Summer cooling load calculation method and system considering comprehensive meteorological temperature

Abstract

The invention discloses a summer cooling load calculation method and system considering comprehensive meteorological temperature, and particularly relates to the field of cooling load calculation, and the technical key points are that the method comprises the steps: determining an optimal clustering number in a comprehensive meteorological temperature sequence through employing an elbow rule, carrying out the regional division of a city through employing a K-means clustering method, and carrying out the calculation of the optimal clustering number; the number of the city region clusters is the optimal clustering number; acquiring a historical spring overall power curve and a historical autumn overall power curve of different city region clusters, and taking the curves as an input feature data sequence; extracting spring load curves and spring load change rate curves of the different urban area clusters in the previous year as related factor sequences, inputting the input feature data sequence into the grey prediction model, and combining the related factor sequences to obtain summer reference load curves of the different urban area clusters; and obtaining summer load curves of the different urban area clusters, and subtracting the summer reference load curve from the summer load curves of the different urban area clusters to obtain cooling load curves of the different urban area clusters.

Description

Technical Field

[0001] The present invention relates to the field of cooling load calculation, and in particular to a summer cooling load calculation method and system taking comprehensive meteorological temperature into consideration. Background Art

[0002] Cooling load refers to the power load generated by the use of cooling equipment such as air conditioners and fans. As the utilization rate of cooling load in summer continues to increase, the power grid will face new problems of safe and stable operation. For example, the concentrated use of cooling equipment (such as air conditioners and fans) in summer will cause the power grid load to rise sharply in a short period of time, thus forming a peak in electricity consumption. This peak load may exceed the design capacity of the power grid, causing overload operation of power grid equipment.

[0003] Usually we believe that the change of cooling load is correlated with the change of summer temperature, but the measured temperature cannot reflect the human body temperature. The temperature actually felt by the human body can directly affect the change of cooling load such as air conditioning. In order to further study the cooling load, it is usually necessary to accurately separate the cooling load from the daily load curve. In the process of separating the cooling load, it is necessary to predict the benchmark load curve. The existing methods of predicting the benchmark load curve include the average method, the regression method and the control group method. However, due to the differences in load patterns, the above-mentioned existing methods have low prediction accuracy and low utilization rate of historical load data.

[0004] In view of this, the present invention aims to provide a summer cooling load calculation method and system taking into account the comprehensive meteorological temperature to solve the above-mentioned related problems. Summary of the invention

[0005] The technical problem to be solved by the present invention is that the existing benchmark load curve has low prediction accuracy and low utilization rate of historical load data due to differences in load patterns. The purpose is to provide a summer cooling load calculation method and system considering comprehensive meteorological temperature. First, the summer daily measured temperature in different areas of the city is corrected based on urban micrometeorology to obtain the comprehensive meteorological temperature of different areas, thereby greatly increasing the correlation between the cooling load and the meteorology; at the same time, considering the differences in load characteristics of different areas, the city is divided into regions using the comprehensive meteorological temperature to obtain multiple urban area clusters, so as to achieve load pattern clustering of different urban areas according to the comprehensive meteorological temperature; then, the historical spring overall power curve and the historical autumn overall power curve of different urban area clusters are weightedly calculated as the input feature data sequence, the spring load curve of the previous year is used as the relevant factor sequence, and the summer benchmark load curve of different urban area clusters is obtained in combination with the gray prediction model; finally, the summer benchmark load curve is subtracted from the summer load curve of different urban area clusters to obtain the cooling load curve of different urban area clusters, thereby solving the problems of low prediction accuracy of the existing benchmark load curve and low utilization rate of historical load data due to differences in load patterns.

[0006] The present invention is achieved through the following technical solutions:

[0007] A summer cooling load calculation method considering comprehensive meteorological temperature, the method comprising:

[0008] Based on urban micrometeorology, the measured daily summer temperatures in different areas of the city are corrected to obtain the comprehensive meteorological temperatures in different areas, and the comprehensive meteorological temperatures in different areas are used to form a comprehensive meteorological temperature sequence;

[0009] The optimal number of clusters in the comprehensive meteorological temperature series is determined by the elbow rule, and the city is divided into regions using the K-means clustering method to obtain the optimal number of urban regional clusters, where different urban regional clusters have corresponding comprehensive meteorological temperatures.

[0010] Obtain historical spring overall power curves and historical autumn overall power curves of different urban area clusters, and use the historical spring overall power curves and historical autumn overall power curves of different urban area clusters as input feature data sequences;

[0011] The spring load curves and spring load change rate curves of the previous year of different urban area clusters are extracted as the correlation factor sequence, the input feature data sequence is input into the grey prediction model, and the summer benchmark load curves of different urban area clusters are obtained by combining the correlation factor sequence;

[0012] The summer load curves of different urban area clusters are obtained, and the cooling load curves of different urban area clusters are obtained by subtracting the summer benchmark load curves from the summer load curves of different urban area clusters. Finally, the cooling load curves of different urban area clusters are accumulated to obtain the total summer cooling load of the city.

[0013] Furthermore, based on the urban micrometeorology, the measured daily summer temperatures in different areas of the city are corrected to obtain the comprehensive meteorological temperatures in different areas. The comprehensive meteorological temperatures in different areas are used to form a comprehensive meteorological temperature sequence, specifically:

[0014] The measured daily summer temperatures in different areas of the city are obtained, and the measured daily summer temperatures are corrected for the heat island effect according to the heat island intensity in different areas, so as to obtain the first summer daily temperatures after the heat island effect correction in different areas;

[0015] According to the relative humidity in different regions, the first summer daily temperature after the heat island effect correction is corrected by temperature and humidity effect, and the second summer daily temperature after the temperature and humidity effect correction is obtained in different regions;

[0016] Combined with the average weighted value of the second summer daily temperature after correction of the temperature and humidity effects in different regions, the second summer daily temperature after correction of the temperature and humidity effects in different regions is corrected for the cumulative effect to obtain the comprehensive meteorological temperature after cumulative effect correction, and the comprehensive meteorological temperature in different regions is used to form a comprehensive meteorological temperature sequence.

[0017] Furthermore, the historical spring overall power curves and historical autumn overall power curves of different urban area clusters are obtained, and the historical spring overall power curves and historical autumn overall power curves of different urban area clusters are used as input feature data sequences, specifically:

[0018] Obtain multiple spring load curves and multiple autumn load curves for different urban area clusters;

[0019] The weight coefficient is adjusted according to the comprehensive meteorological temperature of different urban area clusters, and multiple spring load curves and multiple autumn load curves are weighted calculated using the adjusted weight coefficient to obtain the historical spring overall power curve and the historical autumn overall power curve;

[0020] The historical spring overall power curves and the historical autumn overall power curves of different urban area clusters are combined to serve as the input feature data sequences of different urban area clusters.

[0021] Furthermore, the spring load curves and spring load change rate curves of the previous year of different urban area clusters are extracted as the relevant factor sequences, specifically:

[0022] Obtain the spring load curves of the previous year for different urban area clusters and construct the spring load series of the previous year;

[0023] The spring load curves of the previous year for different urban area clusters were differentially processed to obtain the spring load change rates of the previous year for different urban area clusters, and the spring load change rate series of the previous year were constructed.

[0024] The spring load series of the previous year and the spring load change rate series of the previous year are combined as the correlation factor series.

[0025] Furthermore, the weight coefficient is adjusted according to the comprehensive meteorological temperature of different urban area clusters, specifically:

[0026] Construct multiple weight coefficients, where the multiple weight coefficients include a spring power weight coefficient and the autumn load weight factor Specifically:

[0027]

[0028] in, It represents the first similarity between the load value of the spring load curve before the ith year at time t and the benchmark load; represents the second similarity between the load value of the autumn load curve before the ith year at time t and the benchmark load;

[0029] The first similarity and the second similarity are adjusted according to the comprehensive meteorological temperatures of different urban area clusters, and the corresponding spring power weight coefficient and autumn power weight coefficient are obtained through the adjusted first similarity and second similarity.

[0030] Furthermore, the first similarity and the second similarity are adjusted according to the comprehensive meteorological temperatures of different urban area clusters, specifically:

[0031] When the comprehensive meteorological temperature is less than the first temperature threshold, the comprehensive meteorological temperature and the first temperature difference are calculated and the difference is inverted to obtain the first similarity or the second similarity;

[0032] When the comprehensive meteorological temperature is between the first temperature threshold and the second temperature threshold, the first similarity or the second similarity takes a value of 1;

[0033] When the comprehensive meteorological temperature is greater than the second temperature threshold, the difference between the comprehensive meteorological temperature and the second temperature is calculated and the inverted difference is taken to obtain the first similarity or the second similarity;

[0034] The first temperature difference is 1° C. greater than the first temperature threshold; and the second temperature difference is less than 1° C. greater than the second temperature threshold.

[0035] The present invention also provides a summer cooling load calculation system considering comprehensive meteorological temperature, which is used in any one of the above-mentioned summer cooling load calculation methods considering comprehensive meteorological temperature, and the system comprises:

[0036] The first module is used to correct the measured daily summer temperature in different areas of the city based on urban micrometeorology, obtain the comprehensive meteorological temperature of different areas, and use the comprehensive meteorological temperature of different areas to form a comprehensive meteorological temperature sequence;

[0037] The second module is used to determine the optimal number of clusters in the comprehensive meteorological temperature series using the elbow rule, and to divide the city into regions using the K-means clustering method to obtain urban regional clusters with the optimal number of clusters, where different urban regional clusters have corresponding comprehensive meteorological temperatures;

[0038] The third module is used to obtain the historical spring overall power curve and the historical autumn overall power curve of different urban area clusters, and use the historical spring overall power curve and the historical autumn overall power curve of different urban area clusters as input feature data sequences;

[0039] The fourth module is used to extract the spring load curve and spring load change rate curve of the previous year of different urban area clusters as the correlation factor sequence, input the input feature data sequence into the grey prediction model, and combine the correlation factor sequence to obtain the summer benchmark load curve of different urban area clusters;

[0040] The fifth module is used to obtain the summer load curves of different urban area clusters. The cooling load curves of different urban area clusters are obtained by subtracting the summer benchmark load curves from the summer load curves of different urban area clusters. Finally, the cooling load curves of different urban area clusters are accumulated to obtain the total summer cooling load of the city.

[0041] The present invention also provides a computer device, comprising a system memory and a processor, wherein the system memory stores a computer program, and the processor implements the steps of any one of the above-mentioned methods when executing the computer program.

[0042] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any one of the methods described above are implemented.

[0043] The present invention also provides a computer program product comprising instructions, and when the instructions are executed by a computer device cluster, the computer device cluster executes any of the above methods.

[0044] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0045] In the present invention, firstly, the measured daily summer temperature in different areas of the city is corrected based on urban micrometeorology to obtain the comprehensive meteorological temperature of different areas, thereby greatly increasing the correlation between the cooling load and the meteorology; at the same time, taking into account the differences in load characteristics of different areas, the city is divided into regions using the comprehensive meteorological temperature to obtain multiple urban area clusters, so as to cluster the load patterns of different urban areas according to the comprehensive meteorological temperature; then, the historical spring overall power curves and the historical autumn overall power curves of different urban area clusters are weightedly calculated as the input feature data sequence, and the spring load curve of the previous year is used as the relevant factor sequence, and the summer benchmark load curves of different urban area clusters are obtained in combination with the gray prediction model; finally, the summer benchmark load curves of different urban area clusters are subtracted from the summer load curves of different urban area clusters to obtain the cooling load curves of different urban area clusters, thereby solving the problems of low prediction accuracy of existing benchmark load curves and low utilization rate of historical load data due to differences in load patterns. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without creative work. In the drawings:

[0047] Figure 1 This is a method flow chart of a method for calculating summer cooling load taking into account comprehensive meteorological temperature in this embodiment;

[0048] Figure 2 This is a schematic diagram of module connections for a method for calculating summer cooling loads taking into account comprehensive meteorological temperature in this embodiment;

[0049] Figure 3 It is a structural schematic diagram of a computer device in this embodiment. DETAILED DESCRIPTION

[0050] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0051] In the present disclosure, unless otherwise specified, the use of the terms "first", "second", etc. to describe various elements is not intended to limit the positional relationship, timing relationship, or importance relationship of these elements, and such terms are only used to distinguish one element from another element. In some examples, the first element and the second element may refer to the same instance of the element, and in some cases, based on the description of the context, they may also refer to different instances.

[0052] The terms used in the description of various examples in this disclosure are only for the purpose of describing specific examples and are not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the element can be one or more. In addition, the term "and / or" used in this disclosure covers any one of the listed items and all possible combinations.

[0053] In order to facilitate understanding of the embodiments of the present invention, first, some terms involved in the present invention are explained.

[0054] The heat island effect refers to the phenomenon that the temperature difference between different regions increases due to the influence of population density, building density, traffic conditions, vegetation coverage and industrial production in different regions. It is generally manifested as the temperature in the city center being higher than that in the suburbs.

[0055] The temperature and humidity effect refers to the phenomenon that when the temperature is pleasant, relative humidity has a relatively small impact on the temperature people actually feel; when the temperature is high, relative humidity will have a greater impact on people's perceived temperature.

[0056] The cumulative effect refers to the fact that the human body's current perception of temperature is related to the cumulative effect of the weather conditions in the previous few days on the human body.

[0057] The comprehensive meteorological temperature is a corrected temperature. It comprehensively considers the influence of heat island effect, temperature and humidity effect and cumulative effect on the user's perceived temperature. It corrects the traditional ground temperature data by comprehensive meteorological factors to represent the user's perceived temperature value in the actual environment.

[0058] Cooling load: refers to the power load generated by the use of refrigeration equipment such as air conditioners; and the summer cooling load in this application mainly refers to the power load of air conditioners, fans, etc. used by users to maintain a comfortable indoor environment in hot weather.

[0059] Example 1

[0060] See also Figure 1 As shown, this embodiment provides a method for calculating summer cooling load considering comprehensive meteorological temperature, the method comprising:

[0061] S1: Based on the urban micrometeorology, the measured daily summer temperature in different areas of the city is corrected to obtain the comprehensive meteorological temperature in different areas. The comprehensive meteorological temperature in different areas is used to form a comprehensive meteorological temperature sequence, which is as follows:

[0062] The measured daily summer temperatures in different areas of the city are obtained, and the measured daily summer temperatures are corrected for the heat island effect according to the heat island intensity in different areas, so as to obtain the first summer daily temperatures after the heat island effect correction in different areas;

[0063] It should be noted that, in this embodiment, it is assumed that the city has multiple meteorological stations, and the summer daily measured temperatures in different regions can be obtained through the multiple meteorological stations. Then, the summer daily measured temperatures are corrected for the heat island effect according to the heat island intensity in different regions, and the first summer daily temperature after the heat island effect correction in different regions is obtained, where the heat island intensity HIT = T urban -T suburbs , T urban represents the city center temperature, T suburbs represents the temperature in the suburbs of the city;

[0064] At the same time, it should be noted that the temperature data measured by the meteorological station are all temperature data that have already reflected the heat island effect. Therefore, in other embodiments, the first summer daily temperature after the heat island effect correction in different regions can be directly obtained through the meteorological station.

[0065] According to the relative humidity in different regions, the first summer daily temperature after the heat island effect correction is corrected by temperature and humidity effect, and the second summer daily temperature after the temperature and humidity effect correction is obtained in different regions;

[0066] It should be noted that the temperature and humidity effect correction is only considered when the daily temperature in the first summer is greater than 80.6°F and the relative humidity in the area is greater than 40%. The correction equation for the temperature and humidity effect on the daily temperature in the first summer is as follows:

[0067] T HI =c1+c2T F +c3R+c4T F R+C F 2 +c6R 2 +c7T F 2 R+C F R 2 +c9T F 2 R 2

[0068] Among them, T HI is the Fahrenheit temperature and humidity index, which is the corrected daily temperature of the second summer; T Fis the daily Fahrenheit temperature in the first summer; R represents the relative humidity in different regions; the constant coefficients are: c1 = -42.38, c2 = 2.049, c3 = 10.14, c4 = -0.2248, c5 = -6.838×10 -3 , c6=-5.482×10 -2 , c7=1.228×10 -3 , c8=8.528×10 -4 , c9=-1.99×10 -6 .

[0069] Combined with the average weighted value of the second summer daily temperature after the temperature and humidity effects in different regions are corrected, the cumulative effect correction is performed on the second summer daily temperature after the temperature and humidity effects in different regions to obtain the comprehensive meteorological temperature after the cumulative effect correction The comprehensive meteorological temperature sequence is formed by using the comprehensive meteorological temperature of different regions, specifically:

[0070]

[0071] Where, T ad represents the cumulative effect correction temperature, T i represents the temperature of the previous i-th day, where T0 represents the temperature of the day;

[0072] In order to more accurately analyze the impact of the cumulative effect, when calculating the corrected temperature, the temperature T of the previous i-th day is i The corrected temperature T should be used adi , the corrected cumulative effect correction temperature is calculated as follows:

[0073]

[0074] λ i It represents the cumulative effect weight of the temperature on the previous ith day. It takes different values ​​for different temperatures T. It is generally believed that the higher the temperature, the greater its impact on people's perceived temperature, and the larger the corresponding weight coefficient λ;

[0075] Taking into account the influence of the above three micro-meteorological factors on temperature, the temperature measured by the weather station generally reflects the heat island effect. The influence of the temperature and humidity effect is taken into account by combining the real-time relative humidity through the correction equation of the temperature and humidity effect on the daily temperature in the first summer. Then, the result of the previous step is substituted as a new independent variable into the corrected cumulative effect correction temperature calculation equation to correct the cumulative effect and obtain the comprehensive meteorological temperature. Calculation:

[0076]

[0077] Among them, f(x) represents the correction of temperature due to heat island effect, g(x) represents the correction of temperature due to temperature and humidity effect, and h(x) represents the correction of temperature due to cumulative effect.

[0078] S2: The optimal number of clusters in the comprehensive meteorological temperature series is determined by the elbow rule, and the city is divided into regions using the K-means clustering method to obtain the optimal number of urban regional clusters, where different urban regional clusters have corresponding comprehensive meteorological temperatures;

[0079] It should be noted that, in this embodiment, there are users with different load patterns in different areas of the city. When the temperature changes, the changes in cooling loads in different areas are not the same. In order to improve the accuracy of load baseline estimation, regions with similar load patterns are first classified into one category based on the comprehensive meteorological temperature; first, the optimal clustering number K in the comprehensive meteorological temperature sequence is determined by the elbow rule, and then the K-means clustering method is used to obtain K urban area clusters by regional division of the city.

[0080] S3: Obtain the historical spring overall power curves and historical autumn overall power curves of different urban area clusters, and use the historical spring overall power curves and historical autumn overall power curves of different urban area clusters as input feature data sequences, specifically:

[0081] Get multiple spring load curves S for different urban area clusters i and multiple fall load curves A i , specifically:

[0082]

[0083] Among them, S i A represents the spring load curve before the ith year; i represents the autumn load curve before the ith year; represents the power data at time t in the spring of the i-th year before, t∈[1,2,…,δ], δ is a positive integer, represents the power data at time t in the autumn of the i-th year ago;

[0084] It should be noted that, in this embodiment, considering the separation of the cooling load from the load curve, it is necessary to calculate the benchmark load curves of different urban area clusters; in order to accurately predict the summer benchmark load curve of the year to be predicted and avoid the influence of cooling load and season factors, multiple spring (April-May) load curves and autumn (September-October) load curves before the year to be predicted of the different urban area clusters after division are selected.

[0085] The weight coefficient is adjusted according to the comprehensive meteorological temperature of different urban area clusters, and the adjusted weight coefficient is used to perform weighted calculation on multiple spring load curves and multiple autumn load curves to obtain the historical spring overall power curve and the historical autumn overall power curve, which are as follows:

[0086] Construct multiple weight coefficients, where the multiple weight coefficients include a spring power weight coefficient and the autumn load weight factor Specifically:

[0087]

[0088] in, It represents the first similarity between the load value of the spring load curve before the ith year at time t and the benchmark load; represents the second similarity between the load value of the autumn load curve before the ith year at time t and the benchmark load;

[0089] It should be noted that, in this embodiment, the setting and allocation of multiple weight coefficients are related to the accuracy of the final benchmark load curve prediction. Therefore, the comprehensive meteorological temperature of different urban area clusters is considered as the basis for weight setting. At the same time, each weight coefficient should be greater than or equal to 0. At the same time, the sum of all spring power weight coefficients and the sum of all autumn power weight coefficients are equal to 1. The more suitable the comprehensive meteorological temperature is, the larger the corresponding spring power weight coefficient and autumn power weight coefficient will be.

[0090] The first similarity and the second similarity are adjusted according to the comprehensive meteorological temperature of different urban area clusters, and the corresponding spring power weight coefficient and autumn power weight coefficient are obtained through the adjusted first similarity and second similarity, specifically: when the comprehensive meteorological temperature is less than the first temperature threshold, the comprehensive meteorological temperature and the first temperature difference are calculated and the first similarity or the second similarity is obtained after the difference is inverted; when the comprehensive meteorological temperature is between the first temperature threshold and the second temperature threshold, the first similarity or the second similarity is 1; when the comprehensive meteorological temperature is greater than the second temperature threshold, the comprehensive meteorological temperature and the second temperature difference are calculated and the first similarity or the second similarity is obtained after the difference is inverted; wherein, the first temperature difference is 1°C greater than the first temperature threshold; the second temperature difference is less than 1°C than the second temperature threshold;

[0091] It should be noted that when the temperature is suitable, the correction effects of the heat island effect, temperature and humidity effect, and cumulative effect on the temperature are not obvious. Considering that the human body feels most comfortable when the measured temperature is 18-26°C, it is believed that the load at this time does not contain meteorological sensitive loads, and the similarity can adopt the above adjustment strategy; the first temperature threshold is 17°C, the second temperature threshold is 27°C, the first temperature difference is 18°C, and the second temperature difference is 26°C.

[0092] The adjusted weight coefficients are used to perform weighted calculations on multiple spring load curves and multiple autumn load curves to obtain the historical spring overall power curve S = [s 1 ,s 2 ,...,s δ ] and the historical autumn overall power curve A=[a 1 ,a 2 ,...,a δ ],in:

[0093]

[0094] Among them, s t represents the power value of the historical spring overall power curve S at time t, a t It represents the power value of the overall power curve A in historical autumn at time t; represents the spring power weight coefficient corresponding to the power data of the previous i-th spring at time t, It represents the autumn power weight coefficient corresponding to the power data of the previous i-th autumn at time t.

[0095] The historical spring overall power curves and the historical autumn overall power curves of different urban area clusters are combined to serve as the input feature data sequences of different urban area clusters.

[0096] Specifically, in this embodiment, after obtaining the historical spring overall power curve S=[s 1 ,s 2 ,...,s δ ] and the historical autumn overall power curve A=[a 1 ,a 2 ,...,a δ ], the two curves form a characteristic data sequence X with a length of 2δ (0) , specifically:

[0097] X (0) =[S,A] = [x (0) (1),x (0) (2),……,x (0) (n)]

[0098] S4: extract the spring load curve and spring load change rate curve of the previous year of different urban area clusters as the correlation factor sequence, input the input feature data sequence into the grey prediction model, and combine the correlation factor sequence to obtain the summer benchmark load curve of different urban area clusters. The grey prediction model in this embodiment adopts the GM (1,1) grey prediction model, which is specifically:

[0099] Obtain the spring load curves of the previous year for different urban area clusters and construct the spring load series of the previous year;

[0100] It should be noted that, in this embodiment, the power benchmark load is a time series with a certain development trend and has a strong time correlation. The closer the historical day is to the predicted day, the closer the load change is. The load data and its change rate in the spring before the summer to be predicted (April-May) can be used as a related factor sequence.

[0101] Specifically, in this embodiment, the spring load curve of the previous year is represented by the spring load curve S i Can be obtained, specifically:

[0102] S1=[s1 1 ,s1 2 ,...,s1 δ ]

[0103] The spring load curves of the previous year for different urban area clusters were differentially processed to obtain the spring load change rates of the previous year for different urban area clusters, and the spring load change rate series of the previous year were constructed.

[0104] Specifically, in this embodiment, the load change rate in the spring of the previous year is expressed in a differential form as follows:

[0105]

[0106] Among them, s d t It represents the rate of change of load at time t, and Δt represents the sampling time interval.

[0107] It should be noted that, in this embodiment, since the development of the benchmark load is also stable, s d The value of (δ) can be considered to reflect the overall trend of load change, and the rate of change at time δ s d δ The load change rate can also be expressed as:

[0108]

[0109] Therefore, the load change rate sequence S of the previous year's spring is obtained d =[s d 1 ,s d 2 ,...,s d δ ].

[0110] The spring load series of the previous year and the spring load change rate series of the previous year are combined as the correlation factor series;

[0111] Specifically, in this embodiment, the spring load sequence S1 of the previous year is combined with the spring load change rate sequence S d , and the combined length of the correlation factor sequence F is 2δ (0) =[S1,S d ]=[f (0) (1),f (0) (2),...,f (0) (n)];

[0112] Based on the GM (1,1) grey prediction model, X (0) With F (0) 1-AGO sequence X (1) =[x (1) (1),x (1) (2),...,x (1) (n)] and F (1) =[f (1) (1),f (1) (2),...,f (1) (n)], and X (1) The neighbor mean sequence Z (1) =[z (1) (1),z (1) (2),...,z (1) (n)], specifically:

[0113]

[0114] Then x (1) Prediction function about time t for:

[0115]

[0116] Among them, a is the development coefficient, b is the driving coefficient, and the parameter [a, b] T It can be calculated by the following formula:

[0117]

[0118] Wherein, matrices B and Y are:

[0119]

[0120] Since the characteristic data sequence is accumulated, the predicted value of the benchmark load, that is, x (0) Prediction function about time t Can be Cumulative reduction:

[0121]

[0122] The summer benchmark load curves of different urban area clusters are obtained through the grey prediction model.

[0123] S5: obtaining summer load curves of different urban area clusters, subtracting summer benchmark load curves from summer load curves of different urban area clusters to obtain cooling load curves of different urban area clusters, and finally accumulating cooling load curves of different urban area clusters to obtain the total summer cooling load of the city.

[0124] It should be noted that the summer load calculation formula is as follows:

[0125] P 夏季负荷 =P 基准负荷 +P 降温负荷

[0126] Specifically, in this embodiment, firstly, the measured daily summer temperature in different areas of the city is corrected based on the urban micrometeorology to obtain the comprehensive meteorological temperature of different areas, thereby greatly increasing the correlation between the cooling load and the meteorology; at the same time, taking into account the differences in load characteristics of different areas, the city is divided into regions using the comprehensive meteorological temperature to obtain multiple urban area clusters, so as to cluster the load patterns of different urban areas according to the comprehensive meteorological temperature; then, the historical spring overall power curves and the historical autumn overall power curves of different urban area clusters are weightedly calculated as the input feature data sequence, and the spring load curve of the previous year is used as the relevant factor sequence, and the summer benchmark load curves of different urban area clusters are obtained in combination with the gray prediction model; finally, the summer benchmark load curves of different urban area clusters are subtracted from the summer load curves of different urban area clusters to obtain the cooling load curves of different urban area clusters, thereby solving the problems of low prediction accuracy of existing benchmark load curves and low utilization rate of historical load data due to differences in load patterns.

[0127] Example 2

[0128] The present invention also provides a summer cooling load calculation system considering comprehensive meteorological temperature, which is used in any one of the above-mentioned summer cooling load calculation methods considering comprehensive meteorological temperature, and the system comprises:

[0129] The first module 100 is used to correct the measured daily summer temperatures in different areas of the city based on urban micro-meteorology to obtain comprehensive meteorological temperatures in different areas, and to form a comprehensive meteorological temperature sequence using the comprehensive meteorological temperatures in different areas;

[0130] The second module 200 is used to determine the optimal number of clusters in the comprehensive meteorological temperature sequence by using the elbow rule, and to divide the city into regions by using the K-means clustering method to obtain urban regional clusters with the optimal number of clusters, wherein different urban regional clusters have corresponding comprehensive meteorological temperatures;

[0131] The third module 300 is used to obtain the historical spring overall power curve and the historical autumn overall power curve of different urban area clusters, and use the historical spring overall power curve and the historical autumn overall power curve of different urban area clusters as input feature data sequences;

[0132] The fourth module 400 is used to extract the spring load curve and spring load change rate curve of the previous year of different urban area clusters as the correlation factor sequence, input the input feature data sequence into the grey prediction model, and obtain the summer benchmark load curve of different urban area clusters in combination with the correlation factor sequence;

[0133] The fifth module 500 is used to obtain the summer load curves of different urban area clusters, and obtain the cooling load curves of different urban area clusters by subtracting the summer benchmark load curves from the summer load curves of different urban area clusters. Finally, the cooling load curves of different urban area clusters are accumulated to obtain the total summer cooling load of the city.

[0134] It should be noted that the modules in the system of Example 2 correspond to the steps in the method of Example 1. The steps in the method of Example 1 have been described in detail in Example 1. In this Example 2, the contents of the modules in the system will not be described in detail.

[0135] Example 3

[0136] This embodiment further provides a computer device, including a system memory 1005 and a processor 1001 . The system memory 1005 stores a computer program. When the processor 1001 executes the computer program, the steps of any one of the above methods are implemented.

[0137] It should be noted that the processor 1001 is used to execute the steps in the above method embodiments according to the instructions in the program code. Alternatively, the processor 1001 implements the functions of each module / unit in the above system / device embodiments when executing the computer program.

[0138] Specifically, in this embodiment, the computer program may be divided into one or more modules / units, one or more modules / units are stored in the system memory 1005, and are executed by the processor 1001 to complete the present application. One or more modules / units may be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program in the terminal device.

[0139] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor 1001 and a system memory 1005. Those skilled in the art will appreciate that this does not constitute a limitation on the terminal device, and may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal device may also include an input / output device 1003, a network access device 1002, a bus 1006, etc.

[0140] The processor 1001 may be a central processing unit (CPU), or other general-purpose processors 1001, digital signal processors 1001 (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor 1001 may be a microprocessor or any conventional processor, etc.

[0141] The system memory 1005 may be an internal storage unit of the terminal device, such as a hard disk or memory of the terminal device. The system memory 1005 may also be a storage device 1004 of the terminal device, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the terminal device. Further, the system memory 1005 may also include both the internal storage unit of the terminal device and the storage device 1004. The system memory 1005 is used to store computer programs and other programs and data required by the terminal device. The system memory 1005 may also be used to temporarily store data that has been output or is to be output.

[0142] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0143] Example 4

[0144] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the above methods are implemented.

[0145] Among them, the computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, system or device, or any combination of the above. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk. Random Access Memory (RAM), Read-Only Memory (ROM), Erasable Programmable Read Only Memory (EPROM), registers, hard disks, optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above, or any other form of computer-readable storage medium known in the art.

[0146] An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application-specific integrated circuit (ASIC). In an embodiment of the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system, or device.

[0147] Example 5

[0148] This embodiment also provides a computer program product including instructions. When the instructions are executed by a computer device cluster, the computer device cluster executes the method described in Embodiment 1.

[0149] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for calculating summer cooling load considering comprehensive meteorological temperature, characterized in that: Methods include: Based on urban micrometeorology, the measured daily summer temperatures in different areas of the city are corrected to obtain the comprehensive meteorological temperatures in different areas, and the comprehensive meteorological temperatures in different areas are used to form a comprehensive meteorological temperature sequence; The optimal number of clusters in the comprehensive meteorological temperature series is determined by the elbow rule, and the city is divided into regions using the K-means clustering method to obtain the optimal number of urban regional clusters, where different urban regional clusters have corresponding comprehensive meteorological temperatures. Obtain historical spring overall power curves and historical autumn overall power curves of different urban area clusters, and use the historical spring overall power curves and historical autumn overall power curves of different urban area clusters as input feature data sequences; The spring load curves and spring load change rate curves of the previous year of different urban area clusters are extracted as the correlation factor sequence, the input feature data sequence is input into the grey prediction model, and the summer benchmark load curves of different urban area clusters are obtained by combining the correlation factor sequence; The summer load curves of different urban area clusters are obtained, and the cooling load curves of different urban area clusters are obtained by subtracting the summer benchmark load curves from the summer load curves of different urban area clusters. Finally, the cooling load curves of different urban area clusters are accumulated to obtain the total summer cooling load of the city.

2. A summer cooling load calculation method considering comprehensive meteorological temperature according to claim 1, characterized in that: Based on urban micrometeorology, the measured daily summer temperatures in different areas of the city are corrected to obtain the comprehensive meteorological temperatures in different areas. The comprehensive meteorological temperatures in different areas are used to form a comprehensive meteorological temperature sequence, specifically: The measured daily summer temperatures in different areas of the city are obtained, and the measured daily summer temperatures are corrected for the heat island effect according to the heat island intensity in different areas, so as to obtain the first summer daily temperatures after the heat island effect correction in different areas; According to the relative humidity in different regions, the first summer daily temperature after the heat island effect correction is corrected by temperature and humidity effect, and the second summer daily temperature after the temperature and humidity effect correction is obtained in different regions; Combined with the average weighted value of the second summer daily temperature after correction of the temperature and humidity effects in different regions, the second summer daily temperature after correction of the temperature and humidity effects in different regions is corrected for the cumulative effect to obtain the comprehensive meteorological temperature after cumulative effect correction, and the comprehensive meteorological temperature in different regions is used to form a comprehensive meteorological temperature sequence.

3. A summer cooling load calculation method considering comprehensive meteorological temperature according to claim 1, characterized in that: The historical spring overall power curves and historical autumn overall power curves of different urban area clusters are obtained, and the historical spring overall power curves and historical autumn overall power curves of different urban area clusters are used as input feature data sequences, specifically: Obtain multiple spring load curves and multiple autumn load curves for different urban area clusters; The weight coefficient is adjusted according to the comprehensive meteorological temperature of different urban area clusters, and multiple spring load curves and multiple autumn load curves are weighted calculated using the adjusted weight coefficient to obtain the historical spring overall power curve and the historical autumn overall power curve; The historical spring overall power curves and the historical autumn overall power curves of different urban area clusters are combined to serve as the input feature data sequences of different urban area clusters.

4. A method for calculating summer cooling load considering comprehensive meteorological temperature according to claim 1, characterized in that: The spring load curves and spring load change rate curves of the previous year of different urban area clusters are extracted as the relevant factor sequences, specifically: Obtain the spring load curves of the previous year for different urban area clusters and construct the spring load series of the previous year; The spring load curves of the previous year for different urban area clusters were differentially processed to obtain the spring load change rates of the previous year for different urban area clusters, and the spring load change rate series of the previous year were constructed. The spring load series of the previous year and the spring load change rate series of the previous year are combined as the correlation factor series.

5. The summer cooling load calculation method considering comprehensive meteorological temperature according to claim 3 is characterized in that: The weight coefficient is adjusted according to the comprehensive meteorological temperature of different urban area clusters, specifically: Construct multiple weight coefficients, where the multiple weight coefficients include a spring power weight coefficient and the autumn load weight factor Specifically: in, It represents the first similarity between the load value of the spring load curve before the ith year at time t and the benchmark load; represents the second similarity between the load value of the autumn load curve before the ith year at time t and the benchmark load; The first similarity and the second similarity are adjusted according to the comprehensive meteorological temperatures of different urban area clusters, and the corresponding spring power weight coefficient and autumn power weight coefficient are obtained through the adjusted first similarity and second similarity.

6. A method for calculating summer cooling load considering comprehensive meteorological temperature according to claim 5, characterized in that: The first similarity and the second similarity are adjusted according to the comprehensive meteorological temperature of different urban area clusters, specifically: When the comprehensive meteorological temperature is less than the first temperature threshold, the comprehensive meteorological temperature and the first temperature difference are calculated and the difference is inverted to obtain the first similarity or the second similarity; When the comprehensive meteorological temperature is between the first temperature threshold and the second temperature threshold, the first similarity or the second similarity takes a value of 1; When the comprehensive meteorological temperature is greater than the second temperature threshold, the difference between the comprehensive meteorological temperature and the second temperature is calculated and the inverted difference is taken to obtain the first similarity or the second similarity; The first temperature difference is 1° C. greater than the first temperature threshold; and the second temperature difference is less than 1° C. greater than the second temperature threshold.

7. A summer cooling load calculation system considering comprehensive meteorological temperature, characterized in that: The system is used in a summer cooling load calculation method considering comprehensive meteorological temperature as described in any one of claims 1 to 6, and the system comprises: The first module is used to correct the measured daily summer temperature in different areas of the city based on urban micrometeorology, obtain the comprehensive meteorological temperature of different areas, and use the comprehensive meteorological temperature of different areas to form a comprehensive meteorological temperature sequence; The second module is used to determine the optimal number of clusters in the comprehensive meteorological temperature series using the elbow rule, and to divide the city into regions using the K-means clustering method to obtain urban regional clusters with the optimal number of clusters, where different urban regional clusters have corresponding comprehensive meteorological temperatures; The third module is used to obtain the historical spring overall power curve and the historical autumn overall power curve of different urban area clusters, and use the historical spring overall power curve and the historical autumn overall power curve of different urban area clusters as input feature data sequences; The fourth module is used to extract the spring load curve and spring load change rate curve of the previous year of different urban area clusters as the correlation factor sequence, input the input feature data sequence into the grey prediction model, and combine the correlation factor sequence to obtain the summer benchmark load curve of different urban area clusters; The fifth module is used to obtain the summer load curves of different urban area clusters. The cooling load curves of different urban area clusters are obtained by subtracting the summer benchmark load curves from the summer load curves of different urban area clusters. Finally, the cooling load curves of different urban area clusters are accumulated to obtain the total summer cooling load of the city.

8. A computer device comprising a system memory and a processor, wherein the system memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. 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 according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising instructions, characterized in that When the instructions are executed by a computer device cluster, the computer device cluster executes the method according to any one of claims 1 to 6.

Images