Air conditioning load prediction method and system considering electric vehicles and heat island effect

Abstract

The present invention provides an air conditioning load prediction method and system considering electric vehicles and urban heat island effect, including: obtaining regional information of the air conditioning load to be predicted; obtaining prediction results according to the regional information and a preset air conditioning load prediction model; wherein the air conditioning load prediction model is a regression equation, and the variables of the regression equation are the temperature determined under the urban heat island effect and the factors in the economic index; the temperature determined under the urban heat island effect is affected by the preset replacement rate of electric vehicles; the present invention constructs an air conditioning load prediction model method considering electric vehicles and urban heat island effect. In addition, the prediction method focuses on the impact of economic development on air conditioning load, and obtains the regression equation of air conditioning load with respect to economic factors, so that the air conditioning load prediction is closer to real life.

Description

Technical Field

[0001] The present invention belongs to the technical field of power system load forecasting, and in particular relates to an air conditioning load forecasting method and system taking into account electric vehicles and heat island effects. Background Art

[0002] With the rapid growth of economy and electricity demand, electricity supply and demand are often in a tight state; the proportion of air-conditioning load in power terminal equipment has increased year by year, and has become the most important component of peak load, deepening the contradiction between supply and demand during peak hours and causing the peak-to-valley difference to further widen; therefore, accurately predicting summer air-conditioning load is an important prerequisite for regulating the peak-to-valley difference and ensuring the safe and economical operation of the power system.

[0003] The inventors found that the existing air-conditioning load prediction method did not fully consider the urban heat island effect and the impact of economic development on the air-conditioning load, resulting in inaccurate considerations in the air-conditioning load prediction, the model deviating from the actual living conditions and low prediction accuracy. Summary of the invention

[0004] In order to solve the above problems, the present invention proposes an air-conditioning load prediction method and system considering electric vehicles and urban heat island effect. The present invention constructs an air-conditioning load prediction model method considering electric vehicles and urban heat island effect; and in the prediction method, the impact of economic development on air-conditioning load is emphasized, and the regression equation of air-conditioning load with respect to economic factors is obtained, so that the air-conditioning load prediction is closer to real life.

[0005] In order to achieve the above object, the present invention is implemented through the following technical solutions:

[0006] In a first aspect, the present invention provides an air conditioning load prediction method considering electric vehicles and heat island effect, comprising:

[0007] Obtain information about the area where the air conditioning load to be predicted is located;

[0008] Obtain prediction results based on regional information and the preset air conditioning load prediction model;

[0009] Among them, the air-conditioning load prediction model is a regression equation, and the variables of the regression equation are the temperature determined under the urban heat island effect and the factors in the economic indicators; the temperature determined under the urban heat island effect is affected by the preset replacement rate of electric vehicles.

[0010] Furthermore, the regional information at least includes factors of preset summer temperature and economic indicators in the area to be predicted.

[0011] Furthermore, the factors in the economic indicators include at least one or more of per capita disposable income, urbanization rate and per capita household electricity consumption.

[0012] Furthermore, the air conditioning load prediction model is: fcst =k1x1+k2x2+k3x3+k4x4+b, where y fcst represents per capita air-conditioning load, x1 represents per capita disposable income, x2 represents urbanization rate, x3 represents per capita household electricity consumption, x4 represents temperature, k1, k2, k3, k4 and b are coefficients.

[0013] Furthermore, the construction of the air conditioning load prediction model includes:

[0014] Acquire historical data of air conditioning load, perform regression analysis on the air conditioning load according to the historical data, analyze the relationship between per capita air conditioning load and economic indicators, and obtain a first air conditioning load prediction model;

[0015] Temperature is introduced into the first air-conditioning load prediction model to obtain an air-conditioning load model that takes temperature influence into account, and the influence of electric vehicle development on the urban heat island effect and thus the influence on temperature is analyzed.

[0016] Furthermore, the replacement rate is the proportion of electric vehicles replacing fuel vehicles in the future.

[0017] Further, the temperature is determined according to the preset replacement rate of the electric vehicle, specifically:

[0018] Determine the number of electric vehicles in the future according to the replacement rate, and obtain the reduction in automobile exhaust emissions as the number of electric vehicles increases:

[0019] The reduction in automobile exhaust emissions is logarithmically related to the change in temperature. The temperature is determined based on the relationship between the reduction in automobile exhaust emissions and the change in temperature.

[0020] In a second aspect, the present invention further provides an air conditioning load prediction system considering electric vehicles and heat island effect, comprising:

[0021] The data acquisition module is configured to: obtain information about the area where the air conditioning load to be predicted is located;

[0022] The prediction module is configured to: obtain a prediction result according to the regional information and a preset air conditioning load prediction model;

[0023] Among them, the air-conditioning load prediction model is a regression equation, and the variables of the regression equation are the temperature determined under the urban heat island effect and the factors in the economic indicators; the temperature determined under the urban heat island effect is affected by the preset replacement rate of electric vehicles.

[0024] In a third aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the air conditioning load prediction method considering electric vehicles and heat island effect described in the first aspect.

[0025] In a fourth aspect, the present invention further provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the air conditioning load prediction method considering electric vehicles and heat island effect described in the first aspect are implemented.

[0026] Compared with the prior art, the present invention has the following beneficial effects:

[0027] 1. The present invention constructs an air conditioning load prediction model method that takes into account electric vehicles and the urban heat island effect. In addition, the prediction method focuses on the impact of economic development on air conditioning load, and obtains a regression equation for air conditioning load with respect to economic factors, making air conditioning load prediction closer to real life;

[0028] 2. The present invention quantitatively analyzes the coupling relationship between electric vehicle substitution and urban heat island effect, and integrates this relationship into the air-conditioning load prediction method; electric vehicles, as an emerging industry, will inevitably have a greater impact on temperature in the future, thereby affecting the air-conditioning load; the present invention takes into account the impact of the rapid development of electric vehicle technology on future air-conditioning loads on the basis of considering economic factors, thereby improving the accuracy and reliability of the air-conditioning load prediction model. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The drawings in the specification that constitute a part of this embodiment are used to provide a further understanding of this embodiment. The schematic embodiments of this embodiment and their descriptions are used to explain this embodiment and do not constitute improper limitations on this embodiment.

[0030] Figure 1 This is a flow chart of Embodiment 1 of the present invention;

[0031] Figure 2 This is a schematic diagram of the urban heat island effect of Example 1 of the present invention;

[0032] Figure 3 This is a schematic diagram of air conditioning load fitting considering economic factors according to Example 2 of the present invention;

[0033] Figure 4 This is a schematic diagram of air conditioning load fitting considering the urban heat island effect according to Example 2 of the present invention;

[0034] Figure 5 The electric vehicle ownership growth curve of Example 2 of the present invention;

[0035] Figure 6This is a schematic diagram of the relationship between the electric vehicle replacement rate and the air conditioning load reduction according to Example 2 of the present invention;

[0036] Figure 7 This is a schematic diagram of the air conditioning load prediction results of Example 2 of the present invention. DETAILED DESCRIPTION

[0037] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0038] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

[0039] Embodiment 1:

[0040] In essence, the load forecasting of the power system is to estimate the power demand in advance, and to calculate the future load value based on the historical load data, so as to provide a reliable basis for the power department to formulate the power generation plan; the load forecasting of the power system is one of the important tasks of energy utilization, power planning, dispatching and other management services; on the one hand, the power load forecasting can provide a strong basis for the construction planning and infrastructure layout of the power grid, and avoid the waste of resources caused by duplicate construction due to the backward power infrastructure in some areas; on the other hand, accurate power load forecasting is conducive to more scientifically determining the start and stop quantity and output distribution of each generating unit, maintaining the balance of generation, transformation, transmission, distribution and use, thereby reducing the power generation cost of the system and ensuring the safe and reliable operation of the power grid.

[0041] With the rapid growth of economy and electricity demand, electricity supply and demand are often in a tight state; the proportion of air-conditioning load in power terminal equipment has increased year by year, and has become the most important component of peak load, deepening the contradiction between supply and demand during peak hours and causing the peak-to-valley difference to widen further; therefore, accurately predicting summer air conditioning load is an important prerequisite for adjusting the peak-to-valley difference and ensuring the safe and economical operation of the power system.

[0042] With the rapid increase in the number of cars, exhaust pollution has replaced coal gas pollution as one of the main sources of pollution; factors such as the wide variety of vehicles, uneven quality, low emission standards and poor oil quality have led to serious automobile exhaust pollution, and exhaust pollution is one of the important reasons for the urban heat island effect.

[0043] The urban heat island effect refers to the phenomenon that the air temperature in the city is significantly higher than that in the suburbs outside the city. From the near-ground temperature map, the temperature in the suburbs changes very little, while the shape of the high-temperature area in the urban area is like an island protruding from the sea surface, so it is figuratively called an urban heat island.

[0044] Existing research believes that the formation mechanism, intensity and spatiotemporal distribution characteristics of urban heat islands are mainly related to the following factors: the influence of the underlying surface material, the influence of building combination and material, and the influence of anthropogenic heat emissions. Anthropogenic heat emissions mainly refer to the various heat generated by people's daily production and life in the city, which exacerbates the urban heat island effect. It can include heat from industrial production, heat generated by vehicles, and heat emitted by air conditioners. Figure 2 It reflects the temperature characteristics of suburbs and urban areas. The temperature increases from suburbs to urban areas to central urban areas, and the existence of heat islands is clearly shown. According to statistical results, the average annual temperature in urban areas is 0.5℃-2℃ higher than that in suburbs.

[0045] In response to the above problems, Figure 1 As shown, this embodiment provides an air conditioning load prediction method considering electric vehicles and heat island effect, including:

[0046] Obtain information about the area where the air conditioning load to be predicted is located;

[0047] Obtain prediction results based on regional information and the preset air conditioning load prediction model;

[0048] Among them, the air-conditioning load prediction model is a regression equation, and the variables of the regression equation are the temperature determined under the urban heat island effect and the factors in the economic indicators; the temperature determined under the urban heat island effect is affected by the preset replacement rate of electric vehicles.

[0049] In this embodiment, the regional information at least includes factors of summer temperature and economic indicators preset in the area to be predicted.

[0050] In this embodiment, the factors in the economic indicators include at least one or more of per capita disposable income, urbanization rate and per capita household electricity consumption.

[0051] In this embodiment, the air conditioning load prediction model is: fcst =k1x1+k2x2+k3x3+k4x4+b, where y fcst represents per capita air-conditioning load, x1 represents per capita disposable income, x2 represents urbanization rate, x3 represents per capita household electricity consumption, x4 represents temperature, k1, k2, k3, k4 and b are coefficients.

[0052] In this embodiment, the construction of the air conditioning load prediction model includes:

[0053] Acquire historical data of air conditioning load, perform regression analysis on the air conditioning load according to the historical data, analyze the relationship between per capita air conditioning load and economic indicators, and obtain a first air conditioning load prediction model;

[0054] Temperature is introduced into the first air-conditioning load prediction model to obtain an air-conditioning load model that takes temperature influence into account, and the influence of electric vehicle development on the urban heat island effect and thus the influence on temperature is analyzed.

[0055] Specifically, an air-conditioning load prediction model is constructed which considers economic factors as well as electric vehicles and urban heat island effect. First, the air-conditioning load is measured to obtain historical data. Then, a regression analysis is performed on the air-conditioning load based on the historical data. The relationship between per capita air-conditioning load and economic indicators is analyzed to obtain an air-conditioning load prediction model under general circumstances. Temperature is introduced into the air-conditioning load model that considers economic factors to obtain an air-conditioning load model that takes into account the influence of temperature. The impact of the development of electric vehicles on the urban heat island effect is analyzed, which in turn affects the temperature, leading to the correction of the air-conditioning load in summer.

[0056] In this embodiment, the replacement rate is the proportion of electric vehicles replacing fuel vehicles in the future.

[0057] In this embodiment, the temperature is determined according to the preset replacement rate of electric vehicles. The replacement of fuel vehicles by electric vehicles leads to a decrease in the exhaust emissions of fuel vehicles, thereby reducing the impact of the heat island effect on the temperature, resulting in a decrease in temperature. The decrease in air conditioning load can be determined according to the change in temperature; specifically:

[0058] First, the number of electric vehicles in the future can be determined based on the replacement rate, thereby obtaining the reduction of automobile exhaust emissions as the number of electric vehicles increases.

[0059]

[0060] ΔT emissions =6×10 -4 TM EV

[0061] Among them, K is the replacement rate of electric vehicles, M EV For the number of electric vehicles in the future, is the historical maximum number of fuel vehicles, ΔT emissions is the change in vehicle exhaust emissions due to the replacement of electric vehicles, and T is the vehicle life.

[0062] The reduction in automobile exhaust emissions is logarithmically related to the change in temperature, and the analytical relationship is:

[0063] ΔC=k tem lnΔT emissions

[0064] Where ΔC is the change in temperature, k tem is the influence coefficient. In this embodiment, k is preset temis 0.015; the reduction of air-conditioning load is solved according to the change of temperature, and the air-conditioning load is corrected.

[0065] In this embodiment, in order to predict the future air-conditioning load, it is necessary to calculate the historical air-conditioning load data; first, it is necessary to determine the typical power load curve in summer when the air-conditioning equipment is not in operation. The difference between the actual daily load curve of the power grid in summer and the summer basic load curve is the cooling load curve for the day.

[0066] In this embodiment, the average value of the load curves of spring and autumn is selected as the summer basic load curve. This is because the air conditioning cooling load and heating load are low in spring and autumn and can be ignored. At the same time, in the spring, summer and autumn of a year, even without the influence of air conditioning electricity consumption, other electricity loads will naturally increase. Therefore, using the average load curve of spring or autumn alone as the summer basic load curve will lead to an incorrect estimate of the cooling load.

[0067] Embodiment 2:

[0068] In this embodiment, the air conditioning load prediction method proposed in Embodiment 1 is implemented and verified by using data from a certain province; the air conditioning load prediction is carried out in two steps: first, the study found that although the summer temperature fluctuations are large in recent years, the air conditioning load continues to rise, and it is positively correlated with the level of residents' living indicators; therefore, this embodiment analyzes the changes in summer air conditioning load with urbanization level, per capita disposable income and other economic factors; thus, this embodiment obtains a prediction model for air conditioning load under general circumstances; then, based on the previous prediction, the impact of temperature on air conditioning load is considered, and the impact of urban heat island effect on temperature under the large-scale replacement of electric vehicles is studied, thereby considering the impact of electric vehicles and urban heat island effect on air conditioning load, correcting the air conditioning load, and improving the prediction accuracy; specifically:

[0069] In this embodiment, the summer air-conditioning load is first predicted by economic factors; the main factors affecting the air-conditioning load include the level of per capita resident indicators (per capita residential electricity consumption, per capita disposable income, etc.) and the urbanization process; as shown in Table 1, the per capita resident indicators and per capita air-conditioning load data of the province in recent years.

[0070] Table 1 Per capita resident index and per capita air conditioning load data

[0071]

[0072] According to correlation calculation, per capita air-conditioning load is strongly correlated with per capita household electricity consumption, per capita disposable income of permanent residents and urbanization rate, with Pearson correlation coefficients reaching 0.98, 0.961 and 0.955 respectively.

[0073] The regression analysis method based on principal component analysis was adopted and SPSS was used to perform regression analysis, and the regression equation with the per capita air-conditioning load of the province as the dependent variable was obtained, as shown in formula (1).

[0074] y fcst =k1x1+k2x2+k3x3+b (1)

[0075] Among them, x1, x2 and x3 represent per capita disposable income, urbanization rate and per capita household electricity consumption respectively; y fcst represents the per capita air conditioning load; in this disclosure, k1, k2, k3, k4 and b are all coefficients, and k1, k2, k3 and b can be set to -1.91×10 -5 , 1.319, 1.203×10 -3 and -0.753.

[0076] The fitting effect diagram is as follows Figure 3 As shown below are the fitted value and historical actual value of per capita air-conditioning load in the province, and the prediction error is shown in Table 2 below.

[0077] Table 2 Prediction error

[0078]

[0079] As people's living standards and electrification levels improve, per capita electricity consumption is expected to continue to grow and reach 900 kWh / person in 2025. The province's per capita disposable income is expected to reach 42,980 yuan, and the province's permanent population urbanization rate will reach 65%. Substituting these data into formula (1), it can be obtained that the per capita air conditioning load of the province in 2025 is about 0.366 kw, and the maximum air conditioning load of the province on a typical summer day will reach 29,897 MW.

[0080] On the basis of the above, in this embodiment, the air conditioning load prediction considering the influence of the heat island effect on temperature is studied; the regression analysis method based on principal component analysis is also adopted, and the temperature is considered as an independent variable to find the fitting equation of per capita air conditioning load. The highest summer temperature in the province is shown in Table 3.

[0081] Table 3 Maximum temperature in summer

[0082]

[0083]

[0084] The fitting equation of per capita air conditioning load considering the urban heat island effect is obtained as shown in equation (2); where x4 represents the maximum temperature of a typical day in summer in the province; in this model, k1, k2, k3, k4 and b can be -3.235×10-5 , 2.24, 1.5×10 -3 , 8×10 -3 and -1.402, and its fitting curve is as follows Figure 4 shown.

[0085] y fcst =k1x1+k2x2+k3x3+k4x4+b (2)

[0086] like Figure 4 As shown in Figure 3, after considering the influence of temperature, the prediction results are more accurate.

[0087] At this point, the air conditioning load can be further corrected by predicting the future maximum summer temperature. Assuming that the summer temperature in 2025 is high, when the maximum temperature reaches 38°C, the summer air conditioning load will reach a maximum of 25,967MW; assuming that the summer temperature in 2025 is low, when the maximum temperature is 33°C, the summer air conditioning load will reach a maximum of 22,696MW. Compared with the air conditioning load prediction model that only considers economic factors, the load predicted by this model is smaller and closer to reality.

[0088] In addition, due to the rapid development of electric vehicle technology, the number of electric vehicles owned by residents is increasing rapidly, which will directly lead to a decrease in the number of fuel vehicles; and the exhaust emissions of fuel vehicles are the main cause of the urban heat island effect. The popularization of electric vehicles will lead to a significant reduction in the number of fuel vehicles and their emissions; therefore, the rapid development of electric vehicles will slow down the urban heat island effect; it is estimated that the number of electric vehicles in the province will reach 700,000 in 2025, and it is assumed that these electric vehicles replace 700,000 fuel vehicles.

[0089] S emissions =6×10 -4 TN fv (3)

[0090] Among them, S emissions is the exhaust emission of fuel vehicles, T is the life of the vehicle, N fv is the number of fuel vehicles. According to formula (3), by 2025, the province will reduce 153,300 tons of vehicle exhaust emissions due to the replacement of fuel vehicles by electric vehicles. It is estimated that the reduction in these vehicle exhaust emissions will lead to a 0.2°C drop in the average temperature of the province. This will reduce the air conditioning load in the province by 163MW, help reduce the peak-to-valley difference, and ensure the economic and stable operation of the power system.

[0091] like Figure 5 As shown in Figure 2, the growth trend of electric vehicle ownership is described; Figure 6As shown in the figure, the relationship between the reduction of summer air conditioning load and the replacement rate of electric vehicles is shown; with the rapid increase in the market share of electric vehicles, the number of fuel vehicles has been greatly reduced, resulting in a sharp drop in exhaust carbon emissions from fuel vehicles, thereby alleviating the urban heat island effect. The temperature difference between urban and suburban areas continues to narrow, the temperature in urban areas decreases, and the summer air conditioning load decreases. However, when electric vehicles gradually completely replace fuel vehicles, the impact of the urban heat island effect on temperature will gradually weaken, resulting in a slowdown in the rate of decrease in summer air conditioning load until saturation.

[0092] In addition, the morning and evening travel peaks have a serious impact on the urban heat island effect. Therefore, a small peak of air conditioning load will be generated during the morning and evening travel peaks. Figure 7 As shown in Figure 2, the air conditioning load curves of typical summer days under different electric vehicle replacement rates are shown, where the four curves represent the load curves when the electric vehicle replacement rate is 0%, 30%, 60% and 80% respectively; Figure 7 It can be seen that when the replacement rate of electric vehicles is low, the reduction in air-conditioning load is more significant; when the replacement rate gradually increases, the change in air-conditioning load is slower; in addition, the volatility of the air-conditioning load is large, and the overall trend is a double peak at noon and in the evening; during the morning rush hour, due to the strong urban heat island effect, the air conditioning load begins to rise; and the fluctuation of the air-conditioning load is highly consistent with the travel arrangements of residents.

[0093] Embodiment 3:

[0094] This embodiment provides an air conditioning load prediction system considering electric vehicles and heat island effect, including:

[0095] The data acquisition module is configured to: obtain information about the area where the air conditioning load to be predicted is located;

[0096] The prediction module is configured to: obtain a prediction result according to the regional information and a preset air conditioning load prediction model;

[0097] Among them, the air-conditioning load prediction model is a regression equation, and the variables of the regression equation are the temperature determined under the urban heat island effect and the factors in the economic indicators; the temperature determined under the urban heat island effect is affected by the preset replacement rate of electric vehicles.

[0098] The working method of the system is the same as the air conditioning load prediction method considering electric vehicles and heat island effect in Example 1, and will not be repeated here.

[0099] Embodiment 4:

[0100] This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the steps of the air conditioning load prediction method considering electric vehicles and heat island effect described in Embodiment 1 are implemented.

[0101] Embodiment 5:

[0102] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the air conditioning load prediction method considering electric vehicles and heat island effects described in Example 1 are implemented.

[0103] The above description is only a preferred embodiment of the present embodiment and is not intended to limit the present embodiment. For those skilled in the art, the present embodiment may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present embodiment shall be included in the protection scope of the present embodiment.

Claims

1. An air conditioning load prediction method considering electric vehicles and heat island effect, characterized in that: include: Obtain information about the area where the air conditioning load to be predicted is located; Obtain prediction results based on regional information and the preset air conditioning load prediction model; Wherein, the air conditioning load prediction model is a regression equation, and the variables of the regression equation are the temperature determined under the urban heat island effect and the factors in the economic index; the temperature determined under the urban heat island effect is affected by the preset replacement rate of electric vehicles; The proportion of electric vehicles replacing fuel vehicles is the replacement rate; The temperature is determined according to the preset replacement rate of the electric vehicle, specifically: Determine the number of electric vehicles in the future according to the replacement rate, and obtain the reduction in automobile exhaust emissions as the number of electric vehicles increases: The reduction in automobile exhaust emissions is logarithmically related to the change in temperature. The temperature is determined based on the relationship between the reduction in automobile exhaust emissions and the change in temperature.

2. The air conditioning load prediction method considering electric vehicles and heat island effect as claimed in claim 1, characterized in that: The regional information at least includes factors of summer temperature and economic indicators preset in the area to be predicted.

3. The air conditioning load prediction method considering electric vehicles and heat island effect as claimed in claim 1, characterized in that: The factors in the economic indicators include at least one or more of per capita disposable income, urbanization rate and per capita household electricity consumption.

4. The air conditioning load prediction method considering electric vehicles and heat island effect as claimed in claim 3, characterized in that: The air conditioning load prediction model is: ,in, represents the average air conditioning load per capita, represents per capita disposable income, represents the urbanization rate, represents the per capita electricity consumption. Indicates temperature, , , , and All are coefficients.

5. The air conditioning load prediction method considering electric vehicles and heat island effect as claimed in claim 4, characterized in that: The construction of the air conditioning load prediction model includes: Acquire historical data of air conditioning load, perform regression analysis on the air conditioning load according to the historical data, analyze the relationship between per capita air conditioning load and economic indicators, and obtain a first air conditioning load prediction model; Temperature is introduced into the first air-conditioning load prediction model to obtain an air-conditioning load model that takes temperature influence into account, and the influence of electric vehicle development on the urban heat island effect and thus the influence on temperature is analyzed.

6. Air conditioning load prediction system considering electric vehicles and heat island effect, characterized in that: include: The data acquisition module is configured to: obtain information about the area where the air conditioning load to be predicted is located; The prediction module is configured to: obtain a prediction result according to the regional information and a preset air conditioning load prediction model; The air conditioning load prediction model is a regression equation, and the variables of the regression equation are the temperature determined under the urban heat island effect and the factors in the economic index; the temperature determined under the urban heat island effect is affected by the preset replacement rate of electric vehicles; The proportion of electric vehicles replacing fuel vehicles is the replacement rate; The temperature is determined according to the preset replacement rate of the electric vehicle, specifically: Determine the number of electric vehicles in the future according to the replacement rate, and obtain the reduction in automobile exhaust emissions as the number of electric vehicles increases: The reduction in automobile exhaust emissions is logarithmically related to the change in temperature. The temperature is determined based on the relationship between the reduction in automobile exhaust emissions and the change in temperature.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the air conditioning load prediction method considering electric vehicles and heat island effect as described in any one of claims 1 to 5 are implemented.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the air conditioning load prediction method considering electric vehicles and heat island effect as described in any one of claims 1 to 5 are implemented.

Images