Power demand side response evaluation method based on big data analysis

Abstract

The invention discloses a power demand side response evaluation method based on big data analysis, and particularly relates to the technical field of big data. Comprising the steps of S1, time region division, S2, power demand data collection, S3, power demand data preprocessing, S4, power demand data analysis, S5, power load prediction, S6, power load prediction index grade judgment, S7, power demand side response evaluation and S8, man-machine interaction. The sub-time regions of different grades are evaluated through the step of evaluating the power demand side response, and the peak load of the system is reduced and the stability and economy of the power system are improved by adjusting the power consumption behavior of the user and implementing demand side response measures in the power consumption peak period of the user according to different evaluation results, so that the power supply and demand are balanced; the power grid pressure is reduced.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and more specifically, to a method for evaluating power demand side response based on big data analysis. Background Art

[0002] In the electricity market, traditional grid regulation mainly relies on the power supply side and the grid side, while the demand side often becomes a part that rarely participates in electricity regulation. However, with the continuous growth of electricity demand and the increasing complexity of the power system, the participation of the demand side in grid regulation has become increasingly important. The power demand side response can fully tap the potential of demand side resources, accelerate the coordinated interaction of sources, networks, loads and storage, and assist in the construction of new power systems and new energy systems.

[0003] The traditional grid regulation method includes grid data collection step, grid data analysis step and human-computer interaction step. The grid data collection step is used to collect users' electricity consumption data, electricity market price data, etc., to provide basic data support for evaluation; the grid data analysis step processes and analyzes the collected data, including load characteristics analysis, electricity consumption behavior analysis, etc., to reveal the users' electricity consumption patterns; the human-computer interaction step conducts human-computer interaction on the analysis results, and increases the electricity price for users with higher electricity consumption to control users' electricity consumption.

[0004] However, there are still some shortcomings in its actual use. For example, although the human-computer interaction step can reduce users' electricity consumption by raising electricity prices, the user's electricity consumption is still not adjusted during peak electricity consumption periods, so that the electricity consumption is extremely high during peak electricity consumption periods, which may cause the equipment to overload and increase the occurrence of equipment failure. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a power demand side response evaluation method based on big data analysis, which solves the problems raised in the above-mentioned background technology through the following scheme.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] S1: Divide time zone: Set the user's electricity usage time as the time zone, divide the time zone into sub-time zones by equal time division, and mark them as 1, 2..., k respectively;

[0008] S2: Collecting power demand data: Collecting power demand data according to sub-time zones, including equipment operation data, power quality data, and user behavior data;

[0009] S3: preprocessing power demand data: preprocessing the original power demand data collected by S2, and transmitting the preprocessed power demand data to the system operation database;

[0010] S4: Analyze power demand data: Analyze the data pre-processed in S3 to obtain the equipment operation stability coefficient, power quality coefficient and user power consumption ratio coefficient, and transmit the analyzed data to the system operation database;

[0011] S5: Predicting power load: Based on the equipment operation stability coefficient, power quality coefficient and user power consumption ratio coefficient transmitted in S4, the power load is predicted and transmitted to the system operation database;

[0012] S6: Determination of the level of power load forecast index: Determine the level of user power consumption based on the power load forecast index, and transmit the level to the system operation database after determining it;

[0013] S7: Evaluate the power demand side response: Based on the level of the user's power consumption, evaluate the power demand side response of the sub-time zone, calculate the power demand side response evaluation index and transmit it to the system operation database;

[0014] S8: Human-computer interaction: Based on the power demand side response evaluation index, the power consumption is summarized and the summary content is sent to the user terminal according to the preset summary method.

[0015] Preferably, the time zone is composed of a system operation database, a preset analysis database, a system central processing unit and a user information terminal. The system operation database includes all data in the power demand side response evaluation process, and collects the information text output of each step in real time. The preset analysis database stores preset data, including historical average current and average voltage, power demand measurement response evaluation adjustment parameters and preset power demand side response evaluation index. The system central processing module is used to control the information text instructions output by each step. The user information terminal is an information output device for receiving power usage information, and is bound to a mobile phone or any output electronic device based on user information. The equal time division of each sub-time zone selects the appropriate division time accuracy according to actual needs, including every hour, every minute, every half minute, every second and every half second.

[0016] Preferably, the S2 is used to collect power demand data, including an equipment operation data collection unit, a power quality data collection unit, a user behavior data collection unit and a data transmission unit. The equipment operation data collection unit is used to collect equipment operation data, including active power, phase current signal and phase voltage signal; the power quality data collection unit is used to collect power data, including power factor, harmonic content, current imbalance and voltage imbalance, which are respectively denoted as cosφ, Ch, Pi and Pu; the user behavior data collection unit is used to collect user behavior data, including the power load of users in different sub-time zones and the types of electricity consumption of users; the data transmission unit is used to transmit the collected power demand data to the system operation database.

[0017] Preferably, the preprocessing of S3 extracts features from the collected data through big data and machine learning, and specifically includes the following steps:

[0018] A1: Remove outliers, fill in missing values, and correct erroneous values ​​from the power demand data collected by S2 to ensure the integrity and accuracy of the data, and standardize the data to eliminate the impact of different dimensions and data formats;

[0019] A2: Based on the standardized power demand data, the equipment operation data is classified and summarized, and the active power accumulation value is obtained through the active power. The specific calculation formula is: Where Hp represents the active power of a sub-time zone, t represents the division time of the sub-time zone, and t j-1 represents the j-1th sub-time zone, t j represents the jth sub-time zone, Hc represents the accumulated active energy value of a sub-time zone, that is, the energy consumption in the sub-time zone; the phase current signal and the phase voltage signal are filtered and signal conditioned, and the conditioned signals are converted into digital signals, and the phase current data and the phase voltage data are recorded as Hi and Hu respectively;

[0020] A3: Based on the standardized power demand data, the power quality data is classified and summarized to obtain the average harmonic content Ch′, average current imbalance Pi′ and average voltage imbalance Pu′ in the sub-time zone. The specific calculation formula is as follows: Among them, Ch j represents the harmonic content of the jth sub-time region, Pi j represents the current unbalance degree in the jth sub-time zone, Pu j represents the voltage unbalance degree in the jth sub-time zone, Indicates the average current in a time region, Indicates the average voltage amount in the time region;

[0021] A4: Count the types of electricity consumption by users, including residential electricity consumption, agricultural production electricity consumption, and industrial and commercial electricity consumption, and calculate the proportion of each type of electricity consumption;

[0022] A5: Receive the pre-processed data and transmit it to the system operation database.

[0023] Preferably, the S4 obtains the equipment operation stability coefficient, the power quality coefficient and the user power consumption ratio coefficient by using big data technology and establishing a mathematical model, and the specific analysis steps are as follows:

[0024] B1: Receive the data pre-processed by S3;

[0025] B2: Establish equipment operation stability analysis model and calculate equipment operation stability coefficient. The specific analysis formula is:

[0026]

[0027] Where Y represents the equipment operation stability coefficient in a certain sub-time zone, Hc j Indicates the accumulated active energy value in the jth sub-time zone, Hi j represents the phase current data of the jth sub-time zone, Hu j represents the phase voltage data of the j-th sub-time zone;

[0028] B3: Establish a power quality analysis model and calculate the power quality coefficient. The specific analysis formula is:

[0029]

[0030] Where Z represents the power quality coefficient of a sub-time zone, Pi j represents the current unbalance degree in the jth sub-time zone, Pu j represents the voltage unbalance degree in the jth sub-time zone;

[0031] B4: Establish a user electricity consumption ratio analysis model and calculate the user electricity consumption ratio coefficient. The specific analysis formula is:

[0032]

[0033] Among them, U represents the user electricity consumption ratio coefficient of a certain sub-time zone, Fhj represents the power load of the jth sub-time zone, R represents the proportion of residential electricity consumption in the power load, A represents the proportion of agricultural production electricity consumption in the power load, S represents the proportion of industrial and commercial electricity consumption in the power load, Fh1, Fh2 and Fh3 represent the power load thresholds of residential electricity consumption, agricultural production electricity consumption and industrial and commercial electricity consumption respectively.

[0034] B5: Receive the analyzed data and transmit it to the system operation database.

[0035] Preferably, the S5 calculates the power load prediction index based on the equipment operation stability coefficient, the power quality coefficient and the user power consumption ratio coefficient, and the specific analysis formula is: Where P represents the power load forecast index of a sub-time zone, Y, Z and U represent the equipment operation stability coefficient, power quality coefficient and user power consumption ratio coefficient of a sub-time zone respectively, λ1, λ2 and λ3 are the ratio coefficients corresponding to different indicators, λ1>0,

[0036] λ2>0,λ3>0.

[0037] Preferably, the levels of the user's electricity consumption include electricity level I, electricity level II and electricity level III, where electricity level I is the highest peak of the user's electricity consumption forecast, electricity level II is the second highest peak of the user's electricity consumption, and electricity level III is the lowest valley of the user's electricity consumption. The specific process of level determination is as follows:

[0038] C1: According to the power load forecast index, extract the minimum power load forecast index and the maximum power load forecast index, which are denoted as P min and P max ;

[0039] C2: Calculate the difference η between the minimum value of the power load forecast index and the maximum value of the power load forecast index. The specific calculation formula is: And P min Set to the lower limit of power consumption level III, P min ×(1+η / 2) is set as the lower limit of power consumption level II;

[0040] C3: If P<P min , indicating that the power load forecast index is less than the lower limit of power consumption level III, then the level of this sub-time area is determined to be power consumption level III. min <P<P min ×(1+η / 2), indicating that the power load forecast index is less than the lower limit of power level II and greater than the lower limit of power level III, then the sub-time area level is determined to be power level II. If P>P min ×(1+η / 2), indicating that the power forecast index is greater than the lower limit of power level I, and the level of this sub-time area is determined to be power level I.

[0041] Preferably, the S7 is based on the user's electricity consumption level to determine and calculate the power demand side response evaluation index, and the specific analysis formula is: P x=P×(1+φ), where φ is the power demand response evaluation adjustment parameter corresponding to different user power consumption levels. When the sub-time zone is in power consumption level I, φ is φ1; when the sub-time zone is in power consumption level II, φ is φ2; when the sub-time zone is in power consumption level III, φ is φ3, φ1>φ2>φ3.

[0042] Preferably, if the S8 power demand side response evaluation index is less than the preset power demand side response evaluation index, it means that the user's power consumption is at a low period, and the electricity price is lowered through the system central processor; if the power demand side response evaluation index is greater than the preset power demand side response evaluation index, it means that the user's power consumption is at a peak period, and the electricity price is increased through the system central processor, and an alarm is issued, and the user adjusts his or her own power consumption according to the summary content; the summary content includes the user's power consumption and the power price; the preset summary method includes any one of a report summary and a chart summary.

[0043] Technical effects and advantages of the present invention:

[0044] 1. The present invention can realize refined monitoring of the user's electricity consumption in different time periods by dividing the user's electricity consumption time into sub-time areas. Each sub-time area is independently carried out to more accurately capture the subtle changes in electricity consumption, and provide more accurate data support for subsequent data analysis and prediction; through the step of collecting power demand data, the device operation data, power quality data and user behavior data are collected in real time, and these data are important bases for obtaining the user's electricity consumption; through the step of pre-processing the power demand data, the collected power demand data is further processed, so that the subsequent analysis is more convenient and the resource utilization rate is improved; the pre-processed data is analyzed to establish an equipment operation stability analysis model, a power quality analysis model and a user electricity consumption ratio analysis model, so as to obtain the equipment operation stability coefficient, the power quality coefficient and the user electricity consumption ratio coefficient;

[0045] 2. The power load situation is predicted through the power load prediction step, which can intuitively reflect the user's power consumption in the sub-time area and provide a basis for the power load prediction index level determination step; the power load prediction index level determination step determines the level of the user's power consumption based on the power load prediction index to ensure that different power adjustment measures are taken for different power consumption ranges; the sub-time areas of different levels are evaluated through the power demand side response evaluation step; the human-computer interaction step formulates personalized demand side response strategies according to different evaluation results. During the peak period of user power consumption, the system peak load is reduced by implementing demand side response measures, thereby improving the stability and economy of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1It is a flow chart of the system operation of the present invention.

[0047] Figure 2 This is a flow chart of pre-processing power demand data of the present invention.

[0048] Figure 3 This is a flow chart for determining the level of a user's electricity usage according to the present invention. DETAILED DESCRIPTION

[0049] 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.

[0050] As attached Figure 1 A method for evaluating power demand side response based on big data analysis is shown, and the flow chart mainly includes the following steps: S1 to S8.

[0051] S1: Divide time zone: Set the user's electricity usage time as a time zone, divide the time zone into sub-time zones by equal time division, and mark them as 1, 2..., k respectively.

[0052] In this embodiment, it should be specifically explained that the time zone is composed of a system operation database, a preset analysis database, a system central processing unit and a user information terminal. The system operation database includes all data in the power demand side response evaluation process, and collects the information text output of each step in real time. The preset analysis database stores preset data, including historical average current and average voltage, power demand measurement response evaluation adjustment parameters and preset power demand side response evaluation index. The system central processing module is used to control the information text instructions output by each step. The user information terminal is an information output device for receiving power usage information, and is bound to a mobile phone or any output electronic device based on user information. The equal time division of each sub-time zone selects the appropriate division time accuracy according to actual needs, including every hour, every minute, every half minute, every second and every half second.

[0053] S2: Collecting power demand data: Collecting power demand data according to sub-time zones, including equipment operation data, power quality data, and user behavior data.

[0054] In this embodiment, it should be specifically explained that S2 is used to collect power demand data, including an equipment operation data collection unit, a power quality data collection unit, a user behavior data collection unit and a data transmission unit. The equipment operation data collection unit is used to collect equipment operation data, including active power, phase current signal and phase voltage signal; the power quality data collection unit is used to collect power data, including power factor, harmonic content, current imbalance and voltage imbalance, which are respectively denoted as cosφ, Ch, Pi and Pu; the user behavior data collection unit is used to collect user behavior data, including the power load of users in different sub-time zones and the types of electricity consumption of users; the data transmission unit is used to transmit the collected power demand data to the system operation database.

[0055] S3: Preprocessing power demand data: Preprocessing the original power demand data collected by S2, and transmitting the preprocessed power demand data to the system operation database.

[0056] In this embodiment, it should be specifically explained that the preprocessing of S3 extracts features from the collected data through big data and machine learning, which specifically includes the following steps:

[0057] A1: Remove outliers, fill in missing values, and correct erroneous values ​​from the power demand data collected by S2 to ensure the integrity and accuracy of the data, and standardize the data to eliminate the impact of different dimensions and data formats;

[0058] A2: Based on the standardized power demand data, the equipment operation data is classified and summarized, and the active power accumulation value is obtained through the active power. The specific calculation formula is: Where Hp represents the active power of a sub-time zone, t represents the division time of the sub-time zone, and t j-1 represents the j-1th sub-time zone, t j represents the jth sub-time zone, Hc represents the accumulated active energy value of a sub-time zone, that is, the energy consumption in the sub-time zone; the phase current signal and the phase voltage signal are filtered and signal conditioned, and the conditioned signals are converted into digital signals, and the phase current data and the phase voltage data are recorded as Hi and Hu respectively;

[0059] A3: Based on the standardized power demand data, the power quality data is classified and summarized to obtain the average harmonic content Ch′, average current imbalance Pi′ and average voltage imbalance Pu′ in the sub-time zone. The specific calculation formula is as follows: Among them, Ch j represents the harmonic content of the jth sub-time region, Pi j represents the current unbalance degree in the jth sub-time zone, Pu jrepresents the voltage unbalance degree in the jth sub-time zone, Indicates the average current in a time region, Indicates the average voltage amount in the time region;

[0060] A4: Count the types of electricity consumption by users, including residential electricity consumption, agricultural production electricity consumption, and industrial and commercial electricity consumption, and calculate the proportion of each type of electricity consumption;

[0061] A5: Receive the pre-processed data and transmit it to the system operation database.

[0062] S4: Analyze power demand data: Analyze the data pre-processed in S3 to obtain the equipment operation stability coefficient, power quality coefficient and user power consumption ratio coefficient, and transmit the analyzed data to the system operation database.

[0063] In this embodiment, it should be specifically explained that S4 obtains the equipment operation stability coefficient, power quality coefficient and user power consumption ratio coefficient by using big data technology and establishing a mathematical model. The specific analysis steps are as follows:

[0064] B1: Receive the data pre-processed by S3;

[0065] B2: Establish equipment operation stability analysis model and calculate equipment operation stability coefficient. The specific analysis formula is:

[0066]

[0067] Where Y represents the equipment operation stability coefficient in a certain sub-time zone, Hc j Indicates the accumulated active energy value in the jth sub-time zone, Hi j represents the phase current data of the jth sub-time zone, Hu j represents the phase voltage data of the j-th sub-time zone;

[0068] B3: Establish a power quality analysis model and calculate the power quality coefficient. The specific analysis formula is:

[0069]

[0070] Where Z represents the power quality coefficient of a sub-time zone, Pi j represents the current unbalance degree in the jth sub-time zone, Pu j represents the voltage unbalance degree in the jth sub-time zone;

[0071] B4: Establish a user electricity consumption ratio analysis model and calculate the user electricity consumption ratio coefficient. The specific analysis formula is:

[0072]

[0073] Among them, U represents the user electricity consumption ratio coefficient of a certain sub-time zone, Fhj represents the power load of the jth sub-time zone, R represents the proportion of residential electricity consumption in the power load, A represents the proportion of agricultural production electricity consumption in the power load, S represents the proportion of industrial and commercial electricity consumption in the power load, Fh1, Fh2 and Fh3 represent the power load thresholds of residential electricity consumption, agricultural production electricity consumption and industrial and commercial electricity consumption respectively.

[0074] B5: Receive the analyzed data and transmit it to the system operation database.

[0075] S5: Predicting power load: Based on the equipment operation stability coefficient, power quality coefficient and user power consumption ratio coefficient transmitted by S4, the power load is predicted and transmitted to the system operation database.

[0076] In this embodiment, it should be specifically explained that S5 calculates the power load prediction index based on the equipment operation stability coefficient, the power quality coefficient and the user power consumption ratio coefficient, and the specific analysis formula is:

[0077]

[0078] Where P represents the power load forecast index of a sub-time zone, Y, Z and U represent the equipment operation stability coefficient, power quality coefficient and user power consumption ratio coefficient of a sub-time zone respectively, λ1, λ2 and λ3 are the ratio coefficients corresponding to different indicators, λ1>0, λ2>0 and λ3>0.

[0079] S6: Determination of the level of power load forecast index: Determine the level of user power consumption based on the power load forecast index, and transmit the level to the system operation database after it is determined.

[0080] In this embodiment, it should be specifically explained that the levels of the user's electricity consumption include electricity level I, electricity level II and electricity level III, where electricity level I is the highest peak of the user's electricity consumption forecast, electricity level II is the second highest peak of the user's electricity consumption, and electricity level III is the lowest valley of the user's electricity consumption. The specific process of level determination is as follows:

[0081] C1: According to the power load forecast index, extract the minimum power load forecast index and the maximum power load forecast index, which are denoted as P min and P max ;

[0082] C2: Calculate the difference η between the minimum value of the power load forecast index and the maximum value of the power load forecast index. The specific calculation formula is: And P min Set to the lower limit of power consumption level III, P min×(1+η / 2) is set as the lower limit of power consumption level II;

[0083] C3: If P<P min , indicating that the power load forecast index is less than the lower limit of power consumption level III, then the level of this sub-time area is determined to be power consumption level III. min <P<P min ×(1+η / 2), indicating that the power load forecast index is less than the lower limit of power level II and greater than the lower limit of power level III, then the sub-time area level is determined to be power level II. If P>P min ×(1+η / 2), indicating that the power forecast index is greater than the lower limit of power level I, and the level of this sub-time area is determined to be power level I.

[0084] S7: Evaluate the power demand side response: Based on the level of the user's power consumption, evaluate the power demand side response of the sub-time zone, calculate the power demand side response evaluation index and transmit it to the system operation database.

[0085] In this embodiment, it should be specifically explained that S7 calculates the power demand side response evaluation index based on the level of the user's power consumption, and the specific analysis formula is: x =P×(1+φ), where φ is the power demand response evaluation adjustment parameter corresponding to different user power consumption levels. When the sub-time zone is in power consumption level I, φ is φ1; when the sub-time zone is in power consumption level II, φ is φ2; when the sub-time zone is in power consumption level III, φ is φ3, φ1>φ2>φ3.

[0086] S8: Human-computer interaction: Based on the power demand side response evaluation index, the power consumption is summarized and the summary content is sent to the user terminal according to the preset summary method.

[0087] In this embodiment, it should be specifically noted that if the S8 power demand side response evaluation index is less than the preset power demand side response evaluation index, it means that the user's power consumption is at a low point at this time, then the electricity price will be lowered through the system central processor. If the power demand side response evaluation index is greater than the preset power demand side response evaluation index, it means that the user's power consumption is at a peak point at this time, then the electricity price will be increased through the system central processor, and an alarm will be issued. The user will adjust his or her own power consumption according to the summary content; the summary content includes the user's power consumption and the power price; the preset summary method includes any one of a report summary and a chart summary.

[0088] The present invention can realize the refined monitoring of the user's electricity consumption in different time periods by dividing the user's electricity consumption time into sub-time areas. Each sub-time area is carried out independently, so as to more accurately capture the subtle changes in electricity consumption and provide more accurate data support for subsequent data analysis and prediction; the power demand data collection step collects equipment operation data, power quality data and user behavior data in real time, and these data are important bases for obtaining the user's electricity consumption; the power demand data preprocessing step further processes the collected power demand data, making subsequent analysis more convenient and improving resource utilization; the preprocessed data is analyzed to establish an equipment operation stability analysis model, a power quality analysis model and a user electricity consumption ratio analysis model, so as to obtain Equipment operation stability coefficient, power quality coefficient and user electricity consumption ratio coefficient; predicting the power load situation through the power load prediction step can intuitively reflect the user's power consumption in the sub-time area, providing a basis for the power load prediction index level determination step; the power load prediction index level determination step determines the level of user power consumption based on the power load prediction index to ensure that different power adjustment measures are taken for different power consumption ranges; evaluating sub-time areas of different levels through the power demand side response step; the human-computer interaction step formulates personalized demand side response strategies based on different evaluation results. During the peak period of user power consumption, the system peak load is reduced by implementing demand side response measures, thereby improving the stability and economy of the power system.

[0089] Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other;

[0090] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A power demand side response evaluation method based on big data analysis, characterized in that: include: S1: Divide time zone: Set the user's electricity usage time as the time zone, divide the time zone into sub-time zones by equal time division, and mark them as 1, 2..., k respectively; S2: Collecting power demand data: Collecting power demand data according to sub-time zones, wherein the power demand data includes equipment operation data, power quality data, and user behavior data; S3: preprocessing power demand data: preprocessing the original power demand data collected by S2, and transmitting the preprocessed power demand data to the system operation database; S4: Analyze power demand data: Analyze the data pre-processed in S3 to obtain the equipment operation stability coefficient, power quality coefficient and user power consumption ratio coefficient, and transmit the analyzed data to the system operation database; S5: Predicting power load: Based on the equipment operation stability coefficient, power quality coefficient and user power consumption ratio coefficient transmitted in S4, the power load is predicted and transmitted to the system operation database; S6: Determination of the level of power load forecast index: Determine the level of user power consumption based on the power load forecast index, and transmit the level to the system operation database after determining it; S7: Evaluate the power demand side response: Based on the level of the user's power consumption, evaluate the power demand side response of the sub-time zone, calculate the power demand side response evaluation index and transmit it to the system operation database; S8: Human-computer interaction: Based on the power demand side response evaluation index, the power consumption is summarized and the summary content is sent to the user terminal according to the preset summary method.

2. The power demand side response evaluation method based on big data analysis according to claim 1 is characterized by: The time zone is composed of a system operation database, a preset analysis database, a system central processor and a user information terminal. The system operation database includes all data in the power demand side response evaluation process, and collects the information text output of each step in real time. The preset analysis database stores preset data, including historical user power average current and average voltage, power demand measurement response evaluation adjustment parameters and preset power demand side response evaluation index. The system central processing module is used to control the information text instructions output by each step. The user information terminal is an information output device for receiving power usage information, and is bound to a mobile phone or any output electronic device based on user information. The equal time division of each sub-time zone selects the appropriate division time accuracy according to actual needs, including every hour, every minute, every half minute, every second and every half second.

3. The power demand side response evaluation method based on big data analysis according to claim 1 is characterized by: The S2 is used to collect power demand data, including an equipment operation data collection unit, a power quality data collection unit, a user behavior data collection unit and a data transmission unit. The equipment operation data collection unit is used to collect equipment operation data, including active power, phase current signal and phase voltage signal; The power quality data acquisition unit is used to collect power data, including power factor, harmonic content, current unbalance and voltage unbalance, which are recorded as cosφ, Ch, Pi and Pu respectively; the user behavior data acquisition unit is used to collect user behavior data, including the power load of users in different sub-time zones and the types of electricity consumption of users; The data transmission unit is used to transmit the collected power demand data to the system operation database.

4. The method for evaluating power demand response based on big data analysis according to claim 1 is characterized in that: The S3 standardizes the data through big data and machine learning, classifies and summarizes the equipment operation data based on the standardized power demand data, and obtains the active power accumulation value through the active power. The specific calculation formula is: Where Hp represents the active power of a sub-time zone, t represents the division time of the sub-time zone, and t j-1 represents the j-1th sub-time zone, t j represents the jth sub-time zone, Hc represents the accumulated active energy value of a sub-time zone, that is, the energy consumption in the sub-time zone; the phase current signal and the phase voltage signal are filtered and conditioned, and the conditioned signals are converted into digital signals, and the phase current data and the phase voltage data are recorded as Hi and Hu respectively; the power quality data are classified and summarized to obtain the average harmonic content Ch′, the average current imbalance Pi′ and the average voltage imbalance Pu′ of the sub-time zone. The specific calculation formula is as follows: Among them, Ch j represents the harmonic content of the jth sub-time region, Pi j represents the current unbalance degree in the jth sub-time zone, Pu j represents the voltage unbalance degree in the jth sub-time zone, Indicates the historical average current in the time zone, Indicates the historical average voltage in a time zone; counts the types of electricity consumption by users, including residential electricity consumption, agricultural production electricity consumption, and industrial and commercial electricity consumption, and calculates the proportion of each type of electricity consumption.

5. The method for evaluating power demand response based on big data analysis according to claim 1 is characterized in that: The S4 obtains the equipment operation stability coefficient, power quality coefficient and user power consumption ratio coefficient through big data technology and mathematical model establishment. The specific analysis steps are as follows: B1: Receive the data pre-processed by S3; B2: Establish equipment operation stability analysis model and calculate equipment operation stability coefficient. The specific analysis formula is: Where Y represents the equipment operation stability coefficient in a certain sub-time zone, Hc j Indicates the accumulated active energy value in the jth sub-time zone, Hi j represents the phase current data of the jth sub-time zone, Hu j represents the phase voltage data of the j-th sub-time zone; B3: Establish a power quality analysis model and calculate the power quality coefficient. The specific analysis formula is: Where Z represents the power quality coefficient of a sub-time zone, Pi j represents the current unbalance degree in the jth sub-time zone, Pu j represents the voltage unbalance degree in the jth sub-time zone; B4: Establish a user electricity consumption ratio analysis model and calculate the user electricity consumption ratio coefficient. The specific analysis formula is: Among them, U represents the user electricity consumption ratio coefficient of a certain sub-time zone, Fhj represents the power load of the jth sub-time zone, R represents the proportion of residential electricity consumption in the power load, A represents the proportion of agricultural production electricity consumption in the power load, S represents the proportion of industrial and commercial electricity consumption in the power load, Fh1, Fh2 and Fh3 represent the power load thresholds of residential electricity consumption, agricultural production electricity consumption and industrial and commercial electricity consumption respectively; B5: Receive the analyzed data and transmit it to the system operation database.

6. The method for evaluating power demand response based on big data analysis according to claim 1, characterized in that: The S5 calculates the power load prediction index based on the equipment operation stability coefficient, the power quality coefficient and the user power consumption ratio coefficient. The specific analysis formula is: Where P represents the power load forecast index of a sub-time zone, Y, Z and U represent the equipment operation stability coefficient, power quality coefficient and user power consumption ratio coefficient of a sub-time zone respectively, λ1, λ2 and λ3 are the ratio coefficients corresponding to different indicators, λ1>0, λ2>0 and λ3>0.

7. The method for evaluating power demand response based on big data analysis according to claim 1, characterized in that: The levels of the user's electricity consumption include electricity level I, electricity level II and electricity level III, where electricity level I is the highest peak of the user's electricity consumption forecast, electricity level II is the second peak of the user's electricity consumption, and electricity level III is the lowest valley of the user's electricity consumption; according to the power load forecast index, the minimum value of the power load forecast index and the maximum value of the power load forecast index are extracted, which are respectively recorded as P min and P max ; Calculate the difference η between the minimum value of the power load forecast index and the maximum value of the power load forecast index. The specific calculation formula is: And P min Set to the lower limit of power consumption level III, P min ×(1+η / 2) is set as the lower limit of power consumption level II; If P<P min , indicating that the power load forecast index is less than the lower limit of power consumption level III, then the level of this sub-time area is determined to be power consumption level III. min <P<P min ×(1+η / 2), indicating that the power load forecast index is less than the lower limit of power level II and greater than the lower limit of power level III, then the sub-time area level is determined to be power level II. If P>P min ×(1+η / 2), indicating that the power forecast index is greater than the lower limit of power level I, and the level of this sub-time area is determined to be power level I.

8. The method for evaluating power demand response based on big data analysis according to claim 1, characterized in that: The S7 determines and calculates the power demand side response evaluation index based on the level of the user's power consumption, and the specific analysis formula is: x =P×(1+φ), where φ is the power demand response evaluation adjustment parameter corresponding to different user power consumption levels. When the sub-time zone is in power consumption level I, φ is φ1; when the sub-time zone is in power consumption level II, φ is φ2; when the sub-time zone is in power consumption level III, φ is φ3, φ1>φ2>φ3.

9. The method for evaluating power demand response based on big data analysis according to claim 1, characterized in that: If the S8 power demand side response evaluation index is less than the preset power demand side response evaluation index, it means that the user's power consumption is at a low point at this time, and the electricity price is reduced through the system central processor. If the power demand side response evaluation index is greater than the preset power demand side response evaluation index, it means that the user's power consumption is at a peak point at this time, and the electricity price is increased through the system central processor, and an alarm is issued, and the user adjusts his or her own power consumption according to the summary content; the summary content includes the user's power consumption and the power price; the preset summary method includes any one of a report summary and a chart summary.

Images