Method and system for optimizing total water consumption evolution peak reaching path based on big data

Abstract

The invention discloses a big data-based total water consumption evolution peak reaching path optimization method and system, and relates to the technical field of water consumption analysis, and the method comprises the following steps: S1, collecting historical data, S2, analyzing an industry coefficient, S3, determining a water consumption distribution coefficient, S4, predicting regional water consumption, and S5, outputting the optimal water consumption. According to the method, the specified region is divided into the plurality of sub-regions, the gray scale prediction model is constructed according to the historical water consumption of each sub-region, and the original data is adjusted in the model construction process, so that the model parameters are more accurate, and the result analyzed by the prediction model is ensured to be more practical; due to the fact that the proportion of the industrial water consumption in the total urban water consumption is 80% or above, the method focuses on optimization of the industrial water consumption, the peak value and the valley value of the water consumption of each industry are scientifically and reasonably analyzed after the total production value and the water consumption of each industry in each sub-area are counted, and the industrial structure is adjusted.

Description

Technical Field

[0001] The present invention relates to the technical field of water consumption analysis, and specifically to a method and system for optimizing a peak path based on the evolution of total water consumption based on big data. Background Art

[0002] The total water consumption evolution peak path optimization system can conduct in-depth analysis of historical water consumption data, identify the growth trend and potential peak points of water consumption, and recommend suitable water-saving plans based on actual conditions to support the optimization of the peak path. The invention patent with application number 202210425688.2 discloses "an urban water consumption prediction method, device, electronic device and storage medium based on artificial intelligence. The urban water consumption prediction method based on artificial intelligence includes: obtaining basic urban water consumption data; screening abnormal data in the basic urban water consumption data, and smoothing the abnormal data to obtain optimized urban water consumption data; arranging the optimized urban water consumption data to obtain urban water consumption time series data, and decomposing the urban water consumption time series data to obtain multiple urban water consumption quantum sequences; obtaining multiple urban water use significant characteristic factors through the principal component analysis algorithm; inputting the urban water use quantum sequence and the urban water use significant characteristic factors into the neural network prediction model to obtain the prediction results. The present application can use the optimized wavelet transform to optimize the urban water consumption data, and combine the neural network to accurately predict the urban water consumption."

[0003] The above-mentioned existing technology solves the problem of being unable to predict urban water consumption, but during the execution of this method, since the designated city is not divided into several sub-areas, the prediction results may have large errors, and the method does not construct multiple objective functions, so it is impossible to optimize the water consumption of various industries in the city, resulting in unreasonable water consumption in individual industries, which not only affects the overall regional GDP, but also wastes water resources. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for optimizing the peak path of total water consumption evolution based on big data, so as to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solution: a peak path optimization method based on the evolution of total water consumption in big data, comprising the following steps:

[0006] S1. Collect historical data: extract historical water resource data and water consumption data of the specified area, analyze the corresponding change line graph based on these data, divide the specified area into multiple sub-areas, and obtain the historical water consumption of each sub-area;

[0007] S2. Analyze industry coefficients: determine the quality parameters corresponding to each sub-region, count all the road sections between each sub-region and other sub-regions, extract the speed limit of each road section, analyze the shortest distance between each sub-region based on the road section distance and the corresponding speed limit, combine the data of the sub-regions in pairs, calculate the association value between the regions based on the quality parameters of each two sub-regions, determine the consumption coefficient and transaction coefficient, analyze them, and obtain the circulation value between different industries in each sub-region;

[0008] S3. Determine the water allocation coefficient: Calculate the first indicator data and the second indicator data of each sub-region according to the gross domestic product of the sub-region, the circulation value between different industries and the actual water consumption, use these indicator data to determine the coordination score of each sub-region, take the ratio between the water consumption and the gross domestic product of each sub-region as the water allocation coefficient of the industry, and after determining the water allocation coefficient and the increased production allocation coefficient of different industries in the same sub-region, take the ratio of the two as the effect coefficient;

[0009] S4. Predicting regional water consumption: The historical water consumption of each sub-region is transferred to the grey prediction model as multiple original sequences, each original sequence is optimized to obtain a new sequence, model parameters are calculated based on these sequences, and the predicted water consumption of each sub-region is analyzed using the grey prediction model;

[0010] S5. Output the optimal water consumption: According to the total number of sub-regions, the number of industries, the gross domestic product and the coefficient, the optimal gross domestic product objective function and the optimal water use objective function are constructed. According to the coordination score of each sub-region, constraints are added to the ratio between the gross domestic product of each industry and the overall gross domestic product in the sub-region. The particle swarm optimization algorithm is used to analyze the objective function according to the constraints to obtain the optimal water consumption of each industry in each sub-region.

[0011] Preferably, the step S1 specifically includes the following steps:

[0012] S101, extracting historical water resource data of a designated area, wherein the historical water resource data includes groundwater resource volume, surface water resource volume and total water collection volume, analyzing a water resource change line graph based on the historical water resource data, and outputting the line graph through a visual interface;

[0013] S102, dividing water use types into four types, namely industrial water use, agricultural water use, domestic water use and environmental water use, collecting historical water use data corresponding to each water use type, drawing a line graph of water consumption changes corresponding to each water use type according to the historical water use data, and outputting it through a visual interface;

[0014] S103, after dividing the designated area into multiple sub-areas, numbering each sub-area, obtaining the historical water consumption of each sub-area, and transmitting it to the database.

[0015] Preferably, the step S2 specifically includes the following steps:

[0016] S201. Determine the gross domestic product G corresponding to each sub-region i , total social expenditure S i 、Total import and export value i and the total population N i , according to the gross domestic product G i , total social expenditure S i 、Total import and export value i and the total population N i Calculate the quality parameter q corresponding to the current sub-region i ;

[0017] S202, counting all road sections between each sub-area and the remaining sub-areas, extracting the speed limit of each road section, analyzing the shortest arrival time between each sub-area based on the road section distance and the corresponding speed limit, accumulating the distances of all road sections passed within the shortest arrival time, and obtaining the shortest distance value between each sub-area.

[0018] Preferably, the step S2 specifically further comprises the following steps:

[0019] S203, set the flow coefficient It between sub-areas, and count the shortest distance D between each sub-area and other sub-areas ij After that, the data of the sub-regions are combined in pairs, and the quality parameters q of each two sub-regions are calculated. i and q j Calculate the correlation value T between regions ij ,in

[0020] S204, extracting the consumption coefficients between different industries in each sub-region, calculating the corresponding transaction coefficients according to the consumption coefficients and the correlation values ​​between the sub-regions, and analyzing the industrial consumption coefficients and transaction coefficients in the sub-regions using a coefficient analysis algorithm to obtain the circulation values ​​between different industries in each sub-region. The coefficient analysis algorithm is specifically as follows:

[0021]

[0022] In the formula, represents the circulation value between the ath industry in the ith sub-region and the bth industry in the jth sub-region, represents the external consumption coefficient from the a-th industry to the b-th industry in the j-th sub-region, represents the internal consumption coefficient from the a-th industry to the b-th industry in the i-th sub-region, represents the flow direction between the ath industry in the ith sub-region and the jth sub-region, represents the flow direction between the ath industry in the ith sub-region and the ith sub-region, represents the total expenditure of the bth industry in the jth sub-region, represents the total expenditure of the bth industry in the ith sub-region, and a, b, i, j represent parameters.

[0023] Preferably, the step S3 specifically includes the following steps:

[0024] S301, calculating the gross product of the industries in the region according to the gross product of the sub-region and the circulation value between different industries, and calculating the first indicator data of each sub-region using the total number of industries and the gross product corresponding to each industry;

[0025] S302, after extracting the actual water consumption of different industries in each sub-region, calculate the second indicator data of the corresponding sub-region according to the gross output value and actual water consumption of each industry;

[0026] S303, after counting the first indicator data and the second indicator data of each sub-region, scoring the coordination degree of each sub-region according to these indicator data, and storing the obtained score in a database;

[0027] S304: Count the water consumption w corresponding to different industries in each sub-region k and production volume k , water consumption w k With production volume k The ratio between them is taken as the industrial water allocation coefficient B k , extract the unit matrix E and the direct parameter matrix P, according to the water distribution coefficient B k , directly calculate the production increase distribution coefficient Y using the parameter matrix P and the unit matrix E k , where Y k =B k (EP) -1 ;

[0028] S305. Determine the water allocation coefficient B for different industries in the same sub-region k and the yield-increasing distribution coefficient Y k Then, the ratio of the two is taken as the effect coefficient R k .

[0029] Preferably, the step S4 specifically includes the following steps:

[0030] S401, transmitting the historical water consumption of each sub-region as multiple original sequences to the grey prediction model, and performing accumulation processing on each original sequence to obtain an accumulated generated sequence;

[0031] S402, optimizing the accumulated generated sequences using a sequence optimization algorithm to obtain new sequences, and calculating model parameters based on these sequences;

[0032] S403: Analyze the historical water consumption data of each sub-region using a grey prediction model to obtain the predicted water consumption of each sub-region, and output it through a visualization interface.

[0033] Preferably, the step S5 specifically includes the following steps:

[0034] S501, determining the total number of sub-regions and the number of industries in each sub-region, and calculating the gross output value of each industry, and constructing an optimal gross output value objective function according to the total number of sub-regions, the number of industries and the gross output value;

[0035] S502, after receiving the water use allocation coefficient, effect coefficient and gross output value of different industries in each sub-region, construct an optimal water use objective function according to the water use allocation coefficient, effect coefficient and gross output value of different industries;

[0036] S503, analyzing the peak and valley values ​​of water consumption of the industries in each sub-region according to the predicted water consumption, adding constraints to the ratio between the gross domestic product of each industry and the overall gross domestic product in the sub-region through the coordination score of each sub-region, and setting the upper and lower limits of the gross domestic product of each industry;

[0037] S504, using a particle swarm optimization algorithm to analyze the objective function according to the constraints, and after obtaining the optimal gross production value and water consumption of each industry in each sub-region, output them through a visual interface.

[0038] The peak path optimization system based on big data total water consumption evolution includes a historical data collection unit, an industrial circulation unit, an indicator analysis unit, a water consumption prediction unit and a solution generation unit;

[0039] The historical data collection unit extracts historical water resource data and water consumption data of a designated area, analyzes corresponding change line graphs based on these data, divides the designated area into multiple sub-areas, and obtains historical water consumption of each sub-area;

[0040] The industrial circulation unit determines the quality parameters corresponding to each sub-region, counts all the road sections between each sub-region and the other sub-regions, extracts the speed limit of each road section, analyzes the shortest distance value between each sub-region according to the road section distance and the corresponding speed limit, combines the data of the sub-regions in pairs, calculates the correlation value between the regions according to the quality parameters of each two sub-regions, determines the consumption coefficient and the transaction coefficient, analyzes them, and obtains the circulation value between different industries in each sub-region;

[0041] The index analysis unit calculates the first index data and the second index data of each sub-region according to the gross domestic product of the sub-region, the circulation value between different industries and the actual water consumption, uses these index data to determine the coordination score of each sub-region, takes the ratio between the water consumption and the gross domestic product of each sub-region as the water allocation coefficient of the industry, and after determining the water allocation coefficient and the increased production allocation coefficient of different industries in the same sub-region, takes the ratio of the two as the effect coefficient;

[0042] The water consumption prediction unit calculates the first indicator data and the second indicator data of each sub-region according to the gross domestic product of the sub-region, the circulation value between different industries and the actual water consumption, uses these indicator data to determine the coordination score of each sub-region, takes the ratio between the water consumption and the gross domestic product of each sub-region as the water allocation coefficient of the industry, and after determining the water allocation coefficient and the increased production allocation coefficient of different industries in the same sub-region, takes the ratio of the two as the effect coefficient;

[0043] The scheme generation unit constructs an optimal gross domestic product objective function and an optimal water use objective function according to the total number of sub-regions, the number of industries, the gross domestic product and the coefficient, adds constraints to the ratio between the gross domestic product of each industry and the overall gross domestic product in the sub-region according to the coordination score of each sub-region, and uses a particle swarm optimization algorithm to analyze the objective function according to the constraints to obtain the optimal water consumption of each industry in each sub-region.

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

[0045] The present invention divides the designated area into multiple sub-areas, constructs a grayscale prediction model according to the historical water consumption of each sub-area, and adjusts the original data in the process of building the model to make the model parameters more accurate, ensuring that the results analyzed by the prediction model are more in line with reality. Since industrial water consumption accounts for more than 80% of the total urban water consumption, this method focuses more on the optimization of industrial water use. After counting the gross domestic product and water consumption of each industry in each sub-area, the peak and valley values ​​of water consumption of each industry are scientifically and rationally analyzed, the industry proportion is adjusted, and the optimal gross domestic product and water consumption of each industry are solved using the objective function and constraints. Water use is reduced under the premise of good gross domestic product, which not only protects water resources but also further optimizes the industrial structure of the designated area. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 Provide an overall method flow chart for an embodiment of the present invention;

[0047] Figure 2 A flow chart of a method for collecting historical data is provided for an embodiment of the present invention;

[0048] Figure 3 A flow chart of a method for predicting regional water consumption is provided for an embodiment of the present invention;

[0049] Figure 4 A flow chart of a method for outputting an optimal water consumption is provided for an embodiment of the present invention;

[0050] Figure 5 Provide a water consumption evolution trend diagram for an embodiment of the present invention; DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] See also Figure 1-Figure 5 The present invention provides a technical solution: a peak path optimization method based on the evolution of total water consumption in big data, comprising the following steps:

[0053] S1. Collect historical data: extract historical water resource data and water consumption data of the specified area, analyze the corresponding change line graph based on these data, divide the specified area into multiple sub-areas, and obtain the historical water consumption of each sub-area;

[0054] S2. Analyze industry coefficients: determine the quality parameters corresponding to each sub-region, count all the road sections between each sub-region and other sub-regions, extract the speed limit of each road section, analyze the shortest distance between each sub-region based on the road section distance and the corresponding speed limit, combine the data of the sub-regions in pairs, calculate the association value between the regions based on the quality parameters of each two sub-regions, determine the consumption coefficient and transaction coefficient, analyze them, and obtain the circulation value between different industries in each sub-region;

[0055] S3. Determine the water allocation coefficient: Calculate the first indicator data and the second indicator data of each sub-region according to the gross domestic product of the sub-region, the circulation value between different industries and the actual water consumption, use these indicator data to determine the coordination score of each sub-region, take the ratio between the water consumption and the gross domestic product of each sub-region as the water allocation coefficient of the industry, and after determining the water allocation coefficient and the increased production allocation coefficient of different industries in the same sub-region, take the ratio of the two as the effect coefficient;

[0056] S4. Predicting regional water consumption: The historical water consumption of each sub-region is transferred to the grey prediction model as multiple original sequences, each original sequence is optimized to obtain a new sequence, model parameters are calculated based on these sequences, and the predicted water consumption of each sub-region is analyzed using the grey prediction model;

[0057] S5. Output the optimal water consumption: According to the total number of sub-regions, the number of industries, the gross domestic product and the coefficient, the optimal gross domestic product objective function and the optimal water use objective function are constructed. According to the coordination score of each sub-region, constraints are added to the ratio between the gross domestic product of each industry and the overall gross domestic product in the sub-region. The particle swarm optimization algorithm is used to analyze the objective function according to the constraints to obtain the optimal water consumption of each industry in each sub-region.

[0058] Step S1 specifically includes the following steps:

[0059] S101, extracting historical water resource data of a designated area, wherein the historical water resource data includes groundwater resource volume, surface water resource volume and total water collection volume, analyzing a water resource change line graph based on the historical water resource data, and outputting the line graph through a visual interface;

[0060] S102, dividing water use types into four types, namely industrial water use, agricultural water use, domestic water use and environmental water use, collecting historical water use data corresponding to each water use type, drawing a line graph of water consumption changes corresponding to each water use type according to the historical water use data, and outputting it through a visual interface;

[0061] S103, after dividing the designated area into multiple sub-areas, numbering each sub-area, obtaining the historical water consumption of each sub-area, and transmitting it to the database;

[0062] Step S2 specifically includes the following steps:

[0063] S201. Determine the gross domestic product G corresponding to each sub-region i , total social expenditure S i 、Total import and export value i and the total population N i , according to the gross domestic product G i , total social expenditure S i 、Total import and export value i and the total population N i Calculate the quality parameter q corresponding to the current sub-region i ;

[0064] S202, counting all road sections between each sub-area and other sub-areas, extracting the speed limit of each road section, analyzing the shortest arrival time between each sub-area according to the road section distance and the corresponding speed limit, and accumulating the distances of all road sections passed within the shortest arrival time to obtain the shortest distance value between each sub-area;

[0065] Step S2 specifically also includes the following steps:

[0066] S203, set the flow coefficient It between sub-areas, and count the shortest distance D between each sub-area and other sub-areas ij After that, the data of the sub-regions are combined in pairs, and the quality parameters q of each two sub-regions are calculated. i and q j Calculate the correlation value T between regions ij ,in

[0067] S204, extract the consumption coefficients between different industries in each sub-region, calculate the corresponding transaction coefficients according to the consumption coefficients and the correlation values ​​between the sub-regions, and use the coefficient analysis algorithm to analyze the industrial consumption coefficients and transaction coefficients in the sub-regions to obtain the circulation values ​​between different industries in each sub-region. The specific coefficient analysis algorithm is:

[0068]

[0069] In the formula, represents the circulation value between the ath industry in the ith sub-region and the bth industry in the jth sub-region, represents the external consumption coefficient from the a-th industry to the b-th industry in the j-th sub-region, represents the internal consumption coefficient from the a-th industry to the b-th industry in the i-th sub-region, represents the flow direction between the ath industry in the ith sub-region and the jth sub-region, represents the flow direction between the ath industry in the ith sub-region and the ith sub-region, represents the total expenditure of the bth industry in the jth sub-region, represents the total expenditure of the bth industry in the i-th sub-region, and a, b, i, j represent parameters;

[0070] Step S3 specifically includes the following steps:

[0071] S301, calculating the gross product of the industries in the region according to the gross product of the sub-region and the circulation value between different industries, and calculating the first indicator data of each sub-region using the total number of industries and the gross product corresponding to each industry;

[0072] S302, after extracting the actual water consumption of different industries in each sub-region, calculate the second indicator data of the corresponding sub-region according to the gross output value and actual water consumption of each industry;

[0073] S303, after counting the first indicator data and the second indicator data of each sub-region, scoring the coordination degree of each sub-region according to these indicator data, and storing the obtained score in a database;

[0074] S304: Count the water consumption w corresponding to different industries in each sub-region k and production volume k , water consumption w k With production volume k The ratio between them is taken as the industrial water allocation coefficient B k , extract the unit matrix E and the direct parameter matrix P, according to the water distribution coefficient B k , directly calculate the production increase distribution coefficient Y using the parameter matrix P and the unit matrix E k , where Y k =B k (EP) -1 ;

[0075] S305. Determine the water allocation coefficient B for different industries in the same sub-region k and the yield-increasing distribution coefficient Y k Then, the ratio of the two is taken as the effect coefficient R k ;

[0076] Step S4 specifically includes the following steps:

[0077] S401, transmitting the historical water consumption of each sub-region as multiple original sequences to the grey prediction model, and performing accumulation processing on each original sequence to obtain an accumulated generated sequence;

[0078] S402: Optimize the accumulated generated sequence using a sequence optimization algorithm to obtain a new sequence, and calculate the model parameters based on the sequence. The sequence optimization algorithm is specifically as follows:

[0079]

[0080] In the formula, l(v) represents the vth historical water use data, l(v+1) represents the v+1th historical water use data, l(n) represents the nth historical water use data, and D 2 represents the buffer operator, n represents the total number of data, and v represents the parameter;

[0081] S403, using a grey prediction model to analyze the historical water consumption data of each sub-region, thereby obtaining the predicted water consumption of each sub-region, and outputting it through a visual interface;

[0082] Step S5 specifically includes the following steps:

[0083] S501, determining the total number of sub-regions and the number of industries in each sub-region, and calculating the gross output value of each industry, and constructing an optimal gross output value objective function according to the total number of sub-regions, the number of industries and the gross output value;

[0084] S502, after receiving the water use allocation coefficient, effect coefficient and gross output value of different industries in each sub-region, construct an optimal water use objective function according to the water use allocation coefficient, effect coefficient and gross output value of different industries;

[0085] S503, analyzing the peak and valley values ​​of water consumption of the industries in each sub-region according to the predicted water consumption, adding constraints to the ratio between the gross domestic product of each industry and the overall gross domestic product in the sub-region through the coordination score of each sub-region, and setting the upper and lower limits of the gross domestic product of each industry;

[0086] S504, using a particle swarm optimization algorithm to analyze the objective function according to the constraint conditions, and after obtaining the optimal gross production value and water consumption of each industry in each sub-region, output them through a visual interface;

[0087] The peak path optimization system of total water consumption evolution based on big data includes historical data collection unit 1, industrial circulation unit 2, index analysis unit 3, water consumption prediction unit 4 and solution generation unit 5;

[0088] The historical data collection unit 1 extracts the historical water resource data and water consumption data of the designated area, analyzes the corresponding change line graph based on these data, divides the designated area into multiple sub-areas, and obtains the historical water consumption of each sub-area;

[0089] The industrial circulation unit 2 determines the quality parameters corresponding to each sub-region, counts all the road sections between each sub-region and the other sub-regions, extracts the speed limit of each road section, analyzes the shortest distance value between each sub-region according to the road section distance and the corresponding speed limit, combines the data of the sub-regions in pairs, calculates the correlation value between the regions according to the quality parameters of each two sub-regions, determines the consumption coefficient and the transaction coefficient, analyzes them, and obtains the circulation value between different industries in each sub-region;

[0090] The index analysis unit 3 calculates the first index data and the second index data of each sub-region according to the gross domestic product of the sub-region, the circulation value between different industries and the actual water consumption, and uses these index data to determine the coordination score of each sub-region, and takes the ratio between the water consumption and the gross domestic product of each sub-region as the water allocation coefficient of the industry. After determining the water allocation coefficient and the increased production allocation coefficient of different industries in the same sub-region, the ratio of the two is taken as the effect coefficient;

[0091] The water consumption prediction unit 4 calculates the first index data and the second index data of each sub-region according to the gross domestic product of the sub-region, the circulation value between different industries and the actual water consumption, and uses these index data to determine the coordination score of each sub-region, and takes the ratio between the water consumption and the gross domestic product of each sub-region as the water allocation coefficient of the industry. After determining the water allocation coefficient and the increase allocation coefficient of different industries in the same sub-region, the ratio of the two is taken as the effect coefficient;

[0092] The solution generation unit 5 constructs the optimal gross domestic product objective function and the optimal water use objective function according to the total number of sub-regions, the number of industries, the gross domestic product and the coefficient, adds constraints to the ratio between the gross domestic product of each industry and the overall gross domestic product in the sub-region according to the coordination score of each sub-region, and uses the particle swarm optimization algorithm to analyze the objective function according to the constraints to obtain the optimal water consumption of each industry in each sub-region.

[0093] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0094] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A peak path optimization method based on the evolution of total water consumption based on big data, characterized in that: The method comprises the following steps: S1. Collect historical data: extract historical water resource data and water consumption data of the specified area, analyze the corresponding change line graph based on these data, divide the specified area into multiple sub-areas, and obtain the historical water consumption of each sub-area; S2. Analyze industry coefficients: determine the quality parameters corresponding to each sub-region, count all the road sections between each sub-region and other sub-regions, extract the speed limit of each road section, analyze the shortest distance between each sub-region based on the road section distance and the corresponding speed limit, combine the data of the sub-regions in pairs, calculate the association value between the regions based on the quality parameters of each two sub-regions, determine the consumption coefficient and transaction coefficient, analyze them, and obtain the circulation value between different industries in each sub-region; S3. Determine the water allocation coefficient: Calculate the first indicator data and the second indicator data of each sub-region according to the gross domestic product of the sub-region, the circulation value between different industries and the actual water consumption, use these indicator data to determine the coordination score of each sub-region, take the ratio between the water consumption and the gross domestic product of each sub-region as the water allocation coefficient of the industry, and after determining the water allocation coefficient and the increased production allocation coefficient of different industries in the same sub-region, take the ratio of the two as the effect coefficient; S4. Predicting regional water consumption: The historical water consumption of each sub-region is transferred to the grey prediction model as multiple original sequences, each original sequence is optimized to obtain a new sequence, model parameters are calculated based on these sequences, and the predicted water consumption of each sub-region is analyzed using the grey prediction model; S5. Output the optimal water consumption: According to the total number of sub-regions, the number of industries, the gross domestic product and the coefficient, the optimal gross domestic product objective function and the optimal water use objective function are constructed. According to the coordination score of each sub-region, constraints are added to the ratio between the gross domestic product of each industry and the overall gross domestic product in the sub-region. The particle swarm optimization algorithm is used to analyze the objective function according to the constraints to obtain the optimal water consumption of each industry in each sub-region.

2. The peak path optimization method based on big data water consumption evolution according to claim 1 is characterized by: The step S1 specifically includes the following steps: S101, extracting historical water resource data of a designated area, wherein the historical water resource data includes groundwater resource volume, surface water resource volume and total water collection volume, analyzing a water resource change line graph based on the historical water resource data, and outputting the line graph through a visual interface; S102, dividing water use types into four types, namely industrial water use, agricultural water use, domestic water use and environmental water use, collecting historical water use data corresponding to each water use type, drawing a line graph of water consumption changes corresponding to each water use type according to the historical water use data, and outputting it through a visual interface; S103, after dividing the designated area into multiple sub-areas, numbering each sub-area, obtaining the historical water consumption of each sub-area, and transmitting it to the database.

3. The peak path optimization method based on big data water consumption evolution according to claim 1 is characterized by: The step S2 specifically includes the following steps: S201. Determine the gross domestic product G corresponding to each sub-region i , total social expenditure S i 、Total import and export value i and the total population N i , according to the gross domestic product G i , total social expenditure S i 、Total import and export value i and the total population N i Calculate the quality parameter q corresponding to the current sub-region i ; S202, counting all road sections between each sub-area and the remaining sub-areas, extracting the speed limit of each road section, analyzing the shortest arrival time between each sub-area based on the road section distance and the corresponding speed limit, accumulating the distances of all road sections passed within the shortest arrival time, and obtaining the shortest distance value between each sub-area.

4. The method for optimizing the peak path of total water consumption evolution based on big data according to claim 3 is characterized in that: The step S2 specifically further comprises the following steps: S203, set the flow coefficient It between sub-areas, and count the shortest distance D between each sub-area and other sub-areas ij After that, the data of the sub-regions are combined in pairs, and the quality parameters q of each two sub-regions are calculated. i and q j Calculate the correlation value T between regions ij ,in S204, extracting the consumption coefficients between different industries in each sub-region, calculating the corresponding transaction coefficients according to the consumption coefficients and the correlation values ​​between the sub-regions, analyzing the industrial consumption coefficients and transaction coefficients within the sub-regions using the coefficient analysis algorithm, and obtaining the circulation values ​​between different industries within each sub-region.

5. The method for optimizing the peak path of total water consumption evolution based on big data according to claim 1 is characterized in that: The step S3 specifically comprises the following steps: S301, calculating the gross product of the industries in the region according to the gross product of the sub-region and the circulation value between different industries, and calculating the first indicator data of each sub-region using the total number of industries and the gross product corresponding to each industry; S302, after extracting the actual water consumption of different industries in each sub-region, calculate the second indicator data of the corresponding sub-region according to the gross output value and actual water consumption of each industry; S303, after counting the first indicator data and the second indicator data of each sub-region, scoring the coordination degree of each sub-region according to these indicator data, and storing the obtained score in a database; S304: Count the water consumption w corresponding to different industries in each sub-region k and production volume k , water consumption w k With production volume k The ratio between them is taken as the industrial water allocation coefficient B k , extract the unit matrix E and the direct parameter matrix P, according to the water distribution coefficient B k , directly calculate the production increase distribution coefficient Y using the parameter matrix P and the unit matrix E k , where Y k =B k (EP) -1 ; S305. Determine the water allocation coefficient B for different industries in the same sub-region k and the yield-increasing distribution coefficient Y k Then, the ratio of the two is taken as the effect coefficient R k .

6. The method for optimizing the peak path of total water consumption evolution based on big data according to claim 1 is characterized in that: The step S4 specifically comprises the following steps: S401, transmitting the historical water consumption of each sub-region as multiple original sequences to the grey prediction model, and performing accumulation processing on each original sequence to obtain an accumulated generated sequence; S402, optimizing the accumulated generated sequences using a sequence optimization algorithm to obtain new sequences, and calculating model parameters based on these sequences; S403: Analyze the historical water consumption data of each sub-region using a grey prediction model to obtain the predicted water consumption of each sub-region, and output it through a visualization interface.

7. The method for optimizing the peak path of total water consumption evolution based on big data according to claim 1 is characterized in that: The step S5 specifically comprises the following steps: S501, determining the total number of sub-regions and the number of industries in each sub-region, and calculating the gross output value of each industry, and constructing an optimal gross output value objective function according to the total number of sub-regions, the number of industries and the gross output value; S502, after receiving the water use allocation coefficient, effect coefficient and gross output value of different industries in each sub-region, construct an optimal water use objective function according to the water use allocation coefficient, effect coefficient and gross output value of different industries; S503, analyzing the peak and valley values ​​of water consumption of the industries in each sub-region according to the predicted water consumption, adding constraints to the ratio between the gross domestic product of each industry and the overall gross domestic product in the sub-region through the coordination score of each sub-region, and setting the upper and lower limits of the gross domestic product of each industry; S504, using a particle swarm optimization algorithm to analyze the objective function according to the constraints, and after obtaining the optimal gross production value and water consumption of each industry in each sub-region, output them through a visual interface.

8. Based on big data, the peak path optimization system for total water consumption evolution is characterized by: The total water consumption evolution peak path optimization system is applicable to the total water consumption evolution peak path optimization method based on big data as described in any one of claims 1 to 7, comprising a historical data collection unit (1), an industrial circulation unit (2), an indicator analysis unit (3), a water consumption prediction unit (4) and a solution generation unit (5); The historical data collection unit (1) extracts historical water resource data and water consumption data of a designated area, analyzes the corresponding change line graph based on these data, divides the designated area into multiple sub-areas, and obtains the historical water consumption of each sub-area; The industrial circulation unit (2) determines the quality parameter corresponding to each sub-region, counts all the road sections between each sub-region and other sub-regions, extracts the speed limit of each road section, analyzes the shortest distance value between each sub-region according to the road section distance and the corresponding speed limit, combines the data of the sub-regions in pairs, calculates the correlation value between the regions according to the quality parameters of each two sub-regions, determines the consumption coefficient and the transaction coefficient, analyzes them, and obtains the circulation value between different industries in each sub-region; The index analysis unit (3) calculates the first index data and the second index data of each sub-region according to the gross domestic product of the sub-region, the circulation value between different industries and the actual water consumption, uses these index data to determine the coordination score of each sub-region, takes the ratio between the water consumption and the gross domestic product of each sub-region as the water allocation coefficient of the industry, and after determining the water allocation coefficient and the increased production allocation coefficient of different industries in the same sub-region, takes the ratio of the two as the effect coefficient; The water consumption prediction unit (4) calculates first indicator data and second indicator data of each sub-region according to the gross domestic product of the sub-region, the circulation value between different industries and the actual water consumption, uses these indicator data to determine the coordination score of each sub-region, takes the ratio between the water consumption and the gross domestic product of each sub-region as the water allocation coefficient of the industry, and after determining the water allocation coefficient and the increased production allocation coefficient of different industries in the same sub-region, takes the ratio of the two as the effect coefficient; The solution generation unit (5) constructs an optimal gross product value objective function and an optimal water use objective function according to the total number of sub-regions, the number of industries, the gross product value and the coefficient, adds constraints to the ratio between the gross product value of each industry and the overall gross product in the sub-region according to the coordination score of each sub-region, and uses a particle swarm optimization algorithm to analyze the objective function according to the constraints to obtain the optimal water use of each industry in each sub-region.

Images