Intelligent park equipment energy consumption optimization method and system based on machine learning, and medium

Abstract

The invention relates to the technical field of energy consumption optimization, in particular to a smart park equipment energy consumption optimization method and system based on machine learning and a medium, and the method comprises the steps that S1, a monitoring module takes historical real monitoring data of different days as sending data, and performs confusion processing on the sending data to obtain a plurality of confused data blocks; s2, an optimization module recovers different partial sending data from each confusion data block, and improves the trained analysis algorithm; and S3, the optimization module takes various types of possible condition data of the target day as input data of the analysis algorithm after improvement processing so as to obtain output data of the analysis algorithm after improvement processing, and an optimization plan is made according to the output data. The intelligence of the energy consumption optimization method can be improved.

Description

Technical Field

[0001] This application relates to the technical field of energy consumption optimization, and particularly to an energy consumption optimization method, system and medium for intelligent park equipment based on machine learning. Background Art

[0002] Equipment energy consumption optimization can effectively reduce energy consumption, reduce operating costs, and at the same time contribute to energy conservation, emission reduction and sustainable development.

[0003] The Chinese patent application with the publication number CN108509019A provides an energy consumption optimization method and device for a data center. By obtaining the current working state information of the execution equipment and the refrigeration equipment in the data center, obtaining the corresponding current PUE coefficient according to the current working state information, and using a preset optimization strategy to adjust the current working state information to obtain the adjusted working state information, obtaining the corresponding adjusted PUE coefficient according to the adjusted working state information, and when it is determined that the adjusted PUE coefficient is less than the current PUE coefficient, adjusting the execution equipment and the refrigeration equipment according to the adjusted working state information. In addition, the Chinese patent application with the publication number CN114169056A discloses an energy consumption optimization method based on green buildings, including the following steps: S1: Obtain the three-dimensional model of the building to be designed; S2: According to the three-dimensional model, design the relevant layouts of the building envelope system, heating, ventilation and air conditioning (HVAC) system, and lighting system; Envelope system: According to the three-dimensional model of the building and the climate of the region where the building is located, design the proportion and position distribution of the transparent area and the non-transparent area in the envelope structure, and then determine the thickness of the transparent area and the non-transparent area respectively; HVAC system: According to the three-dimensional model of the building and the climate of the region where the building is located, determine the layout and power of each HVAC equipment in the HVAC system; S3: Obtain the respective energy consumption of each energy consumption system of the building and the total energy consumption of the building; Compare each energy consumption data with the data in the big data, and by reasonably arranging the building envelope system, HVAC system, and lighting system, the energy consumption can be reduced.

[0004] However, the energy consumption optimization methods in the above two patent applications are both relatively complex and lack intelligence. Summary of the Invention

[0005] This application sets up a monitoring module to perform confusion processing on the sent data to obtain several confused data blocks, and sets up an optimization module to recover different parts of the sent data from each confused data block, so as to obtain the complete sent data. The trained analysis algorithm is improved, and various types of possible conditional data of the target day are used as the input data of the improved analysis algorithm, and an optimization plan is formulated based on the output data. This application aims to improve the intelligence of the energy consumption optimization method.

[0006] This application provides a method for optimizing the energy consumption of intelligent park equipment based on machine learning, including the following steps: S1. The monitoring module uses the real monitoring data of different days in history as the sending data, performs confusion processing on the sending data to obtain a number of confused data blocks, and transmits the number of confused data blocks to the optimization module through the network module; S2. The optimization module recovers different partial sending data from each confused data block, obtains the sending data based on all the partial sending data, and the optimization module obtains various types of real condition data of different days in history, determines a number of observation days among different days in history, and the optimization module also obtains a trained analysis algorithm and performs improvement processing on the trained analysis algorithm; S3. The optimization module calculates various types of possible condition data of the target day based on various types of real condition data of different days in history, and the optimization module uses various types of possible condition data of the target day as the input data of the improved analysis algorithm to obtain the output data of the improved analysis algorithm, and formulates an optimization plan based on the output data.

[0007] As a preferred technical solution of this application, the improvement process of the optimization module for the trained analysis algorithm includes the following steps: S211. For each observation day, the optimization module calculates various types of possible condition data of the observation day based on various types of real condition data of different days in history; S212. For each observation day, use various types of possible condition data of the observation day as the input data of the trained analysis algorithm to obtain the output data of the trained analysis algorithm, and calculate the absolute value of the difference between the output data and the real monitoring data of the observation day; S213. The optimization module calculates the first ratio of the sum of all absolute values to the total number of all absolute values, and the optimization module determines whether the first ratio is less than a preset first ratio threshold. If it is less, end all steps. If it is greater than or equal to, perform the first improvement process on the trained analysis algorithm and jump to S212.

[0008] As a preferred technical solution of this application, the improvement process of the optimization module for the trained analysis algorithm further includes the following steps: S221. For each type of real condition data of different days in history, the optimization module calculates the second ratio of the sum of all real condition data to the total number of all real condition data, calculates the square value of the difference between each real condition data and the second ratio, and also calculates the square root value of the third ratio of the sum of all square values to the total number of all square values; S222. The optimization module calculates possible condition data of various types for the target day based on real condition data of various types on different days in history; S223. For each type of possible condition data of the target day, the optimization module calculates the absolute value of the difference between the possible condition data and the corresponding second ratio, and continues to calculate the fourth ratio of the absolute value to the corresponding square root value; S224. Perform a second improvement process on the trained analysis algorithm based on the fourth ratios corresponding to the possible condition data of various types of the target day.

[0009] As a preferred technical solution of the present application, the monitoring module performs obfuscation processing on the sent data, including the following steps: S11. The monitoring module divides the sent data into several sent data blocks, and for each sent data block, generates secret data corresponding to the sent data block, and also for each sent data block, regards the data scale of the sent data block as representative data; S12. For each sent data block, the monitoring module uses the secret data corresponding to the sent data block to perform secret processing on the sent data block to obtain an intermediate data block; S13. For each intermediate data block, the monitoring module adds the secret data corresponding to the previous intermediate data block to the intermediate data block based on the representative data corresponding to the intermediate data block to obtain an obfuscated data block.

[0010] As a preferred technical solution of the present application, the monitoring module adds the secret data corresponding to the previous intermediate data block to the intermediate data block based on the representative data corresponding to the intermediate data block, including the following steps: S131. The monitoring module performs a preset operation on the secret data corresponding to the previous intermediate data block to obtain target data, and performs a preset operation on the representative data corresponding to the intermediate data block to obtain process data; S132. The monitoring module determines whether the process data is greater than the data scale of the intermediate data block. If it is greater, the process data is subtracted by the data scale of the intermediate data block, and this step is repeated. If it is less than or equal, a part of the target data is added to the intermediate data block according to the process data; S133. The monitoring module determines whether the complete target data has been added to the intermediate data block. If not, the process data is updated with the result data of the preset operation on the process data, and jumps to S132. If so, all steps are ended.

[0011] As a preferred technical solution of the present application, the optimization module recovers part of the sent data from the obfuscated data block, including the following steps: S231. The optimization module determines the data scale of the obfuscated data block, uses the result data obtained by subtracting the preset data from the data scale as the representative data corresponding to the obfuscated data block, and performs a preset operation on the representative data to obtain process data; S232. The optimization module determines whether the process data is greater than the representative data. If it is greater, the process data is subtracted by the representative data, and this step is repeated. If it is less than or equal, data removal is performed on the obfuscated data block based on the process data; S233. The optimization module determines whether the stop condition is satisfied. If not, the process data is updated with the result data obtained by performing a preset operation on the process data, and it jumps to S232. If satisfied, restoration processing is performed on the obfuscated data to obtain partial transmission data, and all steps are ended.

[0012] This application also provides an intelligent park equipment energy consumption optimization system based on machine learning, including the following modules: A monitoring module, which is used to use the real monitoring data of different days in history as transmission data, perform obfuscation processing on the transmission data to obtain a number of obfuscated data blocks, and transmit the number of obfuscated data blocks to the optimization module through the network module; A network module, which is used to transmit a number of obfuscated data blocks generated by the monitoring module to the optimization module; An optimization module, which is used to recover different partial transmission data from each obfuscated data block, obtain transmission data based on all partial transmission data, obtain various types of real condition data of different days in history, determine a number of observation days among different days in history, and also obtain a trained analysis algorithm and perform improvement processing on the trained analysis algorithm; and is used to calculate various types of possible condition data of the target day based on various types of real condition data of different days in history, use the various types of possible condition data of the target day as the input data of the improved analysis algorithm to obtain the output data of the improved analysis algorithm, and formulate an optimization plan based on the output data.

[0013] This application also provides a medium, which stores program instructions. Among them, when the program instructions run, they control the device where the medium is located to execute the method described in any one of the above.

[0014] Compared with the prior art, the beneficial effects of this application are at least as follows: In the technical solution provided by this application, first, the monitoring module uses the real monitoring data of different days in history as the sending data, performs obfuscation processing on the sending data to obtain several obfuscated data blocks, and transmits the several obfuscated data blocks to the optimization module through the network module; second, the optimization module recovers different partial sending data from each obfuscated data block, obtains the sending data based on all the partial sending data, and the optimization module obtains various types of real condition data of different days in history, determines several observation days among the different days in history, and the optimization module also obtains the trained analysis algorithm and performs improvement processing on the trained analysis algorithm; finally, the optimization module calculates the possible condition data of various types on the target day based on the various types of real condition data of different days in history, and the optimization module uses the possible condition data of various types on the target day as the input data of the improved analysis algorithm to obtain the output data of the improved analysis algorithm, and formulates an optimization plan based on the output data. Through this application, not only can an optimization plan be formulated simply and quickly, but also the intelligent level of the energy consumption optimization method can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0016] Figure 1 It is a flowchart of the intelligent park equipment energy consumption optimization method based on machine learning in this application; Figure 2 It is a flowchart of the improvement processing for the trained analysis algorithm in this application; Figure 3 It is a flowchart of the continued improvement processing for the trained analysis algorithm in this application; Figure 4 It is a schematic diagram of the intelligent park equipment energy consumption optimization system based on machine learning in this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] The embodiments of the present application provide a method, a system, and a medium for optimizing the energy consumption of smart park devices based on machine learning. The terms "first", "second", "third", "fourth", etc. (if any) in the specification, claims, and the above-mentioned drawings of the present application are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the term "including" or "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily limit to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0018] For ease of understanding, the specific process of the embodiments of the present application will be described below. Please refer to Figure 1 , the method for optimizing the energy consumption of smart park devices based on machine learning in the embodiments of the present application includes the following main steps: S1. The monitoring module uses the real monitoring data on different days in history as the sending data, performs confusion processing on the sending data to obtain a number of confused data blocks, and transmits the number of confused data blocks to the optimization module through the network module; S2. The optimization module recovers different partial sending data from each confused data block, obtains the sending data based on all the partial sending data, and the optimization module obtains various types of real condition data on different days in history, determines a number of observation days among different days in history, and the optimization module also obtains a trained analysis algorithm and performs improvement processing on the trained analysis algorithm; S3. The optimization module calculates various types of possible condition data for the target day based on various types of real condition data on different days in history, and the optimization module uses various types of possible condition data for the target day as the input data of the improved analysis algorithm to obtain the output data of the improved analysis algorithm, and formulates an optimization plan based on the output data.

[0019] Specifically, to improve the intelligence of the energy consumption optimization method, steps S1 to S3 are mainly proposed. In S1, the monitoring module collects the real monitoring data of different days in history and uses it as the sending data to be sent to the optimization module. Here, the real monitoring data refers to the monitoring data of the electricity consumption of the smart park equipment. The monitoring module performs obfuscation processing on the sending data to obtain several obfuscated data blocks, and transmits the several obfuscated data blocks to the optimization module through the network module. This is to ensure the security of the sending data during transmission and prevent the sending data from being tampered with, so as to ensure the correctness of the finally formulated optimization plan. In S2, the optimization module recovers the corresponding partial sending data from each obfuscated data block, and then obtains the sending data based on all the partial sending data. The optimization module obtains various types of real condition data of different days in history, determines several observation days among different days in history, and also obtains the trained analysis algorithm, and performs improvement processing on the trained analysis algorithm. It should be noted that although the analysis algorithm has been trained, if the performance of the trained analysis algorithm is not good, it is necessary to continue to improve it. For the sake of understanding, the analysis algorithm can be, for example. In S3, the optimization module calculates the possible condition data of the corresponding type on the target day based on the real condition data of the same type on different days in history. The target day refers to a day that has not yet arrived, and the machine learning algorithm in the prior art can be used for calculation, which will not be elaborated here. The optimization module uses the possible condition data of various types on the target day as the input data of the improved analysis algorithm, aiming to obtain the output data of the improved analysis algorithm. The output data is the estimated data of the electricity consumption of the smart park equipment. Subsequently, an optimization plan is formulated based on the output data. The optimization plan can be, for example, to shorten the equipment working hours.

[0020] Furthermore, the optimization module performs improvement processing on the trained analysis algorithm, including the following steps: S211. For each observation day, the optimization module calculates the possible condition data of various types on the observation day based on the various types of real condition data of different days in history; S212. For each observation day, the optimization module uses the possible condition data of various types on the observation day as the input data of the trained analysis algorithm to obtain the output data of the trained analysis algorithm, and calculates the absolute value of the difference between the output data and the real monitoring data on the observation day; S213. The optimization module calculates the first ratio of the sum of all the absolute values to the total number of all the absolute values, and the optimization module determines whether the first ratio is less than the preset first ratio threshold. If it is less, all steps end. If it is greater than or equal, the first improvement processing is performed on the trained analysis algorithm, and it jumps to S212.

[0021] Specifically, please refer toFigure 2 , introduce the process of the optimization module for improving the trained analysis algorithm. In S211, for each observation day, the optimization module uses the real conditional data of the same type on different days in history to calculate the possible conditional data of the corresponding type on the observation day. Machine learning algorithms in the prior art can be used for the calculation, which will not be elaborated here. In fact, the optimization module uses the real conditional data of the same type on different days before the observation day. In S212, the optimization module takes the possible conditional data of various types on the observation day as the input data of the trained analysis algorithm, obtains the output data of the trained analysis algorithm, and calculates the absolute value of the difference between the output data and the real monitoring data on the observation day. In S213, the optimization module calculates the first ratio of the sum of all absolute values to the total number of all absolute values, and determines whether the first ratio is less than the preset first ratio threshold. The first ratio threshold is set according to the actual application scenario. If it is less, all steps end. If it is greater than or equal, a first improvement process is performed on the trained analysis algorithm, and it jumps to S212 to continue execution. Continuing with the above example of the analysis algorithm, the first improvement process refers to changing at least one of the coefficients to another coefficient.

[0022] Furthermore, the process of the optimization module for improving the trained analysis algorithm further includes the following steps: S221: Regarding the real conditional data of each type on different days in history, the optimization module calculates the second ratio of the sum of all real conditional data to the total number of all real conditional data, and calculates the square value of the difference between each real conditional data and the second ratio. It also calculates the square root value of the third ratio of the sum of all square values to the total number of all square values; S222: The optimization module calculates the possible conditional data of various types on the target day based on the real conditional data of various types on different days in history; S223: Regarding the possible conditional data of each type on the target day, the optimization module calculates the absolute value of the difference between the possible conditional data and the corresponding second ratio, and continues to calculate the fourth ratio of the absolute value to the corresponding square root value; S224: Perform a second improvement process on the trained analysis algorithm based on the fourth ratios corresponding to the possible conditional data of various types on the target day.

[0023] Specifically, please refer to Figure 3, introduce the process of the optimization module to continue to improve the trained analysis algorithm. In S221, for each type of real condition data on different days in history, the optimization module calculates the second ratio of the sum of all real condition data to the total number of all real condition data, calculates the square value of the difference between each real condition data and the second ratio, and also calculates the square root value of the third ratio of the sum of all square values to the total number of all square values. In S222, the optimization module calculates the possible condition data of the corresponding type on the target day based on the real condition data of the same type on different days in history. Machine learning algorithms in the prior art can be used for the calculation, which will not be elaborated here. In S223, for each type of possible condition data on the target day, the optimization module calculates the absolute value of the difference between the possible condition data and the corresponding second ratio. The corresponding second ratio refers to the second ratio of the same type as the type of the possible condition data. Then, continue to calculate the fourth ratio of the absolute value to the corresponding square root value. The corresponding square root value also refers to the square root value of the same type as the type of the possible condition data. In S224, according to the fourth ratios corresponding to various types of possible condition data on the target day, a second improvement process is performed on the trained analysis algorithm. Continuing with the example of the analysis algorithm above, for example, if the fourth ratio corresponding to a certain type of possible condition data is, then the second improvement process refers to using the update as the coefficient corresponding to this type of possible condition data in the analysis algorithm. By continuously improving the trained analysis model, the output accuracy of the trained analysis model can be improved.

[0024] Furthermore, the monitoring module performs obfuscation processing on the transmitted data, including the following steps: S11. The monitoring module divides the transmitted data into several transmitted data blocks, and for each transmitted data block, generates secret data corresponding to the transmitted data block, and also takes the data scale of the transmitted data block as representative data for each transmitted data block; S12. For each transmitted data block, the monitoring module performs secret processing on the transmitted data block using the secret data corresponding to the transmitted data block to obtain an intermediate data block; S13. For each intermediate data block, the monitoring module adds the secret data corresponding to the previous intermediate data block to the intermediate data block based on the representative data corresponding to the intermediate data block to obtain an obfuscated data block.

[0025] Specifically, the process of the monitoring module performing obfuscation processing on the transmitted data is introduced. In S11, the monitoring module divides the transmitted data into several transmitted data blocks. The data scales of the several transmitted data blocks can be different. For each transmitted data block, secret data corresponding to the transmitted data block is generated. The secret data can be understood as the key used in the symmetric encryption algorithm in the prior art. For each transmitted data block, the data scale of the transmitted data block is also used as representative data. The representative data is, for example, the decimal number 8, corresponding to 8 bytes. In S12, for each transmitted data block, the monitoring module uses the secret data corresponding to the transmitted data block to perform secret processing on the transmitted data block. The purpose is to obtain an intermediate data block. The secret processing can be understood as the encryption processing using the symmetric encryption algorithm in the prior art. It should be noted that the data scale of the intermediate data block is the same as that of the transmitted data block corresponding to it. In S13, for each intermediate data block, the monitoring module adds the secret data corresponding to the previous intermediate data block to the intermediate data block based on the representative data corresponding to the intermediate data block, thereby obtaining an obfuscated data block. For the sake of easy understanding, for example, there are transmitted data blocks D1, D2, D3, the secret data K1 corresponding to the transmitted data block D1, the secret data K2 corresponding to the transmitted data block D2, the secret data K3 corresponding to the transmitted data block D3, the intermediate data block T1 corresponding to the transmitted data block D1, the intermediate data block T2 corresponding to the transmitted data block D2, and the intermediate data block T3 corresponding to the transmitted data block D3. Then, the secret data K3 corresponding to the intermediate data block T3 is added to the intermediate data block T1, the secret data K1 corresponding to the intermediate data block T1 is added to the intermediate data block T2, and the secret data K2 corresponding to the intermediate data block T2 is added to the intermediate data block T3.

[0026] Furthermore, the monitoring module adding the secret data corresponding to the previous intermediate data block to the intermediate data block based on the representative data corresponding to the intermediate data block includes the following steps: S131. The monitoring module performs a preset operation on the secret data corresponding to the previous intermediate data block to obtain target data, and performs a preset operation on the representative data corresponding to the intermediate data block to obtain process data; S132. The monitoring module determines whether the process data is greater than the data scale of the intermediate data block. If it is greater, the process data is subtracted by the data scale of the intermediate data block, and this step is repeated. If it is less than or equal, a part of the target data is added to the intermediate data block according to the process data; S133. The monitoring module determines whether the complete target data has been added to the intermediate data block. If not, the process data is updated with the result data obtained by performing a preset operation on the process data, and jumps to S132. If so, all steps are ended.

[0027] Specifically, it is introduced how the monitoring module adds the secret data corresponding to the previous intermediate data block to the intermediate data block based on the representative data corresponding to the intermediate data block. In S131, the monitoring module performs a preset operation on the secret data corresponding to the previous intermediate data block, aiming to obtain target data. The preset operation can be an operation using a hash function. The meaning of the preset operation that appears multiple times in this embodiment is the same. The data scale of the target data is a fixed value set in advance, for example, a decimal number 2, corresponding to 2 bytes. Also, a preset operation is performed on the representative data corresponding to the intermediate data block, aiming to obtain process data. In S132, the monitoring module determines whether the process data is greater than the data scale of the intermediate data block. For the sake of easy understanding, for example, the process data is a binary number 10001, corresponding to a decimal number 18, and the data scale of the intermediate data block is a decimal number 8, corresponding to 8 bytes. Then the process data 18 is greater than the data scale 8 of the intermediate data block. In the case of being greater, the process data is subtracted by the data scale of the intermediate data block, and the judgment process is repeated until the process data is less than or equal to the data scale of the intermediate data block. Continuing to assume that the process data is reduced to 2. In the case of being less than or equal, a part of the target data is added to the intermediate data block according to the process data. For example, the data of the first byte of the target data starting from the left is added after the data of the second byte of the intermediate data block starting from the left. It should be noted that when continuing to add a byte of data of the target data to the intermediate data block, the original intermediate data block is still used as a reference, rather than the intermediate data block after the addition process. In S133, the monitoring module determines whether the complete target data has been added to the intermediate data block, that is, determines whether each byte of data of the target data has been added to the intermediate data block. If not, the process data is updated with the result data of the preset operation performed on the process data, that is, the result data of the preset operation performed on the process data is regarded as the new process data, and it jumps to S132 to continue execution. If so, all steps are ended.

[0028] Furthermore, the optimization module recovers part of the transmitted data from the obfuscated data block, including the following steps: S231. The optimization module determines the data scale of the obfuscated data block, uses the result data obtained by subtracting the preset data from the data scale as the representative data corresponding to the obfuscated data block, and performs a preset operation on the representative data to obtain process data; S232. The optimization module determines whether the process data is greater than the representative data. In the case of being greater, the process data is subtracted by the representative data, and this step is repeated. In the case of being less than or equal, data removal is performed on the obfuscated data block based on the process data; S233. The optimization module determines whether the stop condition is met. If not, it updates the process data with the result data obtained by performing a preset operation on the process data, and jumps to S232. If the condition is met, it performs a restoration process on the obfuscated data to obtain partial transmission data, and ends all steps.

[0029] Specifically, the process of the optimization module recovering partial transmission data from the obfuscated data block is introduced. Before the introduction, it should be noted that the monitoring module sends different obfuscated data blocks in the order of generating different obfuscated data blocks. For example, the transmission data is separated into several transmission data blocks in the order from left to right, and the order of generating different obfuscated data blocks is the same as this order. The order in which the optimization module receives different obfuscated data blocks is the same as the order in which the monitoring module sends different obfuscated data blocks. Therefore, after the optimization module recovers partial transmission data from each obfuscated data block, it can obtain the complete transmission data based on all the partial transmission data.

[0030] In S231, the optimization module determines the data scale of the obfuscated data block, subtracts the preset data from the data scale, and uses the calculated result data as the representative data corresponding to the obfuscated data block. The preset data is the data scale of the target data mentioned above and is a fixed value. For example, it is a decimal number 2, corresponding to 2 bytes. A preset operation is performed on the representative data to obtain the process data. In S232, the optimization module determines whether the process data is greater than the representative data. If it is, the process data is subtracted by the representative data, and this step is repeated until the process data is less than or equal to the representative data. If it is less than or equal, data removal is performed on the obfuscated data block based on the process data. For the sake of understanding, for example, if the process data is 2, then the data after the second byte of the obfuscated data starting from the left is deleted. It should be noted that when continuing the deletion process, the obfuscated data after the deletion process is referred to, rather than the original obfuscated data. In S233, the optimization module determines whether the stop condition is met. The stop condition is, for example, that the data scale of the obfuscated data is equal to the representative data. If not, the process data is updated with the result data obtained by performing a preset operation on the process data, that is, the result data obtained by performing a preset operation on the process data is regarded as the new process data, and it jumps to S232 to continue execution. If not, a restoration process is performed on the obfuscated data to obtain partial transmission data, and all steps are ended. The restoration process can be understood as a decryption process using a symmetric encryption algorithm in the prior art.

[0031] According to another aspect of the embodiments of the present application, with reference to Figure 4As shown, the present application also provides an intelligent park equipment energy consumption optimization system based on machine learning, including a monitoring module, a network module, and an optimization module, to implement the intelligent park equipment energy consumption optimization method described above.

[0032] Among them, the functions of each module are as follows: The monitoring module is used to use the real monitoring data of different days in history as the sending data, perform confusion processing on the sending data to obtain a number of confused data blocks, and transmit the number of confused data blocks to the optimization module through the network module; The network module is used to transmit a number of confused data blocks generated by the monitoring module to the optimization module; The optimization module is used to recover different partial sending data from each confused data block, obtain the sending data based on all the partial sending data, obtain various types of real condition data of different days in history, determine a number of observation days among different days in history, and also obtain a trained analysis algorithm, and perform improvement processing on the trained analysis algorithm; and is used to calculate various types of possible condition data of the target day based on various types of real condition data of different days in history, use the various types of possible condition data of the target day as the input data of the improved analysis algorithm to obtain the output data of the improved analysis algorithm, and formulate an optimization plan according to the output data.

[0033] According to another aspect of the embodiments of the present application, a medium is also provided. The medium stores program instructions, wherein when the program instructions run, the device where the medium is located is controlled to execute any one of the above methods.

[0034] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the above-described system, system, and unit can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0035] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0036] As described above, the above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit them; although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of various embodiments of this application.

Claims

1. A method for optimizing the energy consumption of intelligent park equipment based on machine learning, characterized in that The method includes the following steps: S1. The monitoring module uses the real monitoring data on different days in history as the sending data, performs obfuscation processing on the sending data to obtain a number of obfuscated data blocks, and transmits the number of obfuscated data blocks to the optimization module through the network module; S2. The optimization module recovers different partial sending data from each obfuscated data block, obtains the sending data based on all the partial sending data, and the optimization module obtains various types of real condition data on different days in history, determines a number of observation days among different days in history, and the optimization module also obtains the trained analysis algorithm and performs improvement processing on the trained analysis algorithm; S3. The optimization module calculates various types of possible condition data for the target day based on various types of real condition data on different days in history, and the optimization module uses various types of possible condition data for the target day as the input data of the improved analysis algorithm to obtain the output data of the improved analysis algorithm, and formulates an optimization plan based on the output data.

2. The method according to claim 1, wherein The improvement processing performed by the optimization module on the trained analysis algorithm includes the following steps: S211. For each observation day, the optimization module calculates various types of possible condition data for the observation day based on various types of real condition data on different days in history; S212. For each observation day, use various types of possible condition data for the observation day as the input data of the trained analysis algorithm to obtain the output data of the trained analysis algorithm, and calculate the absolute value of the difference between the output data and the real monitoring data of the observation day; S213. The optimization module calculates the first ratio of the sum of all the absolute values to the total number of all the absolute values, and the optimization module determines whether the first ratio is less than the preset first ratio threshold. If it is less, end all steps. If it is greater than or equal, perform the first improvement processing on the trained analysis algorithm and jump to S212.

3. The method according to claim 2, wherein The improvement processing performed by the optimization module on the trained analysis algorithm further includes the following steps: S221. For each type of real condition data on different days in history, the optimization module calculates the second ratio of the sum of all the real condition data to the total number of all the real condition data, calculates the squared value of the difference between each real condition data and the second ratio, and also calculates the square root value of the third ratio of the sum of all the squared values to the total number of all the squared values; S222. The optimization module calculates various types of possible condition data for the target day based on various types of real condition data on different days in history; S223. For each type of possible condition data for the target day, the optimization module calculates the absolute value of the difference between the possible condition data and the corresponding second ratio, and continues to calculate the fourth ratio of the absolute value to the corresponding square root value; S224. Perform the second improvement processing on the trained analysis algorithm based on the fourth ratio corresponding to various types of possible condition data for the target day.

4. The method according to claim 1, wherein The obfuscation processing performed by the monitoring module on the sending data includes the following steps: S11. The monitoring module divides the sending data into several sending data blocks, and for each sending data block, generates secret data corresponding to the sending data block, and also takes the data scale of the sending data block as representative data for each sending data block; S12. For each sending data block, the monitoring module performs secret processing on the sending data block using the secret data corresponding to the sending data block to obtain an intermediate data block; S13. For each intermediate data block, the monitoring module adds the secret data corresponding to the previous intermediate data block to the intermediate data block based on the representative data corresponding to the intermediate data block to obtain a confused data block.

5. The method according to claim 4, characterized in that The monitoring module adds the secret data corresponding to the previous intermediate data block to the intermediate data block based on the representative data corresponding to the intermediate data block, including the following steps: S131. The monitoring module performs a preset operation on the secret data corresponding to the previous intermediate data block to obtain target data, and performs a preset operation on the representative data corresponding to the intermediate data block to obtain process data; S132. The monitoring module determines whether the process data is greater than the data scale of the intermediate data block. If it is greater, the process data is subtracted by the data scale of the intermediate data block, and this step is repeated. If it is less than or equal, a part of the target data is added to the intermediate data block according to the process data; S133. The monitoring module determines whether the complete target data has been added to the intermediate data block. If not, the process data is updated using the result data obtained by performing a preset operation on the process data, and jumps to S132. If so, all steps are ended.

6. The method according to claim 5, wherein The optimization module recovers part of the sending data from the confused data block, including the following steps: S231. The optimization module determines the data scale of the confused data block, takes the result data obtained by subtracting the preset data from the data scale as the representative data corresponding to the confused data block, and performs a preset operation on the representative data to obtain process data; S232. The optimization module determines whether the process data is greater than the representative data. If it is greater, the process data is subtracted by the representative data, and this step is repeated. If it is less than or equal, data removal is performed on the confused data block based on the process data; S233. The optimization module determines whether the stop condition is met. If not, the process data is updated using the result data obtained by performing a preset operation on the process data, and jumps to S232. If it is met, restoration processing is performed on the confused data to obtain part of the sending data, and all steps are ended.

7. A machine learning-based intelligent park equipment energy consumption optimization system for implementing the method according to any one of claims 1 to 6, characterized in that, Including the following modules: A monitoring module, configured to use the real monitoring data on different days in history as sending data, perform confusion processing on the sending data to obtain several confused data blocks, and transmit the several confused data blocks to the optimization module through a network module; A network module, configured to transmit several confused data blocks generated by the monitoring module to the optimization module; An optimization module, which is used to recover different partial transmission data from each obfuscated data block, obtain the transmission data based on all the partial transmission data, acquire various types of real conditional data on different days in history, determine several observation days among different days in history, and also obtain a trained analysis algorithm, and perform improvement processing on the trained analysis algorithm; And it is used to calculate various types of possible conditional data for the target day based on various types of real conditional data on different days in history, use the various types of possible conditional data for the target day as the input data of the improved analysis algorithm to obtain the output data of the improved analysis algorithm, and formulate an optimization plan based on the output data.

8. A medium, characterized in that, The medium stores program instructions, wherein when the program instructions run, the device where the medium is located is controlled to execute the method according to any one of claims 1 to 6.

Images