Intelligent control method and system for power consumption of street lamps based on solar power generation

Abstract

The present invention relates to the field of energy consumption control technology. The present invention provides an intelligent control method and system for street lamp power consumption based on solar power generation. Based on the constructed utilization efficiency of factors in a second street lamp energy consumption information set, a second regression analysis parameter set is used to regress and analyze the second regression analysis energy production efficiency of the factors in the second street lamp energy consumption information set through a second regression analysis method, and the energy production efficiency of the factors in the second street lamp energy consumption information set is compared with the constructed energy production efficiency of the factors in the second street lamp energy consumption information set to obtain a second quality index. According to the comparison between the first quality index and the second quality index, a suitable regression analysis method can be screened out from the first regression analysis method and the second regression analysis method, and a factor energy production efficiency regression analysis can be performed on the power consumption data set to be processed. The regression analysis method selected in this way takes into account the different characteristics of the power consumption data set to be processed and is flexible. Therefore, the energy consumption control efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of energy consumption control, and in particular to an intelligent control method and system for power consumption of street lamps based on solar power generation. Background Art

[0002] Solar power generation refers to a power generation method that directly converts light energy into electrical energy without going through a thermal process. It includes photovoltaic power generation, photochemical power generation, photo-induction power generation and photobiological power generation. Photovoltaic power generation is a direct power generation method that uses solar-grade semiconductor electronic devices to effectively absorb solar radiation energy and convert it into electrical energy. It is the mainstream of solar power generation today. Among photochemical power generation, there are electrochemical photovoltaic cells, photoelectrolytic cells and photocatalytic cells. Currently, photovoltaic cells are used in practice.

[0003] Energy control is only required for street lamps powered by solar energy. Because the amount of solar energy generated varies with seasons and weather, there may be insufficient energy for street lamps to illuminate at night, resulting in a failure to illuminate. Therefore, an intelligent power control method is urgently needed to improve the above technical problems. Summary of the invention

[0004] In order to improve the technical problems existing in the related art, the present invention provides a method and system for intelligently controlling the power consumption of street lamps based on solar power generation.

[0005] In a first aspect, a method for intelligently controlling power consumption of street lamps based on solar power generation is provided, comprising:

[0006] The energy consumption attributes in the electric energy consumption data set to be processed are used to filter the first street lamp energy consumption information set and the second street lamp energy consumption information set that have been constructed;

[0007] Based on the constructed utilization efficiency and the constructed energy production efficiency of the factors in the first street lamp energy consumption information set, a first regression analysis parameter set is obtained, and a second regression analysis parameter set is obtained, wherein the first regression analysis parameter set is obtained by a first regression analysis method, and the second regression analysis parameter set is obtained by a second regression analysis method;

[0008] Based on the constructed utilization efficiency of the factors in the second street lamp energy consumption information set, using the first regression analysis parameter set, and through the first regression analysis method, regressing and analyzing the first regression analysis energy production efficiency of the factors in the second street lamp energy consumption information set, and determining a first quality indicator based on a comparison result of the constructed energy production efficiency of the factors in the second street lamp energy consumption information set and the first regression analysis energy production efficiency;

[0009] Based on the constructed utilization efficiency of the factors in the second street lamp energy consumption information set, using the second regression analysis parameter set, through the second regression analysis method, regressing the second regression analysis energy production efficiency of the factors in the second street lamp energy consumption information set, and determining the second quality indicator based on the comparison result of the constructed energy production efficiency of the factors in the second street lamp energy consumption information set and the second regression analysis energy production efficiency;

[0010] Based on the comparison between the first quality indicator and the second quality indicator, at least one of the first regression analysis method and the second regression analysis method is selected, and the factors of the power consumption data set to be processed are intelligently controlled to obtain an intelligent control processing result.

[0011] In the present invention, the energy consumption attribute in the to-be-processed electric energy consumption data set, screening the constructed first street lamp energy consumption information set and the second street lamp energy consumption information set, comprises:

[0012] Filtering the constructed second street lamp energy consumption information set, wherein the first sample data of the second street lamp energy consumption information set is similar to the electric energy consumption data set to be processed;

[0013] The constructed first street lamp energy consumption information set is screened, wherein the first street lamp energy consumption information set is similar to the second sample data of the second street lamp energy consumption information set, and the second sample data is opposite to the first sample data.

[0014] In the present invention, it is characterized in that the first regression analysis method includes:

[0015] Mining the constructed utilization efficiency of factors in the second street lamp energy consumption information set to obtain a second utilization rate mining result;

[0016] For the factors in the second street lamp energy consumption information set, based on the second utilization mining results of the factors and the second utilization mining results of similar factors in the second street lamp energy consumption information set, the first regression analysis parameter set is used to regress the first regression analysis energy production efficiency of the factors.

[0017] In the present invention, it is characterized in that the obtaining of the first regression analysis parameter set comprises:

[0018] Mining the constructed utilization efficiency of factors in the first street lamp energy consumption information set to obtain a first utilization rate mining result;

[0019] For the factors in the first street lamp energy consumption information set, the first utilization mining results of the factors, the first utilization mining results of similar factors in the first street lamp energy consumption information set and the constructed energy production efficiency of the factors are input into a first regression analysis algorithm to obtain a first regression analysis parameter set, wherein the first regression analysis algorithm is used for the first regression analysis method, and is an algorithm in which the energy production efficiency of the factors changes with the first utilization mining results of the factors and the first utilization mining results of similar factors to the factors based on the first regression analysis parameter set.

[0020] In the present invention, the first quality indicator is determined based on the comparison result of the constructed energy production efficiency of the factors in the second street lamp energy consumption information set and the first regression analysis energy production efficiency, including:

[0021] For the independent factors in the second street lamp energy consumption information set, determining a first comparison result between the constructed energy production efficiency of the independent factors and the first regression analysis energy production efficiency;

[0022] A first quality indicator is determined based on the first comparison result of each factor in the second street lamp energy consumption information set.

[0023] In the present invention, the second regression analysis method includes:

[0024] For the factors in the second street lamp energy consumption information set, screening a number of second key factors in the second street lamp energy consumption information set according to a specified rule;

[0025] According to the constructed utilization efficiencies of the plurality of the second key factors, the second regression analysis energy production efficiencies of the factors are regressively analyzed using the second regression analysis parameter set.

[0026] In the present invention, the specified rules include:

[0027] Determining the street lamp energy consumption in the second street lamp energy consumption information set, wherein the street lamp energy consumption is a set of several similar factors having a common utilization efficiency;

[0028] Determine the important factors of energy consumption of said street lamp;

[0029] A preset number of important factors that are ranked top in descending order of differences between the important factors and the factors are screened and determined as the key factors, where the preset number is an integer greater than 5.

[0030] In the present invention, obtaining the second regression analysis parameter set includes:

[0031] For the factors in the first street lamp energy consumption information set, screening a plurality of first key factors in the first street lamp energy consumption information set according to the specified rule;

[0032] The constructed utilization efficiencies of several of the first key factors and the constructed energy production efficiencies of the factors are input into a second regression analysis algorithm to obtain a second regression analysis parameter set, wherein the second regression analysis algorithm is used for the second regression analysis method, and is an algorithm in which the energy production efficiency of the factors changes with the constructed utilization efficiencies of several of the first key factors based on the second regression analysis parameter set.

[0033] In the present invention, the second quality index is determined based on the comparison result of the constructed energy production efficiency of the factors in the second street lamp energy consumption information set and the second regression analysis energy production efficiency, including:

[0034] For the independent factors in the second street lamp energy consumption information set, determining a second comparison result between the constructed energy production efficiency of the independent factors and the second regression analysis energy production efficiency;

[0035] A second quality indicator is determined based on the second comparison result of each factor in the second street lamp energy consumption information set.

[0036] In the present invention, based on the comparison between the first quality indicator and the second quality indicator, at least one of the first regression analysis method and the second regression analysis method is selected, and the factors of the power consumption data set to be processed are intelligently controlled to obtain the intelligent control processing result, including:

[0037] If the first quality index is less than the second quality index, the first regression analysis method is selected, and the factors of the power consumption data set to be processed are intelligently controlled to obtain an intelligent control processing result;

[0038] If the first quality index is not less than the second quality index, the second regression analysis method is selected, and the factors of the power consumption data set to be processed are intelligently controlled to obtain an intelligent control processing result.

[0039] In the present invention, based on the comparison between the first quality indicator and the second quality indicator, at least one of the first regression analysis method and the second regression analysis method is selected, and the factors of the power consumption data set to be processed are intelligently controlled to obtain the intelligent control processing result, including:

[0040] Determining a first weight and a second weight based on the first quality indicator and the second quality indicator;

[0041] Using the first regression analysis method, a regression analysis is performed on the energy production efficiency of the factors of the power consumption data set to be processed to obtain a first regression analysis feature vector;

[0042] Using the second regression analysis method, a regression analysis is performed on the energy production efficiency of the factors of the power consumption data set to be processed to obtain a second regression analysis feature vector;

[0043] The first weight and the second weight are used to perform a weighted sum operation on the first regression analysis feature vector and the second regression analysis feature vector to obtain a first regression analysis result.

[0044] In the present invention, after selecting at least one of the first regression analysis method and the second regression analysis method based on the comparison between the first quality indicator and the second quality indicator, performing intelligent control processing on the factors of the power consumption data set to be processed, and obtaining the intelligent control processing result, the method further includes:

[0045] Using a third regression analysis method, a regression analysis is performed on the energy production efficiency of the factors of the set of electric energy consumption data to be processed to obtain a second regression analysis result, wherein the third regression analysis method is different from the first regression analysis method and the second regression analysis method;

[0046] Based on the comparison between the initial energy production efficiency of the factor and the first regression analysis result and the comparison between the initial energy production efficiency of the factor and the second regression analysis result, at least one of the first regression analysis result and the second regression analysis result is screened to be determined as the regression analysis result of the factor.

[0047] In a second aspect, an intelligent control system for street lamp power consumption based on solar power generation is provided, comprising a processor and a memory communicating with each other, wherein the processor is used to read a computer program from the memory and execute it to implement the above method.

[0048] The intelligent control method and system for street lamp power consumption based on solar power generation provided in the embodiment of the present invention screens the constructed first street lamp energy consumption information set and the second street lamp energy consumption information set from the energy consumption attributes in the electric energy consumption data set to be processed. Since the first street lamp energy consumption information set and the second street lamp energy consumption information set have been constructed, the constructed utilization efficiency and the constructed energy production efficiency of each factor of them are known. Regardless of the regression analysis method adopted, it is necessary to first obtain the regression analysis parameter set for the regression analysis method, and then perform regression analysis based on the regression analysis parameter set. Therefore, the first regression analysis parameter set required for the first regression analysis method and the second regression analysis parameter set required for the second regression analysis method are obtained using the known constructed utilization efficiency and constructed energy production efficiency of each factor in the first street lamp energy consumption information set. Then, the two regression analysis methods are compared using the second street lamp energy consumption information set. Based on the constructed utilization efficiency of the factors in the second street lamp energy consumption information set, the first regression analysis parameter set is used, and the first regression analysis method is used to regress and analyze the first regression analysis energy production efficiency of the factors in the second street lamp energy consumption information set, and the first quality index is compared with the constructed energy production efficiency of the factors in the second street lamp energy consumption information set. Based on the constructed utilization efficiency of the factors in the second street lamp energy consumption information set, the second regression analysis parameter set is used, and the second regression analysis method is used to regress and analyze the second regression analysis energy production efficiency of the factors in the second street lamp energy consumption information set, and the second quality index is compared with the constructed energy production efficiency of the factors in the second street lamp energy consumption information set. According to the comparison of the first quality index and the second quality index, it is possible to screen out a suitable regression analysis method in the first regression analysis method and the second regression analysis method, and perform factor energy production efficiency regression analysis on the power consumption data set to be processed. The regression analysis method selected in this way takes into account the different characteristics of the power consumption data set to be processed and is flexible. Therefore, the energy consumption control efficiency is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0050] Figure 1 The present invention provides a flow chart of a method for intelligently controlling power consumption of a street lamp based on solar power generation. DETAILED DESCRIPTION

[0051] In order to better understand the above technical scheme, the technical scheme of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical scheme of the present invention, rather than limitations on the technical scheme of the present invention. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0052] See also Figure 1 , shows a method for intelligently controlling the power consumption of street lamps based on solar power generation, which method may include the technical solutions described in the following steps 410-450.

[0053] In step 410, the energy consumption attributes in the to-be-processed electric energy consumption data set are used to filter the constructed first street lamp energy consumption information set and the second street lamp energy consumption information set.

[0054] By screening different regression analysis methods according to different power consumption data sets, the flexibility and accuracy of regression analysis can be improved. The power consumption data set to be processed here is the basic unit of regression analysis.

[0055] Exemplarily, the energy consumption attribute in the present invention refers to information such as the time when a street light is turned on, the time when a street light is turned off, the power of the street light, and the number of street lights.

[0056] The first street lamp energy consumption information set refers to a street lamp energy consumption data set when it gets dark later in the summer (the sunshine is sufficient in the summer, the solar energy power generation is large, and the excess solar energy needs to be stored), and the second street lamp energy consumption information set refers to a street lamp energy consumption data set when it gets dark earlier in the winter.

[0057] The first street lamp energy consumption information set is a street lamp energy consumption information set that derives regression analysis parameter sets of different regression analysis methods. The second street lamp energy consumption information set is an evaluation street lamp energy consumption information set of different regression analysis methods. The key reason why different regression analysis methods are different is that different regression analysis formulas and regression analysis parameter sets are used. The regression analysis parameter sets of various candidate regression analysis methods can be obtained through the first street lamp energy consumption information set.

[0058] The energy consumption attribute in the to-be-processed electric energy consumption data set refers to an attribute that is similar to the to-be-processed electric energy consumption data set, or is not similar but the difference between the boundary and the to-be-processed electric energy consumption data set is less than a specified difference.

[0059] In one possible implementation example, step 410 may include but is not limited to steps 510 to 540 .

[0060] Step 510, obtaining energy consumption data characters to be processed;

[0061] Step 520, dividing the energy consumption data characters to be processed into an electric energy consumption data set;

[0062] Step 530: construct the power consumption data set according to the specified order;

[0063] Step 540: Filter the constructed first street lamp energy consumption information set and the second street lamp energy consumption information set by the energy consumption attributes in the to-be-processed electric energy consumption data set.

[0064] In another embodiment, a first street light energy consumption information set that has been constructed is filtered on the left side of the electric energy consumption data set to be processed, and a second street light energy consumption information set that has been constructed is filtered above the electric energy consumption data set to be processed, wherein the first sample data of the first street light energy consumption information set is similar to the electric energy consumption data set to be processed, the second sample data of the first street light energy consumption information set is corresponding to the first sample data of the first street light energy consumption information set, the first sample data of the second street light energy consumption information set is similar to the electric energy consumption data set to be processed, the second sample data of the second street light energy consumption information set is corresponding to the first sample data of the first street light energy consumption information set, and the sizes of the street light energy consumption information sets of the first street light energy consumption information set and the second street light energy consumption information set may be the same or different without limitation. Specifically, edge factors of the electric energy consumption data set to be processed are obtained, where the edge factors are factors that constitute the block outline of the electric energy consumption data set to be processed; based on the leftmost edge factor in the electric energy consumption data set to be processed, a preset number of column factors are screened on the left side of the electric energy consumption data set to be processed, and a street light energy consumption information set consisting of this series of factors is determined as a first street light energy consumption information set; then, based on the topmost edge factor in the electric energy consumption data set to be processed, a preset number of row factors are screened on the top of the electric energy consumption data set to be processed, and the street light energy consumption information set consisting of this series of factors is determined as a second street light energy consumption information set, and the number of factors contained in the first street light energy consumption information set and the second street light energy consumption information set may be equal or different.

[0065] In another embodiment, the constructed first street light energy consumption information set and the second street light energy consumption information set are screened on the left side of the power consumption data set to be processed, wherein the first sample data of the second street light energy consumption information set is similar to the power consumption data set to be processed, the first sample data of the first street light energy consumption information set is similar to the second sample data of the second street light energy consumption information set, and the second sample data of the first street light energy consumption information set is relative to the first sample data of the first street light energy consumption information set. The sizes of the street light energy consumption information sets of the first street light energy consumption information set and the second street light energy consumption information set can be the same or different without limitation. Specifically, edge factors of the set of electric energy consumption data to be processed are obtained, and the edge factors are factors constituting the block outline of the set of electric energy consumption data to be processed; according to the leftmost edge factors in the set of electric energy consumption data to be processed, a preset number of columns of factors are screened on the left side of the set of electric energy consumption data to be processed, and then the preset number of columns of factors are divided into two sets of street light energy consumption information in the vertical direction, wherein the set of street light energy consumption information close to the set of electric energy consumption data to be processed is determined as the second set of street light energy consumption information, and the set of street light energy consumption information relatively far from the set of electric energy consumption data to be processed is determined as the first set of street light energy consumption information, the right side of the second set of street light energy consumption information is similar to the set of electric energy consumption data to be processed, the left side of the second set of street light energy consumption information is similar to the right side of the first set of street light energy consumption information, and the left side of the first set of street light energy consumption information is opposite to the right side of the first set of street light energy consumption information. The number of factors included in the first set of street light energy consumption information and the second set of street light energy consumption information may be equal or different. Since the second street lamp energy consumption information set is closer to the pending electric energy consumption data set, and the second street lamp energy consumption information set is the verification street lamp energy consumption information set, the closer the difference between the verification street lamp energy consumption information set and the pending electric energy consumption data set is, the more the regression analysis accuracy can be improved.

[0066] Through the above steps 510 to 540, the embodiment of the present disclosure can more conveniently screen the first street lamp energy consumption information set and the second street lamp energy consumption information set that have been constructed in the energy consumption attributes in the electric energy consumption data set to be processed. Since the first street lamp energy consumption information set and the second street lamp energy consumption information set have been constructed, the constructed utilization efficiency and the constructed energy production efficiency of each factor of them are known. Therefore, the first street lamp energy consumption information set can be used to obtain the regression analysis parameter set, and the second street lamp energy consumption information set can be used to verify the accuracy of the regression analysis, which can improve the calculation accuracy and verification accuracy of the regression analysis parameter set.

[0067] Step 420: Based on the constructed utilization efficiency and the constructed energy production efficiency of the factors in the first street lamp energy consumption information set, obtain a first regression analysis parameter set and obtain a second regression analysis parameter set;

[0068] Exemplarily, utilization efficiency can be understood as the ratio of electric energy lost during use to the total electric energy to obtain the loss rate, and 1-loss rate is the utilization rate of electric energy. The reasons for the loss of electric energy include the loss of electric energy during transmission due to resistance, temperature and other factors. Energy production efficiency refers to the efficiency of solar power generation (solar energy is a renewable energy source. It refers to the thermal radiation energy of the sun, which is mainly manifested in the so-called sunlight. In modern times, it is generally used to generate electricity or provide energy for water heaters.).

[0069] Next, in step 420, the constructed utilization efficiency and the constructed energy production efficiency of the factors of the first street lamp energy consumption information set are used to obtain a first regression analysis parameter set and a second regression analysis parameter set, wherein the first regression analysis parameter set and the second regression analysis parameter set both contain at least one regression analysis parameter, the first regression analysis parameter set is obtained by a first regression analysis method, and the second regression analysis parameter set is obtained by a second regression analysis method. The first regression analysis method and the second regression analysis method can both realize the chromaticity of the electric energy consumption data set by constructing a brightness regression analysis based on the electric energy consumption data set, but the specific implementation processes of the first regression analysis method and the second regression analysis method are different, therefore, it is necessary to obtain the first regression analysis parameter set corresponding to the first regression analysis method and the second regression analysis parameter set corresponding to the second regression analysis method, respectively.

[0070] In one possible implementation example, the specific process of obtaining the first regression analysis parameter set in step 420 may include but is not limited to steps 910 to 920 .

[0071] Step 910: mining the constructed utilization efficiency of factors in the first street lamp energy consumption information set to obtain a first utilization rate mining result;

[0072] Step 920: for the factors in the first street lamp energy consumption information set, the first utilization mining results of the factors, the first utilization mining results of similar factors in the first street lamp energy consumption information set and the constructed energy production efficiency of the factors are input into the first regression analysis algorithm to obtain the first regression analysis parameter set.

[0073] In step 920, for the factors in the first street lamp energy consumption information set, the first utilization mining results of the factors, the first utilization mining results of similar factors in the first street lamp energy consumption information set, and the constructed energy production efficiency of the factors are input into a first regression analysis algorithm to obtain a first regression analysis parameter set, specifically including:

[0074] determining similar factors of factors in the first street lamp energy consumption information set;

[0075] Extracting first utilization mining results of factors in the first street lamp energy consumption information set, first utilization mining results of similar factors of the factors, and constructed energy production efficiency of the factors;

[0076] The first utilization mining result of the factor, the first utilization mining result of similar factors in the first street lamp energy consumption information set and the constructed energy production efficiency of the factor are input into the first regression analysis algorithm to obtain the first regression analysis parameter set.

[0077] Therefore, when using the first regression analysis method to perform regression analysis on the factors of the power consumption data set to be processed, it is necessary to solve the specific value of each regression analysis parameter in the first regression analysis parameter set of the first regression analysis algorithm, that is, it is necessary to obtain the first regression analysis parameter set.

[0078] Through the above steps 910 to 920, the embodiment of the present disclosure can more conveniently use the known constructed utilization efficiency and constructed energy production efficiency of each factor in the first street lamp energy consumption information set to obtain the first regression analysis parameter set required by the first regression analysis method. Since the above steps show multiple ways to obtain the first regression analysis parameter set, the calculation accuracy and screening flexibility of the first regression analysis parameter set can be improved.

[0079] In one possible implementation example, the specific process of obtaining the second regression analysis parameter set in step 420 may include but is not limited to steps 1310 to 1320 .

[0080] Step 1310: for the factors in the first street lamp energy consumption information set, filter a plurality of first key factors in the first street lamp energy consumption information set according to a specified rule;

[0081] Step 1320: Input the constructed utilization efficiencies of the first key factors and the constructed energy production efficiencies of the factors into a second regression analysis algorithm to obtain a second regression analysis parameter set.

[0082] In one embodiment, the specified rules include:

[0083] Determine the street lamp energy consumption in the first street lamp energy consumption information set, where the street lamp energy consumption is a set of several similar factors with common utilization efficiency;

[0084] Important factors in determining the energy consumption of street lights;

[0085] A preset number of important factors that are ranked top from large to small based on the difference between the screening important factors and the factors are determined as the first key factors, and the preset number is an integer greater than 5.

[0086] In step 1320, since the factors of the first street lamp energy consumption information set have been factor-constructed, the constructed utilization efficiencies of several first key factors and the constructed energy production efficiencies of the factors in the first street lamp energy consumption information set can be directly extracted.

[0087] When the second regression analysis method is used to perform regression analysis on the factors of the power consumption data set to be processed, it is necessary to solve the specific value of each regression analysis parameter in the second regression analysis parameter set of the second regression analysis algorithm, that is, it is necessary to obtain the second regression analysis parameter set.

[0088] Through the above steps 1310 to 1320, the embodiment of the present disclosure can conveniently use the known constructed utilization efficiency and constructed energy production efficiency of each factor in the first street lamp energy consumption information set to obtain the second regression analysis parameter set required by the second regression analysis method. Since the above steps show multiple ways to obtain the second regression analysis parameter set, the calculation accuracy and screening flexibility of the second regression analysis parameter set can be improved.

[0089] Step 430: Based on the constructed utilization efficiency of the factors in the second street lamp energy consumption information set, using the first regression analysis parameter set, regressing the first regression analysis energy production efficiency of the factors in the second street lamp energy consumption information set through the first regression analysis method, and determining the first quality indicator based on the comparison result of the constructed energy production efficiency of the factors in the second street lamp energy consumption information set and the first regression analysis energy production efficiency;

[0090] For example, the quality indicator can be understood as loss. For example, if the solar radiation time is a, the power generation value calculated according to the theoretical value is x, but the actual power generation is y, x is greater than y, and the value obtained by xy is the loss.

[0091] Next, in step 430, the constructed utilization efficiency of the factors in the second street lamp energy consumption information set is mined to obtain a second utilization mining result. The second utilization mining result corresponds to the constructed energy production efficiency. Further, for the factors in the second street lamp energy consumption information set, the first regression analysis energy production efficiency of the factors is regressed using the first regression analysis parameter set, the second utilization mining result of the factors, and the second utilization mining result of similar factors in the second street lamp energy consumption information set.

[0092] In one possible implementation example, step 430 may include but is not limited to steps 1710 to 1720 .

[0093] Step 1710: mining the constructed utilization efficiency of the factors in the second street lamp energy consumption information set to obtain a second utilization rate mining result;

[0094] Step 1720: for the factors in the second street lamp energy consumption information set, based on the second utilization mining results of the factors and the second utilization mining results of similar factors in the second street lamp energy consumption information set, using the first regression analysis parameter set, regress the first regression analysis energy production efficiency of the factors.

[0095] Step 1710 is similar to step 910, except that step 910 mines the constructed utilization efficiency of the factors in the first street light energy consumption information set to obtain a first utilization mining result (used to obtain a first regression analysis parameter set), while step 1710 mines the constructed utilization efficiency of the factors in the second street light energy consumption information set to obtain a second utilization mining result (used for regression analysis of the first regression analysis energy production efficiency of the factors in the second street light energy consumption information set).

[0096] In step 1720, for the factors in the second street lamp energy consumption information set, according to the second utilization mining results of the factors and the second utilization mining results of similar factors in the second street lamp energy consumption information set, using the first regression analysis parameter set, the first regression analysis energy production efficiency of the regression analysis factors includes:

[0097] determining similar factors of the factors in the second street lamp energy consumption information set;

[0098] The first regression analysis energy production efficiency of the factor is regressed by using the second utilization mining results of the factors in the first regression analysis parameter set and the second street lamp energy consumption information set and the second utilization mining results of the similar factors of the factors.

[0099] In one possible implementation example, step 430 may include but is not limited to steps 1810 to 1820 .

[0100] Step 1810: for the independent factors in the second street lamp energy consumption information set, determine a first comparison result of the constructed energy production efficiency of the independent factors and the first regression analysis energy production efficiency;

[0101] Step 1820: Determine a first quality indicator based on a first comparison result of each factor in the second street lamp energy consumption information set.

[0102] Through the above-mentioned step 430, the embodiment of the present disclosure can more conveniently use the constructed energy production efficiency of the factors in the second street lamp energy consumption information set and the first regression analysis value to verify the regression analysis accuracy of the first regression analysis method. Since the second street lamp energy consumption information set is similar to the electric energy consumption data set to be processed, the first quality indicator of the second street lamp energy consumption information set can more clearly and objectively reflect the suitability of using the first regression analysis method to perform regression analysis on the factors of the electric energy consumption data set to be processed, which can improve the accuracy of the regression analysis.

[0103] Step 440: Based on the constructed utilization efficiency of the factors in the second street lamp energy consumption information set, using the second regression analysis parameter set, and through the second regression analysis method, regressing and analyzing the second regression analysis energy production efficiency of the factors in the second street lamp energy consumption information set, and determining the second quality indicator based on the comparison result between the constructed energy production efficiency of the factors in the second street lamp energy consumption information set and the second regression analysis energy production efficiency;

[0104] Next, in step 440, for the factors in the second street lamp energy consumption information set, several second key factors in the second street lamp energy consumption information set are screened according to specified rules, and the second regression analysis energy production efficiency of the regression analysis factors is obtained by using the second regression analysis parameter set and the constructed utilization efficiency of the several second key factors.

[0105] In one possible implementation example, step 440 may include but is not limited to steps 1910 to 1920 .

[0106] Step 1910: for the factors in the second street lamp energy consumption information set, filter a plurality of second key factors in the second street lamp energy consumption information set according to a specified rule;

[0107] Step 1920: Based on the constructed utilization efficiencies of the plurality of second key factors, a second regression analysis energy production efficiency is performed using a second regression analysis parameter set.

[0108] In step 1910, step 1910 is similar to step 1310, except that step 1310 is for factors in the first street light energy consumption information set, and screens several first key factors in the first street light energy consumption information set according to specified rules (used to obtain a second regression analysis parameter set), while step 1910 is for factors in the second street light energy consumption information set, and screens several second key factors in the second street light energy consumption information set according to specified rules (used for regression analysis of the second regression analysis energy production efficiency of the factors in the second street light energy consumption information set).

[0109] In one possible implementation example, step 440 may include but is not limited to steps 2010 to 2020 .

[0110] Step 210: for the independent factors in the second street lamp energy consumption information set, determine a second comparison result of the constructed energy production efficiency of the independent factors and the second regression analysis energy production efficiency;

[0111] Step 2020: Determine a second quality indicator based on a second comparison result of each factor in the second street lamp energy consumption information set.

[0112] Through the above-mentioned step 440, the embodiment of the present disclosure can more conveniently use the constructed energy production efficiency and the second regression analysis value of the factors in the second street lamp energy consumption information set to verify the regression analysis accuracy of the second regression analysis method. Since the second street lamp energy consumption information set is similar to the electric energy consumption data set to be processed, the second quality indicator of the second street lamp energy consumption information set can more clearly and objectively reflect the suitability of using the second regression analysis method to perform regression analysis on the factors of the electric energy consumption data set to be processed, which can improve the accuracy of the regression analysis.

[0113] Step 450: Based on the comparison between the first quality index and the second quality index, at least one of the first regression analysis method and the second regression analysis method is selected, and the factors of the power consumption data set to be processed are intelligently controlled to obtain an intelligent control processing result.

[0114] In one possible implementation example, step 450 may include but is not limited to step 2110 and step 2120 .

[0115] Step 2110: If the first quality index is less than the second quality index, select the first regression analysis method, perform intelligent control processing on the factors of the power consumption data set to be processed, and obtain an intelligent control processing result;

[0116] Step 2120: If the first quality index is not less than the second quality index, select the second regression analysis method, perform intelligent control processing on the factors of the power consumption data set to be processed, and obtain an intelligent control processing result.

[0117] In this embodiment, the first regression analysis method is selected to perform intelligent control processing on the factors of the power consumption data set to be processed, and the intelligent control processing results obtained specifically include:

[0118] Step a1, filtering the constructed third street lamp energy consumption information set by energy consumption attributes in the power consumption data set to be processed;

[0119] Step b1, obtaining a first regression analysis parameter set based on the constructed utilization efficiency and the constructed energy production efficiency of the third street lamp energy consumption information set;

[0120] Step c1: Based on the constructed utilization efficiency of the factors in the power consumption data set to be processed, using the first regression analysis parameter set and through the first regression analysis method, intelligent control processing is performed on the factors in the power consumption data set to be processed to obtain intelligent control processing results.

[0121] Step 410 is to filter the first street lamp energy consumption information set and the second street lamp energy consumption information set (used to verify the first regression analysis method and the second regression analysis method) by the energy consumption attribute in the power consumption data set to be processed, and step a1 is to filter the third street lamp energy consumption information set (used to obtain the first regression analysis parameter set) by the energy consumption attribute in the power consumption data set to be processed. Therefore, calculating the first regression analysis parameter set based on the filtered third street lamp energy consumption information set can improve the calculation accuracy and further improve the accuracy of the factor regression analysis.

[0122] Step b1 is similar to steps 910-920, except that steps 910-920 are based on obtaining a first regression analysis parameter set based on a constructed first street lamp energy consumption information set (the first regression analysis parameter set is used to verify the first regression analysis method), while step b1 is based on a third street lamp energy consumption information set to obtain a first regression analysis parameter set (the first regression analysis parameter set is used to perform regression analysis on the energy production efficiency of the factors of the power consumption data set to be processed).

[0123] Step c1 is similar to steps 1710-1720, with the difference being that steps 1710-1720 are to perform a regression analysis on the energy production efficiency of the factors in the second street lamp energy consumption information set to obtain a first regression analysis energy production efficiency for verifying the first regression analysis method, while step c1 is to perform a regression analysis on the energy production efficiency of the factors in the power consumption data set to be processed to obtain a first regression analysis result of the factors in the power consumption data set to be processed.

[0124] In this embodiment, the second regression analysis method is selected to perform intelligent control processing on the factors of the power consumption data set to be processed, and the intelligent control processing results obtained specifically include:

[0125] Step a2, filtering the constructed third street lamp energy consumption information set by energy consumption attributes in the power consumption data set to be processed;

[0126] Step b2: obtaining a second regression analysis parameter set based on the constructed utilization efficiency and the constructed energy production efficiency of the third street lamp energy consumption information set;

[0127] Step c2: Based on the constructed utilization efficiency of the factors in the power consumption data set to be processed, the factors in the power consumption data set to be processed are intelligently controlled and processed by the second regression analysis method using the second regression analysis parameter set to obtain intelligent control processing results.

[0128] Step a2 is similar to step a1, except that, in step a1, a third street lamp energy consumption information set (used to obtain a first regression analysis parameter set) is constructed by screening the energy consumption attributes in the electric energy consumption data set to be processed, while in step a2, a third street lamp energy consumption information set (used to obtain a second regression analysis parameter set) is constructed by screening the energy consumption attributes in the electric energy consumption data set to be processed.

[0129] Step b2 is similar to steps 1310-1320, except that steps 1310-1320 are based on the constructed first street light energy consumption information set to obtain the second regression analysis parameter set (the second regression analysis parameter set is used to verify the second regression analysis method), while step b2 is based on the third street light energy consumption information set to obtain the second regression analysis parameter set (the second regression analysis parameter set is used to perform regression analysis on the energy production efficiency of the factors of the power consumption data set to be processed).

[0130] Step c2 is similar to steps 1910-1920, with the difference that steps 1910-1920 perform a regression analysis on the energy production efficiency of the factors in the second street lamp energy consumption information set to obtain a second regression analysis energy production efficiency for verifying the second regression analysis method, while step c2 performs a regression analysis on the energy production efficiency of the factors in the power consumption data set to be processed to obtain a first regression analysis result of the factors in the power consumption data set to be processed.

[0131] Through the above steps 2110 and 2120, the disclosed embodiment can select a suitable regression analysis method from the first regression analysis method and the second regression analysis method to perform factor energy production efficiency regression analysis on the power consumption data set to be processed based on the comparison of the first quality index and the second quality index. The regression analysis method selected in this way takes into account the different characteristics of the power consumption data set to be processed and is flexible. Since the regression analysis method selected in this way has been actually verified in the first street lamp energy consumption information set and the second street lamp energy consumption information set, the energy consumption control efficiency is improved.

[0132] It should be noted that although the above step 2110 shows a method in which the first regression analysis method regresses the energy production efficiency of factors based on a first regression analysis parameter set, the first regression analysis method in step 2110 can also regress the energy production efficiency of factors based on other regression analysis parameter sets, and is not limited to this.

[0133] In one possible implementation example, step 420 may also include but is not limited to steps 2310 to 2320 .

[0134] Step 2310: mining the constructed utilization efficiency of factors in the first street lamp energy consumption information set to obtain a first utilization rate mining result;

[0135] Step 2320: for the factors in the first street lamp energy consumption information set, input the constructed energy production efficiency and the first utilization rate mining results of the factors into the third regression analysis algorithm to obtain a third regression analysis parameter set.

[0136] Step 2310 is similar to step 910, except that step 910 mines the constructed utilization efficiency of the factors in the first street lamp energy consumption information set to obtain a first utilization mining result (used to obtain a first regression analysis parameter set), while step 2310 mines the constructed utilization efficiency of the factors in the first street lamp energy consumption information set to obtain a first utilization mining result (used to obtain a third regression analysis parameter set).

[0137] In step 2320, since the factors of the first street lamp energy consumption information set have been factor constructed, the first utilization mining results of the factors in the first street lamp energy consumption information set and the constructed energy production efficiency of the factors can be directly extracted.

[0138] Therefore, when using the first regression analysis method to perform regression analysis on the factors of the power consumption data set to be processed, it is necessary to solve the specific value of each regression analysis parameter in the third regression analysis parameter set of the third regression analysis algorithm, that is, it is necessary to obtain the third regression analysis parameter set.

[0139] Through the above steps 2310-2320, the embodiment of the present disclosure can more conveniently utilize the known constructed utilization efficiency and constructed energy production efficiency of each factor in the first street lamp energy consumption information set to obtain the third regression analysis parameter set required by the first regression analysis method, so that the first regression analysis method can implement factor regression analysis based on the first regression analysis parameter set, and can also implement factor regression analysis based on the third regression analysis parameter set, which can improve the screening flexibility of the first regression analysis method.

[0140] In one possible implementation example, step 430 may also include but is not limited to steps 2410 to 2420 .

[0141] Step 2410: mining the constructed utilization efficiency of the factors in the second street lamp energy consumption information set to obtain a second utilization rate mining result;

[0142] Step 2430: for the factors in the second street lamp energy consumption information set, based on the second utilization rate mining results of the factors, and using the third regression analysis parameter set, regressively analyze the first regression analysis energy production efficiency of the factors.

[0143] Step 2410 is similar to step 910, except that step 910 mines the constructed utilization efficiency of the factors in the first street light energy consumption information set to obtain a first utilization mining result (used to obtain a first regression analysis parameter set), while step 2410 mines the constructed utilization efficiency of the factors in the second street light energy consumption information set to obtain a second utilization mining result (used for regression analysis of the first regression analysis energy production efficiency of the factors in the second street light energy consumption information set).

[0144] Through the above steps 2410-2420, the first regression analysis method of the embodiment of the present disclosure can perform regression analysis on the energy production efficiency of the factors in the second street lamp energy consumption information set based on the third regression analysis parameter set, which can improve the screening flexibility of the first regression analysis method.

[0145] In this embodiment, using the first regression analysis method, performing energy production efficiency regression analysis on factors of the power consumption data set to be processed based on the third regression analysis parameter set includes:

[0146] Step a3, filtering the constructed third street lamp energy consumption information set by energy consumption attributes in the power consumption data set to be processed;

[0147] Step b3: obtaining a third regression analysis parameter set based on the constructed utilization efficiency and the constructed energy production efficiency of the third street lamp energy consumption information set;

[0148] Step c3: Based on the constructed utilization efficiency of the factors in the power consumption data set to be processed, using the third regression analysis parameter set and through the first regression analysis method, intelligent control processing is performed on the factors in the power consumption data set to be processed to obtain intelligent control processing results.

[0149] Step a3 is similar to step a1, except that, in step a1, a third street lamp energy consumption information set (used to obtain a first regression analysis parameter set) is constructed by screening the energy consumption attributes in the electric energy consumption data set to be processed, while in step a3, a third street lamp energy consumption information set (used to obtain a third regression analysis parameter set) is constructed by screening the energy consumption attributes in the electric energy consumption data set to be processed.

[0150] Step b3 is similar to steps 2310-2320, except that steps 2310-2320 are based on the constructed first street lamp energy consumption information set to obtain the third regression analysis parameter set (the third regression analysis parameter set is used to verify the first regression analysis method), while step b3 is based on the third street lamp energy consumption information set to obtain the third regression analysis parameter set (the third regression analysis parameter set is used to perform regression analysis on the energy production efficiency of the factors of the power consumption data set to be processed).

[0151] Step c2 is similar to steps 2410-2420, with the difference being that steps 2410-2420 are to perform a regression analysis on the energy production efficiency of the factors in the second street lamp energy consumption information set to obtain a first regression analysis energy production efficiency for verifying the first regression analysis method, while step c3 is to perform a regression analysis on the energy production efficiency of the factors in the power consumption data set to be processed to obtain a first regression analysis result of the factors in the power consumption data set to be processed.

[0152] Although the above step 2120 shows that the second regression analysis method regresses the energy production efficiency of the factors based on the second regression analysis parameter set, the second regression analysis method in step 2120 can also regress the energy production efficiency of the factors based on other regression analysis parameter sets.

[0153] In one possible implementation example, step 450 may include but is not limited to steps 2610 to 2640 .

[0154] Step 2610: Determine a first weight and a second weight based on the first quality indicator and the second quality indicator;

[0155] Step 2620: Using a first regression analysis method, perform a regression analysis on the energy production efficiency of the factors of the power consumption data set to be processed to obtain a first regression analysis feature vector;

[0156] Step 2630: Using a second regression analysis method, perform regression analysis on the energy production efficiency of the factors of the power consumption data set to be processed to obtain a second regression analysis feature vector;

[0157] Step 2640: Use the first weight and the second weight to perform a weighted sum operation on the first regression analysis feature vector and the second regression analysis feature vector to obtain a first regression analysis result.

[0158] In step 2610, since the first quality indicator and the second quality indicator can intuitively reflect the suitability of the first regression analysis method and the second regression analysis method for performing regression analysis on the factors of the processed power consumption data set, the ratio of the first quality indicator and the second quality indicator can be calculated to obtain the quality indicator ratio, and the inverse of the quality indicator ratio can be obtained, and the first weight and the second weight can be determined according to the inverse ratio result.

[0159] In step 2640, when using the first weight and the second weight to perform a weighted sum operation on the first regression analysis feature vector and the second regression analysis feature vector, the first weight and the first regression analysis feature vector are multiplied to obtain a first product result, and then the second weight and the second regression analysis feature vector are multiplied to obtain a second product result. Finally, the first product result and the second product result are summed to obtain the first regression analysis result.

[0160] Through the above steps 2610-2640, the embodiment of the present disclosure can simultaneously use the first regression analysis method and the second regression analysis method to perform regression analysis on the energy production efficiency of the factors of the processed power consumption data set, and superimpose the two regression analysis results to obtain the first regression analysis result, which can integrate the advantages of the first regression analysis method and the second regression analysis method, improve the accuracy of the factor regression analysis, and also improve the screening diversity and screening flexibility of the regression analysis method.

[0161] Through the above steps 410-450, the embodiment of the present disclosure takes into account that there may be different parts in the video frame to be encoded, and each part may have its own suitable regression analysis method. The embodiment of the present disclosure does not use a single regression analysis method to perform regression analysis on all parts of the video frame, but flexibly selects a suitable regression analysis method for regression analysis according to the specific situation of the power consumption data set to be processed in the video frame. Specifically, the energy consumption attributes in the power consumption data set to be processed are screened for the first street lamp energy consumption information set and the second street lamp energy consumption information set that have been constructed. Since the first street lamp energy consumption information set and the second street lamp energy consumption information set have been constructed, the constructed utilization efficiency and the constructed energy production efficiency of each factor of them are known. Regardless of which regression analysis method is used, the regression analysis parameter set for the regression analysis method must be obtained first, and then the regression analysis is performed according to the regression analysis parameter set. Therefore, the first regression analysis parameter set required for the first regression analysis method and the second regression analysis parameter set required for the second regression analysis method are obtained using the known constructed utilization efficiency and constructed energy production efficiency of each factor in the first street lamp energy consumption information set. Then, the two regression analysis methods are compared using the second street lamp energy consumption information set. Based on the constructed utilization efficiency of the factors in the second street lamp energy consumption information set, the first regression analysis parameter set is used, and the first regression analysis method is used to regress and analyze the first regression analysis energy production efficiency of the factors in the second street lamp energy consumption information set, and the first quality index is compared with the constructed energy production efficiency of the factors in the second street lamp energy consumption information set. Based on the constructed utilization efficiency of the factors in the second street lamp energy consumption information set, the second regression analysis parameter set is used, and the second regression analysis method is used to regress and analyze the second regression analysis energy production efficiency of the factors in the second street lamp energy consumption information set, and the second quality index is compared with the constructed energy production efficiency of the factors in the second street lamp energy consumption information set. According to the comparison of the first quality index and the second quality index, it is possible to screen out a suitable regression analysis method in the first regression analysis method and the second regression analysis method, and perform factor energy production efficiency regression analysis on the power consumption data set to be processed. The regression analysis method selected in this way takes into account the different characteristics of the power consumption data set to be processed and is flexible. Since the regression analysis method selected in this way has been actually verified in the first street lamp energy consumption information set and the second street lamp energy consumption information set, the energy consumption control efficiency is improved.

[0162] Comparison between the first regression analysis method, the second regression analysis method and other regression analysis methods.

[0163] In the above embodiment, the energy production efficiency of the factors of the power consumption data set to be processed is intelligently controlled and processed according to at least one of the first regression analysis method and the second regression analysis method to obtain an intelligent control processing result. However, the regression analysis method in this field is not limited to the first regression analysis method and the second regression analysis method. In one embodiment, other regression analysis methods can be used to perform regression analysis on the energy production efficiency of the factors of the power consumption data set to be processed to obtain regression analysis results. For different video energy consumption data characters, there is a possibility that the regression analysis results of other regression analysis methods are better than the first regression analysis results. Therefore, other regression analysis methods can be further used to perform regression analysis on the energy production efficiency of the factors of the power consumption data set to be processed to obtain regression analysis results, and more suitable regression analysis results can be screened from the regression analysis results of other regression analysis methods and the first regression analysis results to determine as the regression analysis results of the factors.

[0164] In one possible implementation example, the intelligent control method for power consumption of street lamps based on solar power generation according to the embodiment of the present disclosure may include, but is not limited to, steps 2710 to 2720 after step 450 .

[0165] Step 2710: Using a third regression analysis method, a regression analysis is performed on the energy production efficiency of the factors of the power consumption data set to be processed to obtain a second regression analysis result;

[0166] Step 2720: based on the comparison between the initial energy production efficiency of the factor and the first regression analysis result and the comparison between the initial energy production efficiency of the factor and the second regression analysis result, screen at least one regression analysis result of the first regression analysis result and the second regression analysis result to be determined as the factor.

[0167] In step 2720, since there may be different parts in the video frame to be encoded, each part may have its own suitable regression analysis method. For example, a part of the video content in the video frame to be encoded is suitable for factor regression analysis using the first regression analysis method and the second regression analysis method. At this time, the first regression analysis result will be more accurate and the first regression analysis result will be more suitable for determination as the final regression analysis result; while the other part is suitable for factor regression analysis using other regression analysis methods. At this time, the second regression analysis result will be more accurate and the second regression analysis result will be more suitable for determination as the final regression analysis result. Therefore, it is necessary to screen at least one regression analysis result of the first regression analysis result and the second regression analysis result to be determined as the factor based on the comparison between the initial energy production efficiency of the factor and the first regression analysis result and the comparison between the initial energy production efficiency of the factor and the second regression analysis result.

[0168] Step 2720 may include, but is not limited to, steps 2810 to 2850 .

[0169] Step 2810: for the independent factors in the power consumption data set to be processed, determine the third difference between the initial energy production efficiency of the independent factors and the first regression analysis result;

[0170] Step 2820: determining a third quality indicator based on the third difference of each factor in the power consumption data set to be processed;

[0171] Step 2830: for the independent factors in the power consumption data set to be processed, determine the fourth difference between the initial energy production efficiency of the independent factors and the second regression analysis result;

[0172] Step 2840: determining a fourth quality indicator based on the fourth difference of each factor in the power consumption data set to be processed;

[0173] Step 2850: Based on the comparison between the third quality index and the fourth quality index, at least one regression analysis result determined as a factor in the first regression analysis result and the second regression analysis result is screened.

[0174] Step 2810 is similar to step 1810, except that step 1810 determines the first comparison result (used to obtain the first comparison result) between the constructed energy production efficiency of the independent factor and the energy production efficiency of the first regression analysis for the factors in the second street lamp energy consumption information set, while step 2810 determines the third difference (used to obtain the third difference) between the initial energy production efficiency of the independent factor and the first regression analysis result for the factors in the electric energy consumption data set to be processed.

[0175] In step 2840, based on the comparison between the third quality index and the fourth quality index, at least one regression analysis result determined as a factor in the first regression analysis result and the second regression analysis result is screened, including:

[0176] Based on the comparison between the third quality indicator and the fourth quality indicator, screening the regression analysis result determined as the factor by the first regression analysis result or the second regression analysis result;

[0177] or,

[0178] Based on the comparison between the third quality index and the fourth quality index, the first regression analysis result and the second regression analysis result are screened and determined as the regression analysis results of the factors.

[0179] On the basis of the above, an intelligent control system for street lamp power consumption based on solar power generation is shown, including a processor and a memory that communicate with each other, and the processor is used to read and execute a computer program from the memory to implement the above method.

[0180] Based on the above, a computer-readable storage medium is also provided, on which a computer program stored implements the above method when running.

[0181] In summary, based on the above scheme, the energy consumption attributes in the set of electric energy consumption data to be processed are used to screen the constructed first street lamp energy consumption information set and the second street lamp energy consumption information set. Since the first street lamp energy consumption information set and the second street lamp energy consumption information set have been constructed, the constructed utilization efficiency and the constructed energy production efficiency of each factor of them are known. Regardless of the regression analysis method used, the regression analysis parameter set used for the regression analysis method must be obtained first, and then the regression analysis is performed according to the regression analysis parameter set. Therefore, the first regression analysis parameter set required for the first regression analysis method and the second regression analysis parameter set required for the second regression analysis method are obtained by using the known constructed utilization efficiency and constructed energy production efficiency of each factor in the first street lamp energy consumption information set. Then, the second street lamp energy consumption information set is used to compare the two regression analysis methods. Based on the constructed utilization efficiency of the factors in the second street lamp energy consumption information set, the first regression analysis parameter set is used to regress and analyze the first regression analysis energy production efficiency of the factors in the second street lamp energy consumption information set through the first regression analysis method, and compared with the constructed energy production efficiency of the factors in the second street lamp energy consumption information set to obtain the first quality indicator. Based on the constructed utilization efficiency of the factors in the second street light energy consumption information set, using the second regression analysis parameter set, through the second regression analysis method, the second regression analysis energy production efficiency of the factors in the second street light energy consumption information set is regressed and analyzed, and compared with the constructed energy production efficiency of the factors in the second street light energy consumption information set to obtain the second quality index. According to the comparison of the first quality index and the second quality index, it is possible to screen out a suitable regression analysis method in the first regression analysis method and the second regression analysis method, and perform factor energy production efficiency regression analysis on the power consumption data set to be processed. The regression analysis method selected in this way takes into account the different characteristics of the power consumption data set to be processed and is flexible. Therefore, the energy consumption control efficiency is improved.

[0182] It should be understood that the system and its modules shown above can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented by hardware, software, or a combination of software and hardware. Among them, the hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or a dedicated design hardware. Those skilled in the art will understand that the above methods and systems can be implemented using computer executable instructions and / or included in processor control codes, such as carrier media such as disks, CDs or DVD-ROMs, programmable memories such as read-only memories (firmware), or data carriers such as optical or electronic signal carriers. Such codes are provided on. The system and its modules of the present invention can be implemented not only by hardware circuits such as ultra-large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but can also be implemented by software such as executed by various types of processors, and can also be implemented by a combination of the above hardware circuits and software (e.g., firmware).

[0183] It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced may be any one or a combination of the above, or any other beneficial effects that may be obtained.

Claims

1. An intelligent control method for power consumption of street lamps based on solar power generation, characterized in that: include: The energy consumption attributes in the electric energy consumption data set to be processed are used to filter the first street lamp energy consumption information set and the second street lamp energy consumption information set that have been constructed; Based on the constructed utilization efficiency and the constructed energy production efficiency of the factors in the first street lamp energy consumption information set, a first regression analysis parameter set is obtained, and a second regression analysis parameter set is obtained, wherein the first regression analysis parameter set is obtained by a first regression analysis method, and the second regression analysis parameter set is obtained by a second regression analysis method; Based on the constructed utilization efficiency of the factors in the second street lamp energy consumption information set, using the first regression analysis parameter set, and through the first regression analysis method, regressing and analyzing the first regression analysis energy production efficiency of the factors in the second street lamp energy consumption information set, and determining a first quality indicator based on a comparison result of the constructed energy production efficiency of the factors in the second street lamp energy consumption information set and the first regression analysis energy production efficiency; Based on the constructed utilization efficiency of the factors in the second street lamp energy consumption information set, using the second regression analysis parameter set, through the second regression analysis method, regressing the second regression analysis energy production efficiency of the factors in the second street lamp energy consumption information set, and determining the second quality indicator based on the comparison result of the constructed energy production efficiency of the factors in the second street lamp energy consumption information set and the second regression analysis energy production efficiency; Based on the comparison between the first quality indicator and the second quality indicator, at least one of the first regression analysis method and the second regression analysis method is selected, and the factors of the power consumption data set to be processed are intelligently controlled to obtain an intelligent control processing result.

2. The method according to claim 1, characterized in that The energy consumption attributes in the to-be-processed electric energy consumption data set are used to filter the constructed first street lamp energy consumption information set and the second street lamp energy consumption information set, including: Filtering the constructed second street lamp energy consumption information set, wherein the first sample data of the second street lamp energy consumption information set is similar to the electric energy consumption data set to be processed; The constructed first street lamp energy consumption information set is screened, wherein the first street lamp energy consumption information set is similar to the second sample data of the second street lamp energy consumption information set, and the second sample data is opposite to the first sample data.

3. The method according to claim 1, characterized in that: The first regression analysis method includes: Mining the constructed utilization efficiency of factors in the second street lamp energy consumption information set to obtain a second utilization rate mining result; For the factors in the second street light energy consumption information set, based on the second utilization mining results of the factors in the second street light energy consumption information set and the second utilization mining results of similar factors in the second street light energy consumption information set, using the first regression analysis parameter set, regress and analyze the first regression analysis energy production efficiency of the second street light energy consumption information set.

4. The method according to claim 3, characterized in that: The obtaining of the first regression analysis parameter set comprises: Mining the constructed utilization efficiency of factors in the first street lamp energy consumption information set to obtain a first utilization rate mining result; For the factors in the first street light energy consumption information set, the first utilization mining results of the factors in the first street light energy consumption information set, the first utilization mining results of similar factors in the first street light energy consumption information set and the constructed energy production efficiency of the factors in the first street light energy consumption information set are input into a first regression analysis algorithm to obtain a first regression analysis parameter set, wherein the first regression analysis algorithm is used for the first regression analysis method, and is an algorithm in which the energy production efficiency of the factors in the first street light energy consumption information set changes with the first utilization mining results of the factors in the first street light energy consumption information set and the first utilization mining results of similar factors in the first street light energy consumption information set based on the first regression analysis parameter set.

5. The method according to claim 1, characterized in that The first quality indicator is determined based on the comparison result of the constructed energy production efficiency of the factors in the second street lamp energy consumption information set and the first regression analysis energy production efficiency, including: For the independent factors in the second street lamp energy consumption information set, determining a first comparison result between the constructed energy production efficiency of the independent factors and the first regression analysis energy production efficiency; A first quality indicator is determined based on the first comparison result of each factor in the second street lamp energy consumption information set.

6. The method according to claim 1, characterized in that: The second regression analysis method includes: For the factors in the second street lamp energy consumption information set, screening a number of second key factors in the second street lamp energy consumption information set according to a specified rule; According to the constructed utilization efficiencies of the plurality of the second key factors, the second regression analysis energy production efficiency of the second key factors is regressively analyzed using the second regression analysis parameter set.

7. The method according to claim 6, characterized in that The specified rules include: Determining the street lamp energy consumption in the second street lamp energy consumption information set, wherein the street lamp energy consumption is a set of several similar factors having a common utilization efficiency; Determine the important factors of energy consumption of said street lamp; The important factors of the street lamp energy consumption and a preset number of important factors ranked top from large to small are screened and determined as the key factors, and the preset number is an integer greater than 5.

8. The method according to claim 6, characterized in that The obtaining of the second regression analysis parameter set comprises: For the factors in the first street lamp energy consumption information set, screening a plurality of first key factors in the first street lamp energy consumption information set according to the specified rule; The constructed utilization efficiencies of several of the first key factors and the constructed energy production efficiencies of the first key factors are input into a second regression analysis algorithm to obtain a second regression analysis parameter set, wherein the second regression analysis algorithm is used for the second regression analysis method, and is an algorithm for changing the energy production efficiency of the first key factor with the constructed utilization efficiencies of several of the first key factors based on the second regression analysis parameter set.

9. The method according to claim 1, characterized in that: The second quality indicator is determined based on the comparison result of the constructed energy production efficiency of the factors in the second street lamp energy consumption information set and the second regression analysis energy production efficiency, including: For the independent factors in the second street lamp energy consumption information set, determining a second comparison result between the constructed energy production efficiency of the independent factors and the second regression analysis energy production efficiency; Determining a second quality indicator based on the second comparison result of each factor in the second street lamp energy consumption information set; Wherein, based on the comparison between the first quality indicator and the second quality indicator, at least one of the first regression analysis method and the second regression analysis method is selected, and the factors of the power consumption data set to be processed are intelligently controlled to obtain the intelligent control processing result, including: If the first quality index is less than the second quality index, the first regression analysis method is selected, and the factors of the power consumption data set to be processed are intelligently controlled to obtain an intelligent control processing result; If the first quality index is not less than the second quality index, selecting the second regression analysis method, performing intelligent control processing on the factors of the power consumption data set to be processed, and obtaining an intelligent control processing result; Wherein, based on the comparison between the first quality indicator and the second quality indicator, at least one of the first regression analysis method and the second regression analysis method is selected, and the factors of the power consumption data set to be processed are intelligently controlled to obtain the intelligent control processing result, including: Determining a first weight and a second weight based on the first quality indicator and the second quality indicator; Using the first regression analysis method, a regression analysis is performed on the energy production efficiency of the factors of the power consumption data set to be processed to obtain a first regression analysis feature vector; Using the second regression analysis method, a regression analysis is performed on the energy production efficiency of the factors of the power consumption data set to be processed to obtain a second regression analysis feature vector; Using the first weight and the second weight, performing a weighted sum operation on the first regression analysis feature vector and the second regression analysis feature vector to obtain a first regression analysis result; Wherein, based on the comparison between the first quality indicator and the second quality indicator, at least one of the first regression analysis method and the second regression analysis method is selected, and the factors of the power consumption data set to be processed are intelligently controlled and processed to obtain the intelligent control processing result, the method further includes: Using a third regression analysis method, a regression analysis is performed on the energy production efficiency of the factors of the set of electric energy consumption data to be processed to obtain a second regression analysis result, wherein the third regression analysis method is different from the first regression analysis method and the second regression analysis method; Based on the comparison between the initial energy production efficiency of the factors of the set of electric energy consumption data to be processed and the first regression analysis result, and the comparison between the initial energy production efficiency of the factors of the set of electric energy consumption data to be processed and the second regression analysis result, at least one of the first regression analysis result and the second regression analysis result is screened to be determined as the regression analysis result of the factors of the set of electric energy consumption data to be processed.

10. An intelligent control system for street lamp power consumption based on solar power generation, characterized in that: The invention comprises a processor and a memory communicating with each other, wherein the processor is used to read a computer program from the memory and execute the computer program to implement the method according to any one of claims 1 to 9.

Images