw a dynamic width histogram of each dimension of the temperature data, and determine the probability density of the data of each dimension of the temperature data at the current moment according to the dynamic width histogram;

[0008] Determine a first abnormality degree of the temperature data at the current moment according to the probability density, so as to reflect the abnormality of the temperature data at the current moment in terms of value, wherein the probability density is negatively correlated with the first abnormality degree;

[0009] Determine the second abnormality degree of the temperature data at the current moment, so as to reflect the abnormality of the temperature data at the current moment in terms of time series;

[0010] The first abnormality degree is corrected according to the second abnormality degree to obtain a comprehensive abnormality degree, and the comprehensive abnormality degree is positively correlated with the first abnormality degree and the second abnormality degree;

[0011] The temperature data at the current moment is corrected according to the comprehensive abnormality degree, the heat demand is determined according to the corrected temperature data, and the heating method is selected for heating.

[0012] Preferably, the step of drawing a dynamic width histogram of each dimension of the temperature data comprises:

[0013] For any dimension of the temperature data, sort the data of that dimension from small to large according to the value size, and then The data is divided into a group. During the division process, if the number of data in the group is full , but the value of the next data is equal to the last data in the group, then the next data is added to the group. At this time, the number of the group is allowed to be greater than ,in is the preset first quantity, is the preset second quantity, is the rounding symbol;

[0014] Each group corresponds to a box in the dynamic width histogram. The width of the box is determined by the minimum and maximum values ​​in the group. The number of data contained in each group is used as the area of ​​the box, and the ratio of the area of ​​the box to the width of the box is used as the height of the box to represent the density and realize the drawing of the dynamic width histogram.

[0015] Preferably, determining the probability density of each dimension of the temperature data at the current moment according to the dynamic width histogram includes:

[0016] The ratio of the height of the box to which the data of each dimension in the temperature data at the current moment belongs in the corresponding dynamic width histogram to the height of the highest box in the dynamic width histogram is used as the probability density of the data of each dimension in the temperature data at the current moment.

[0017] Preferably, the first abnormality degree satisfies the expression:

[0018] ;

[0019] in, Indicates the first abnormality level of the temperature data at the current moment, Indicates the temperature data at the current moment. The probability density of the data in the dimension; The number of dimensions representing the temperature data.

[0020] Preferably, the first abnormality degree satisfies the expression:

[0021] ;

[0022] in, Indicates the first abnormality level of the temperature data at the current moment, Indicates the temperature data at the current moment. The probability density of the data in the dimension; Represents the number of dimensions of temperature data; Indicates the temperature data at the current moment. Data of dimensions; Indicates the temperature data at the current moment. The data of the dimension is The smallest value in the box in the dynamic width histogram of the dimension; Indicates the temperature data at the current moment. The data of the dimension is The maximum value in the box in the dynamic width histogram of the dimension. Represents the minimum function.

[0023] Preferably, the second abnormality degree satisfies the expression:

[0024] ;

[0025] in, Indicates the second abnormality level of the temperature data at the current moment; is a preset third quantity; Indicates the temperature data at the current moment. The data of the dimension is The ordinal number of the box in the dynamic width histogram of the dimension; Indicates the number before the current time. The temperature data at the moment The data of the dimension is The ordinal number of the box in the dynamic width histogram of the dimension; Indicates the sequence number of the time before the current time; represents a preset second quantity; Indicates the absolute value symbol; The number of dimensions representing the temperature data.

[0026] Preferably, the comprehensive abnormality degree satisfies the expression:

[0027] ;

[0028] in, Indicates the comprehensive abnormality of the temperature data at the current moment; Indicates the first abnormality level of the temperature data at the current moment; Indicates the second abnormality level of the temperature data at the current moment; represents the hyperbolic tangent function; Represents an exponential function with a natural constant as its base.

[0029] Preferably, the correcting of the temperature data at the current moment according to the comprehensive abnormality degree includes:

[0030] The difference between 1 and the comprehensive abnormality level is used as the smoothing coefficient; the most recent The temperature data at each moment is taken as the data sample, and the smoothing coefficient is used to calculate the temperature of the sample. , use the exponential smoothing method to perform exponential smoothing on the data samples, obtain the predicted value of the temperature data at the current moment, and use the predicted value as the correction result of the temperature data at the current moment, where is the preset first quantity.

[0031] Preferably, determining the heat demand according to the corrected temperature data and selecting a heating mode for heating includes:

[0032] The heat demand is calculated based on the outlet water temperature and return water temperature in the temperature data corrected at the current moment; the ambient temperature in the temperature data corrected at the current moment is compared with the set defrost temperature. When the ambient temperature is not higher than the set defrost temperature, the gas equipment is called first. Otherwise, the natural gas cost and electricity cost required to meet the heat demand are calculated based on COP, ambient temperature, electricity price, natural gas price, and natural gas calorific value. When the electricity cost is less than the natural gas cost, the heat pump equipment is called first. When the electricity cost is not less than the natural gas cost, the gas equipment is called first.

[0033] In a second aspect, the present invention provides a multi-energy coupling heating control system, comprising a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned multi-energy coupling heating intelligent scheduling method is implemented.

[0034] By adopting the above technical solution, the above-mentioned multi-energy coupling heating intelligent scheduling method is generated into a computer program and stored in a memory so as to be loaded and executed by a processor, thereby making a terminal device based on the memory and the processor for easy use.

[0035] The beneficial effects of the present invention are:

[0036] The present invention uses the first abnormality degree to reflect the abnormality of the temperature data at the current moment in terms of value, uses the second abnormality degree to reflect the abnormality of the temperature data at the current moment in terms of time series, and corrects the first abnormality degree by the second abnormality degree, so that the obtained comprehensive abnormality degree is more accurate. The temperature data is corrected by setting the smoothing coefficient of the exponential smoothing method by using the comprehensive abnormality degree, which can ensure that the correction degree of abnormal temperature data is large, the correction degree of normal temperature data is small, and the correction result is more accurate, avoiding the influence of the accuracy of the correction result by improper setting of the smoothing coefficient. Selecting the heating mode for heating according to the correction result can reduce the operating cost of the heating system under the premise of satisfying stable and continuous heating. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The above and other purposes, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the detailed description below through the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0038] Figure 1 is a flow chart schematically illustrating a multi-energy coupled heating intelligent scheduling method in the present invention;

[0039] Figure 2 is a flow chart schematically illustrating step S2;

[0040] Figure 3 is a histogram schematically showing the dynamic width of the ambient temperature;

[0041] Figure 4 is a flowchart schematically showing step S3. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0043] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0044] The embodiment of the present invention discloses a multi-energy coupled heating intelligent scheduling method, referring to Figure 1 , including steps S1 to S3:

[0045] S1. Collect temperature data at every moment, including ambient temperature, outlet water temperature of the heating system, and return water temperature.

[0046] It should be noted that the water supply temperature in the heating system refers to the temperature of the hot water delivered from the heat source, and the return water temperature refers to the temperature of the hot water returned from the heating equipment to the heat source. The water supply temperature, return water temperature, and ambient temperature directly affect the heating effect and energy consumption. Therefore, the present invention collects the ambient temperature, water supply temperature, and return water temperature at each moment to calculate the heat demand.

[0047] Specifically, temperature sensors are installed at the outlet and return outlet of the heating system to collect the outlet and return water temperatures. Temperature sensors are installed outdoors to collect ambient temperature. The frequency of collecting the outlet, return and ambient temperatures is consistent and is set by the implementation personnel according to the actual implementation situation. There is no specific limit, for example, once every 5 minutes.

[0048] The ambient temperature, outlet water temperature and return water temperature at the same moment constitute the temperature data at that moment. Thus, the collection of temperature data at each moment is realized.

[0049] S2. Correct the temperature data at the current moment.

[0050] It should be noted that due to the influence of various factors such as electromagnetic interference and radio frequency interference, the collected temperature data may be abnormal. Directly calculating the heat demand based on the collected temperature data may lead to inaccurate results and affect the heating effect. Therefore, the present invention makes an abnormal judgment on the collected temperature data and corrects the abnormal temperature data to obtain accurate heat demand data to ensure the heating effect.

[0051] Specifically, the flowchart of step S2 is as follows: Figure 2 , including steps S201 to S206, specifically:

[0052] S201. Draw a dynamic width histogram of each dimension of the temperature data.

[0053] It should be noted that the temperature data includes three dimensions: ambient temperature, outlet water temperature, and return water temperature. The present invention takes ambient temperature as an example to illustrate a method for obtaining a dynamic width histogram of each dimension of temperature data.

[0054] Specifically, the most recent The ambient temperatures at each moment are sorted in ascending order. The ambient temperatures are divided into a group. During the division process, if the number of ambient temperatures in the group is full , but the next ambient temperature is equal to the value of the last ambient temperature in the group, then the next ambient temperature is added to the group. At this time, the number of groups allowed to be greater than .in is the preset first quantity, is the preset second quantity, The first quantity and the second quantity are set by the implementer according to the actual implementation situation, for example , .

[0055] Draw a dynamic width histogram based on all the groups obtained by division, specifically:

[0056] Each group corresponds to a box in the dynamic width histogram. The width of the box is determined by the minimum and maximum values ​​in the group, that is, the starting position of the box is the minimum value in the group, and the ending position of the box is the maximum value in the group. The number of ambient temperatures contained in each group is used as the area of ​​the box, and the ratio of the area of ​​the box to the width of the box is used as the height of the box to represent the density, thereby realizing the drawing of the dynamic width histogram.

[0057] For example, when , , when the most recent 20 ambient temperatures are sorted in ascending order as -1℃, -1℃, -1℃, -1℃, 0℃, 1℃, 1℃, 1℃, 1℃, 1℃, 2℃, 2℃, 2℃, 3℃, 4℃, 4℃, 4℃, 4℃, 6℃, 7℃, the first group is -1℃, -1℃, -1℃, -1℃, the second group is 0℃, 1℃, 1℃, 1℃, 1℃, 1℃, the third group is 2℃, 2℃, 2℃, 3℃, the fourth group is 4℃, 4℃, 4℃, 4℃, and the fifth group is 6℃, 7℃. See the dynamic width histogram for details. Figure 3 .

[0058] At this point, the drawing of the dynamic width histogram of the ambient temperature is achieved.

[0059] Similarly, the dynamic width histogram of the outflow water temperature and the dynamic width histogram of the return water temperature are drawn respectively.

[0060] S202: Determine the probability density of the data in each dimension of the temperature data at the current moment according to the dynamic width histogram of each dimension.

[0061] Specifically, the probability density of the data in each dimension of the temperature data at the current moment satisfies the expression:

[0062] ;

[0063] in, Indicates the temperature data at the current moment. The probability density of the data in the dimension; Indicates the temperature data at the current moment. The data of the dimension is The height of the box in the dynamic width histogram of the dimension, Indicates The height of the highest box in the dynamic width histogram of the dimension. The height of each box in the dynamic width histogram can reflect the density of the data. Dividing the height of the box by the height of the highest box can ensure that the probability density is not greater than 1.

[0064] S203: Determine a first abnormality level of the temperature data at the current moment, so as to reflect the abnormality of the value of the temperature data at the current moment.

[0065] In one embodiment, the first abnormality degree of the temperature data at the current moment satisfies the expression:

[0066] ;

[0067] in, Indicates the first abnormality level of the temperature data at the current moment, Indicates the temperature data at the current moment. The probability density of the data in the dimension; Represents the number of dimensions of the temperature data, which is 3 in the present invention; if the probability density of the data of a certain dimension of the temperature data at the current moment is smaller, it means that the data of the dimension at the current moment is independent of the distribution of the data of the dimension at other moments, the data of the dimension at the current moment is numerically different from other data, and the temperature data at the current moment is relatively abnormal; if the probability density of the data of a certain dimension of the temperature data at the current moment is larger, it means that the data of the dimension at the current moment is concentratedly distributed with the data of the dimension at other moments, and the data of the dimension at the current moment is numerically different from other data; if the probability density of the data of all dimensions of the temperature data at the current moment is larger, the temperature data at the current moment is more normal.

[0068] In another embodiment, the first abnormality degree of the temperature data at the current moment satisfies the expression:

[0069] ;

[0070] in, Indicates the first abnormality level of the temperature data at the current moment, Indicates the temperature data at the current moment. The probability density of the data in the dimension; Indicates the number of dimensions of temperature data, which is 3 in the present invention; Indicates the temperature data at the current moment. Data of dimensions; Indicates the temperature data at the current moment. The data of the dimension is The smallest value in the box in the dynamic width histogram of the dimension; Indicates the temperature data at the current moment. The data of the dimension is The maximum value in the box in the dynamic width histogram of the dimension. Represents the minimum function. Indicates the temperature data at the current moment. The data of the dimension is The width of the bins in the dynamic width histogram of the dimension, Used for Normalize.

[0071] , Respectively represent the temperature data at the current moment The distance from the data of the dimension to the left and right boundaries of the box to which it belongs. , The purpose of adding one is to prevent the exponent from being 0. The closer the data of a dimension is to any boundary of the box to which it belongs, the closer the temperature data of the current moment is to any boundary of the box to which it belongs. The closer the data in the first dimension is to the value in the previous box or the next box, the closer the temperature data at the current moment is. The worse the grouping effect of the data in the previous grouping, the worse the grouping effect of the data in the current temperature data. The probability density of the data in one dimension is less accurate, so the present invention adopts Probability density To make corrections, if the current temperature data The closer the data of a dimension is to any boundary of the box to which it belongs, The smaller the probability density The greater the degree of correction; if the current temperature data The farther the data of a dimension is from the left and right boundaries of the box to which it belongs, The larger the probability density The smaller the degree of correction.

[0072] S204: Determine a second abnormality level of the temperature data at the current moment, to reflect the abnormality of the temperature data at the current moment in terms of time series.

[0073] It should be noted that since the temperature changes gradually rather than suddenly, we should consider not only the numerical anomaly of the temperature data, but also the anomaly of the temperature data in time series.

[0074] Specifically, the second abnormality degree of the temperature data at the current moment satisfies the expression:

[0075] ;

[0076] in, Indicates the second abnormality level of the temperature data at the current moment; It is the preset third quantity, which can be set by the implementer according to the actual implementation situation, for example ; Indicates the temperature data at the current moment. The data of the dimension is The ordinal number of the box in the dynamic width histogram of the dimension; Indicates the number before the current time. The temperature data at the moment The data of the dimension is The ordinal number of the box in the dynamic width histogram of the dimension; Indicates the sequence number of the time before the current time; Indicates the preset second quantity, Used to limit the second abnormality degree to the range of [0,1]; Indicates the absolute value symbol; The number of dimensions representing the temperature data.

[0077] Indicates the current time and the number before the current time The temperature data at the moment The smaller the difference is, the closer the current moment is to the box before the current moment. The temperature data at the moment The more continuous the data in the dimension is in time series, the The more normal the data of the dimension is, the greater the difference is. The temperature data at the moment The more discontinuous the data in the dimension is, the more discontinuous the temperature data at the current moment is. The more abnormal the data in each dimension is.

[0078] Indicates the number before the current time. The weight of the temperature data at a moment The smaller the value, the The smaller the difference between the previous moment and the current moment, The larger the value, the The greater the weight of the temperature data at a moment, the more attention is paid to the current moment and the temperature data before the current moment. The temperature data at the moment The difference between the boxes to which the data on the dimension belongs; on the contrary, the The greater the difference between the previous moment and the current moment, The smaller the value, the The smaller the weight of the temperature data at a moment, the less attention is paid to the current moment and the temperature data before the moment. The temperature data at the moment The difference between the boxes to which the data belongs in the dimensions. The moment The second abnormality degree of the temperature data at the current moment is obtained by calculating the difference between the boxes to which the data in each dimension belongs.

[0079] S205: Correct the first abnormality level according to the second abnormality level to determine the comprehensive abnormality level of the temperature data at the current moment.

[0080] Specifically, the comprehensive abnormality of the temperature data at the current moment satisfies the expression:

[0081] ;

[0082] in, Indicates the comprehensive abnormality of the temperature data at the current moment; Indicates the first abnormality level of the temperature data at the current moment; Indicates the second abnormality level of the temperature data at the current moment; represents the hyperbolic tangent function; Represents an exponential function with a natural constant as its base.

[0083] The first abnormality degree reflects the numerical abnormality of the temperature data at the current moment, and the second abnormality degree reflects the temporal abnormality of the temperature data at the current moment. When the second abnormality degree is larger, the correction to the first abnormality degree is larger, so that the comprehensive abnormality degree increases on the basis of the first abnormality degree; conversely, when the second abnormality degree is smaller, the correction to the first abnormality degree is smaller, so that the comprehensive abnormality degree depends more on the size of the first abnormality degree.

[0084] S206. Correct the temperature data at the current moment according to the comprehensive abnormality degree.

[0085] Specifically, the smoothing coefficient is obtained according to the comprehensive abnormality of the temperature data at the current moment:

[0086] ;

[0087] in, represents the smoothing coefficient, It indicates the comprehensive abnormality degree of the temperature data at the current moment. If the comprehensive abnormality degree of the temperature data at the current moment is smaller, it means that the temperature data at the current moment is more normal. At this time, the larger the smoothing coefficient is, and the subsequent correction value of the temperature data according to the smoothing coefficient will refer to the temperature data at the current moment more; if the comprehensive abnormality degree of the temperature data at the current moment is larger, it means that the temperature data at the current moment is more abnormal. At this time, the smaller the smoothing coefficient is, and the subsequent correction value of the temperature data according to the smoothing coefficient will refer to the temperature data before the current moment more.

[0088] The most recent The temperature data at each moment is taken as the data sample, and the smoothing coefficient is used to calculate the temperature of the sample. , use the exponential smoothing method to perform exponential smoothing on the data samples, obtain the predicted value of the temperature data at the current moment, and use the predicted value as the correction result of the temperature data at the current moment.

[0089] S3. Determine the heat demand according to the corrected temperature data, and select a heating method to supply heat according to the heat demand.

[0090] Specifically, the flowchart of step S3 is as follows: Figure 4 , including steps S301 to S310, specifically:

[0091] S301, calculating the heat demand according to the outlet water temperature and return water temperature in the temperature data corrected at the current moment. The heat demand calculation formula is a well-known technology and will not be described in detail here.

[0092] S302, compare the ambient temperature in the corrected temperature data at the current moment with the set defrost temperature. If the ambient temperature is higher than the set defrost temperature, it is determined that the current environment is not low temperature, the heat pump equipment does not need frequent defrosting, and will not cause the heat pump equipment efficiency to decrease. In the case of insufficient heating, the heat pump equipment can be called at any time, and enter S303. If the ambient temperature is not higher than the set defrost temperature, it is determined that the current environment is low temperature, the heat pump equipment needs frequent defrosting, which will cause the heat pump equipment efficiency to decrease, insufficient heating, and gas equipment will be called first, and enter S308. The defrost temperature is set by the implementer according to the actual implementation situation, and there is no specific limit, such as 0°C.

[0093] S303, obtain parameters such as natural gas price, electricity price, natural gas calorific value, and energy efficiency ratio (Coefficient of Performance, COP) of heat pump equipment. COP indicates how many units of effective energy output can be generated by inputting 1 unit of energy. According to COP, ambient temperature, electricity price, natural gas price, natural gas calorific value and other parameters, calculate the cost of a single energy (natural gas or electricity) required to meet the same heat demand.

[0094] S304: Compare the two different energy costs with the single energy cost calculated in S303. When the electricity cost is less than the natural gas cost, the heat pump equipment is called first, and the process goes to S305. When the electricity cost is not less than the natural gas cost, the gas equipment is called first, and the process goes to S308.

[0095] S305. According to the group control logic, by comparing the heat demand with the heat supply of a single heat pump device, the number of heat pump devices is increased or decreased until the total heat demand is met or all heat pump devices are put into use, and the use time of each heat pump device is balanced.

[0096] S306. After all the heat pump equipment is put into operation, determine whether there is a heat gap. If there is a heat gap, proceed to S307.

[0097] S307, calling the gas equipment, according to the group control logic, by comparing the heat gap and the heat supply of a single gas equipment, increase or decrease the number of gas equipment until the total heat demand is met and the use time of each gas equipment is balanced.

[0098] S308, calling the gas equipment, according to the group control logic, by comparing the heat demand and the heat supply of a single gas equipment, increase the number of gas equipment until the total heat demand is met or all gas equipment is put into use, and balance the use time of each gas equipment.

[0099] S309: After all gas equipment is put into operation, determine whether there is a heat gap. If there is a heat gap, proceed to S310.

[0100] S310, calling the heat pump equipment, according to the group control logic, by comparing the heat gap and the heat supply of a single heat pump equipment, increase or decrease the number of heat pump equipment until the total heat demand is met and the use time of each heat pump equipment is balanced.

[0101] An embodiment of the present invention further discloses a multi-energy coupling heating control system, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a multi-energy coupling heating intelligent scheduling method according to the present invention is implemented.

[0102] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0103] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0104] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. A multi-energy coupled heating intelligent scheduling method, characterized in that: include: Collect temperature data, including ambient temperature, outlet water temperature of the heating system, and return water temperature; Draw a dynamic width histogram of each dimension of the temperature data, and determine the probability density of the data of each dimension of the temperature data at the current moment according to the dynamic width histogram; Determine a first abnormality degree of the temperature data at the current moment according to the probability density, so as to reflect the abnormality of the temperature data at the current moment in terms of value, wherein the probability density is negatively correlated with the first abnormality degree; Determine the second abnormality degree of the temperature data at the current moment, so as to reflect the abnormality of the temperature data at the current moment in terms of time series; The second abnormality degree satisfies the expression: ； in, Indicates the second abnormality level of the temperature data at the current moment; is a preset third quantity; Indicates the temperature data at the current moment. The data of the dimensions are The ordinal number of the box in the dynamic width histogram of the dimension; Indicates the number before the current time. The temperature data at the moment The data of the dimension is The ordinal number of the box in the dynamic width histogram of the dimension; Indicates the sequence number of the time before the current time; represents a preset second quantity; Indicates the absolute value symbol; Represents the number of dimensions of temperature data; The first abnormality degree is corrected according to the second abnormality degree to obtain a comprehensive abnormality degree, and the comprehensive abnormality degree is positively correlated with the first abnormality degree and the second abnormality degree; The temperature data at the current moment is corrected according to the comprehensive abnormality degree, the heat demand is determined according to the corrected temperature data, and the heating method is selected for heating.

2. A multi-energy coupled heating intelligent scheduling method according to claim 1, characterized in that: The dynamic width histogram of each dimension of the temperature data is drawn, including: For any dimension of the temperature data, sort the data of that dimension from small to large according to the value size, and then The data is divided into a group. During the division process, if the number of data in the group is full , but the value of the next data is equal to the last data in the group, then the next data is added to the group. At this time, the number of the group is allowed to be greater than ,in is the preset first quantity, is the preset second quantity, is the rounding symbol; Each group corresponds to a box in the dynamic width histogram. The width of the box is determined by the minimum and maximum values ​​in the group. The number of data contained in each group is used as the area of ​​the box, and the ratio of the area of ​​the box to the width of the box is used as the height of the box to represent the density and realize the drawing of the dynamic width histogram.

3. The multi-energy coupled heating intelligent scheduling method according to claim 1 is characterized in that: Determining the probability density of each dimension of the temperature data at the current moment according to the dynamic width histogram includes: The ratio of the height of the box to which the data of each dimension in the temperature data at the current moment belongs in the corresponding dynamic width histogram to the height of the highest box in the dynamic width histogram is used as the probability density of the data of each dimension in the temperature data at the current moment.

4. The multi-energy coupled heating intelligent scheduling method according to claim 1 is characterized in that: The first abnormality degree satisfies the expression: ； in, Indicates the first abnormality level of the temperature data at the current moment, Indicates the temperature data at the current moment. The probability density of the data in the dimension; The number of dimensions representing the temperature data.

5. The multi-energy coupled heating intelligent scheduling method according to claim 1 is characterized in that: The first abnormality degree satisfies the expression: ； in, Indicates the first abnormality level of the temperature data at the current moment, Indicates the temperature data at the current moment. The probability density of the data in the dimension; Represents the number of dimensions of temperature data; Indicates the temperature data at the current moment. Data of dimensions; Indicates the temperature data at the current moment. The data of the dimension is The smallest value in the box in the dynamic width histogram of the dimension; Indicates the temperature data at the current moment. The data of the dimension is The maximum value in the box in the dynamic width histogram of the dimension. Represents the minimum function.

6. The multi-energy coupled heating intelligent scheduling method according to claim 1 is characterized in that: The comprehensive abnormality degree satisfies the expression: ； in, Indicates the comprehensive abnormality of the temperature data at the current moment; Indicates the first abnormality level of the temperature data at the current moment; Indicates the second abnormality level of the temperature data at the current moment; represents the hyperbolic tangent function; Represents an exponential function with a natural constant as its base.

7. The multi-energy coupled heating intelligent scheduling method according to claim 1 is characterized in that: The correcting of the temperature data at the current moment according to the comprehensive abnormality degree includes: The difference between 1 and the comprehensive abnormality level is used as the smoothing coefficient; the most recent The temperature data at each moment is taken as the data sample, and the smoothing coefficient is used to calculate the temperature of the sample. , use the exponential smoothing method to perform exponential smoothing on the data sample, obtain the predicted value of the temperature data at the current moment, and use the predicted value as the correction result of the temperature data at the current moment, where is the preset first quantity.

8. A multi-energy coupling heating intelligent scheduling method according to any one of claims 1-7, characterized in that: The step of determining the heat demand according to the corrected temperature data and selecting a heating method for heating includes: The heat demand is calculated based on the outlet water temperature and return water temperature in the temperature data corrected at the current moment; the ambient temperature in the temperature data corrected at the current moment is compared with the set defrost temperature. When the ambient temperature is not higher than the set defrost temperature, the gas equipment is called first. Otherwise, the natural gas cost and electricity cost required to meet the heat demand are calculated based on COP, ambient temperature, electricity price, natural gas price, and natural gas calorific value. When the electricity cost is less than the natural gas cost, the heat pump equipment is called first. When the electricity cost is not less than the natural gas cost, the gas equipment is called first.

9. A multi-energy coupling heating control system, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a multi-energy coupling heating intelligent scheduling method according to any one of claims 1-8 is implemented.

Images