Method and system for adjusting real-time electricity price of smart power grid

Abstract

The invention relates to the technical field of smart power grids, and discloses a smart power grid real-time electricity price adjustment method and system, and the method comprises the steps: collecting user electricity consumption data in real time through a sensor, and carrying out the preprocessing; clustering the power utilization data of the users, dividing the users into different groups, and designing a personalized electricity price strategy; and dynamically adjusting the electricity price by adopting a preset rule according to the real-time load state of the power grid. The electricity utilization data of the users are collected in real time, personalized clustering is carried out, the electricity price is dynamically adjusted in combination with the load state of the power grid, and a more flexible and accurate electricity price strategy is achieved. The method not only can improve the supply and demand balance of the power grid, but also encourages the user to adjust the power consumption behavior in the peak period through a differential pricing strategy, supports the demands of renewable energy sources and electric vehicle users, facilitates the optimization of the use of power grid resources, and improves the overall efficiency and sustainability of a power system.

Description

Technical Field

[0001] The present invention relates to the field of smart grid technology, and in particular to a smart grid real-time electricity price adjustment method and system. Background Art

[0002] With the continuous growth of global energy demand, the intelligent and efficient operation of power systems has become an important development direction of the current power industry. As a modern upgrade of the power system, smart grid integrates advanced information and communication technology, automation control technology and energy management technology, aiming to achieve the optimal configuration of electricity, intelligent scheduling of energy and efficient implementation of demand response. In recent years, the application of smart grids in various countries has gradually expanded, especially with the large-scale access of renewable energy, the advantages of smart grids have become more and more significant. Smart grids can dynamically adjust electricity prices according to the real-time load status of the power grid by real-time monitoring of power grid load, user power consumption behavior and the operating status of power equipment, so as to achieve the balance of power grid load and the reasonable allocation of power demand. Compared with traditional power systems, smart grids have higher flexibility and efficiency, and can optimize the allocation of power resources through load management, demand response and smart metering technology.

[0003] However, although the existing smart grid technology has made some progress, there are still some shortcomings in the electricity price adjustment mechanism, user demand response and grid load management. The existing electricity price adjustment methods often rely on simple time period electricity price differences or fixed price adjustment strategies, and fail to fully consider the individual differences of users and the real-time load fluctuations of the power grid. Traditional electricity price adjustment strategies usually lack personalized customization and are difficult to make precise adjustments based on the load requirements, electricity consumption periods and response capabilities of different users. At the same time, the existing electricity price adjustment methods are not flexible enough in responding to rapid changes in grid load and emergencies, and fail to make full use of real-time data to dynamically optimize electricity prices, which may lead to excessive concentration of grid load or waste of resources. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is that the existing smart grid electricity price adjustment method lacks personalization, the electricity price adjustment is not flexible enough, and the response is not timely.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for adjusting the real-time electricity price of a smart grid, comprising:

[0007] Collect user electricity consumption data in real time through sensors and perform pre-processing;

[0008] Cluster user electricity consumption data, divide users into different groups, and design personalized electricity price strategies;

[0009] According to the real-time load status of the power grid, the electricity price is dynamically adjusted using preset rules.

[0010] As a preferred solution of the smart grid real-time electricity price adjustment method of the present invention, wherein:

[0011] The user electricity consumption data includes electricity consumption data, electricity consumption period data, load demand data, electricity consumption behavior characteristics, historical data, renewable energy data and electricity price response data;

[0012] Preprocessing includes cleaning missing values, duplicate data and outliers from user electricity consumption data through ETL tools; unifying the units and formats of user electricity consumption data, and performing multi-source data fusion and data quality checks.

[0013] As a preferred solution of the smart grid real-time electricity price adjustment method of the present invention, wherein:

[0014] The user classification into different groups includes clustering the power consumption behavior characteristics, power consumption time periods and load characteristics using a hierarchical clustering algorithm based on the collected user power consumption data. The formula is expressed as follows:

[0015]

[0016] Among them, D total represents the total clustering metric, M represents the total number of samples, and w ij represents the weight between sample i and sample j, d i,j represents the distance metric between sample i and sample j, α represents the parameter that controls the influence of distance metric on clustering quality, and D cluster represents the clustering metric, β represents the parameter that controls the influence of the clustering metric on the total metric, n represents the dimension of the feature space, and w k represents the weight of the kth feature, f k (x i ) represents the value of the kth feature on sample i, f k (x j ) represents the value of the kth feature on sample j, x i represents all eigenvalues ​​of sample i, x j represents all eigenvalues ​​of sample j, μ k Represents the cluster center value of the kth feature;

[0017] The electricity consumption behavior characteristics include daily total electricity consumption, maximum load, and electricity consumption fluctuation;

[0018] The electricity consumption period includes peak electricity consumption period and off-peak electricity consumption period;

[0019] The load characteristics include load curve and load stability.

[0020] As a preferred solution of the real-time electricity price adjustment method for the smart grid of the present invention, wherein: dividing users into different groups also includes, based on the clustering results, dividing users into a high-load user group, a low-load user group, a high-responsiveness user group, a renewable energy user group and an electric vehicle user group, the formula is expressed as:

[0021]

[0022] Among them, G(u) represents the group to which user u belongs, Load(u) represents the total load of user u, and L threshold represents the load threshold, Response(u) represents the responsiveness of user u to changes in electricity prices, and R threshold represents the threshold of responsiveness, RenewableEnergyUsage(u) represents the proportion of renewable energy used by user u, and E threshold represents the threshold of renewable energy use, EVUsage(u) indicates whether user u uses an electric vehicle, T threshold Indicates the threshold for electric vehicle use.

[0023] As a preferred solution of the real-time electricity price adjustment method of the smart grid described in the present invention, wherein: the personalized electricity price strategy includes designing a suitable electricity price strategy according to the characteristics of each group;

[0024] The electricity price strategy for the high-load user group includes increasing the electricity price to 1.3 times the original price during the peak load period of the power grid, and reducing the electricity price to 0.65 times the original price during the low load period of the power grid;

[0025] The electricity price strategy for low-load user groups includes reducing the electricity price to 0.45 times the original price during off-peak hours;

[0026] The electricity price strategy for the high-responsiveness user group includes providing customized electricity prices according to the actual responsiveness of users during high-load periods;

[0027] The electricity price strategy for renewable energy user groups includes providing a subsidy of 1.15 times the original electricity price per kilowatt-hour when they deliver excess electricity to the grid;

[0028] The electricity price strategy for electric vehicle user groups includes reducing the electricity price to 0.85 times the original price during periods of low grid load.

[0029] As a preferred solution of the real-time electricity price adjustment method of the smart grid of the present invention, wherein: dynamically adjusting the electricity price according to the real-time load state of the power grid by using preset rules includes using user electricity consumption data collected in real time by sensors to monitor the real-time load state of the power grid and set the load threshold of the power grid;

[0030] The setting of the grid load threshold includes training a regression model using historical data, predicting a dynamic adjustment factor, and calculating peak and valley load thresholds, which are expressed as follows:

[0031]

[0032] in, Represents the estimated value vector of the regression coefficients, including β0,β1,…,β n , used to describe the relationship between independent variables and dependent variables; X represents the independent variable matrix, including historical load data L t and related external influencing factors; X T represents the transpose of the independent variable matrix X, and Y represents the dependent variable vector; represents the dynamic adjustment factor at time t predicted by the regression model, represents the intercept term of the regression model, represents the regression coefficient, L t represents the grid load data at time t, X t1 ,X t2 ,…,X tn Represents external influencing factors related to grid load; L peak (t) represents the peak load threshold at time t, μ represents the mean of historical load data, κ represents the load threshold adjustment coefficient, σ represents the standard deviation of historical load data, and L valley (t) represents the valley load threshold at time t.

[0033] As a preferred solution of the real-time electricity price adjustment method of the smart grid described in the present invention, wherein: dynamically adjusting the electricity price using preset rules according to the real-time load state of the power grid also includes establishing a rule engine according to the load threshold of the power grid to automatically adjust the electricity price;

[0034] The rules engine includes that when the load on the power grid exceeds the set peak load threshold, the electricity price is automatically increased to 1.35 times the original price;

[0035] When the load of the power grid is lower than the set off-peak load threshold, the electricity price is automatically reduced to 0.45 times the original price;

[0036] When the grid load increases dramatically, the electricity price will automatically increase to 1.5 times the original price;

[0037] When the grid load drops sharply, the electricity price will automatically drop to 0.35 times the original price.

[0038] A smart grid real-time electricity price adjustment system, wherein:

[0039] The data module collects user electricity consumption data in real time through sensors and performs pre-processing;

[0040] Divide the module, cluster the user's electricity consumption data, divide the users into different groups, and design personalized electricity price strategies;

[0041] The adjustment module dynamically adjusts the electricity price using preset rules according to the real-time load status of the power grid.

[0042] A computer device comprises: a memory and a processor; the memory stores a computer program, wherein the processor implements the steps of any one of the methods of the present invention when executing the computer program.

[0043] A computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of any one of the methods of the present invention.

[0044] Beneficial effects of the invention: The real-time electricity price adjustment method for smart grids provided by the invention collects user electricity consumption data in real time and performs personalized clustering, and dynamically adjusts electricity prices in combination with the load status of the power grid, thereby realizing a more flexible and accurate electricity price strategy. It can not only improve the supply and demand balance of the power grid, but also encourage users to adjust their electricity consumption behavior during peak hours through differentiated pricing strategies, while supporting the needs of renewable energy and electric vehicle users, helping to optimize the use of power grid resources and improve the overall efficiency and sustainability of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0046] Figure 1 An overall flow chart of a smart grid real-time electricity price adjustment method provided for the first embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0048] Example 1, reference Figure 1 , is an embodiment of the present invention, and provides a smart grid real-time electricity price adjustment method, comprising:

[0049] S1: Collect user electricity consumption data in real time through sensors and perform preprocessing.

[0050] User electricity consumption data includes electricity consumption data, electricity consumption period data, load demand data, electricity consumption behavior characteristics, historical data, renewable energy data and electricity price response data;

[0051] Preprocessing includes cleaning missing values, duplicate data and outliers from user electricity consumption data through ETL tools; unifying the units and formats of user electricity consumption data, and performing multi-source data fusion and data quality checks.

[0052] Furthermore, through the real-time collection and preprocessing of user electricity consumption data, a high-quality data foundation is provided for subsequent analysis and decision-making. The data collected in real time by sensors covers multiple dimensions of information such as user electricity consumption, electricity consumption period, load demand, electricity consumption behavior characteristics, historical data, renewable energy usage, and electricity price response, which can fully reflect the user's electricity consumption behavior and needs. By using ETL tools to clean up data, missing values, duplicate data, and outliers are removed to improve data accuracy and consistency. Unifying data units and formats and fusing multi-source data can solve data incompatibility issues between different devices and systems and ensure the availability and reliability of data in subsequent analysis.

[0053] S2: Cluster user electricity consumption data, divide users into different groups, and design personalized electricity price strategies.

[0054] Dividing users into different groups includes clustering electricity consumption behavior characteristics, electricity consumption time periods and load characteristics based on the collected user electricity consumption data using a hierarchical clustering algorithm. The formula is expressed as:

[0055]

[0056] Among them, D total represents the total clustering metric, M represents the total number of samples, and w ij represents the weight between sample i and sample j, di,j represents the distance metric between sample i and sample j, α represents the parameter that controls the influence of distance metric on clustering quality, and D cluster represents the clustering metric, β represents the parameter that controls the influence of the clustering metric on the total metric, n represents the dimension of the feature space, and w k represents the weight of the kth feature, f k (x i ) represents the value of the kth feature on sample i, f k (x j ) represents the value of the kth feature on sample j, x i represents all eigenvalues ​​of sample i, x j represents all eigenvalues ​​of sample j, μ k Represents the cluster center value of the kth feature.

[0057] The electricity consumption behavior characteristics include daily total electricity consumption, maximum load, and electricity consumption fluctuation.

[0058] The formula for total daily electricity consumption is:

[0059]

[0060] Among them, E total (x i ) represents user x i The total daily electricity consumption, P(x i ,t) represents user x i The power consumption at time t, T represents the total number of time periods in a day; Δt represents the length of each time period.

[0061] The formula for the maximum load is:

[0062]

[0063] Among them, Load max (x i ) represents user x i The maximum load in a day, P(x i ,t) represents user x i Power consumption at time t.

[0064] The formula for electrical volatility is:

[0065]

[0066] Among them, Var(x i ) represents user x i The fluctuation of electricity consumption, Represents user x i The average electricity consumption.

[0067] The electricity consumption period includes peak electricity consumption time period and off-peak electricity consumption time period.

[0068] The formula for peak electricity consumption behavior is:

[0069]

[0070] Among them, (x i ) represents user x i The power consumption during peak hours; T peak Represents a collection of peak hour indexes.

[0071] The formula for electricity consumption during off-peak hours is:

[0072]

[0073] Among them, E off-peak (x i ) represents user x i The power consumption during off-peak hours; T off-peak Represents the trough period index collection.

[0074] The load characteristics include load curve and load stability.

[0075] The formula for the load curve is:

[0076] Load Curve(x i )={P(x i ,t)|t∈[1,T]}

[0077] Among them, Load Curve(x i ) represents user x i The load curve.

[0078]

[0079] Show user x i The average load.

[0080] Based on the clustering results, users are divided into high-load user group, low-load user group, high-response user group, renewable energy user group and electric vehicle user group. The formula is expressed as:

[0081]

[0082] Among them, G(u) represents the group to which user u belongs, Load(u) represents the total load of user u, and L threshold represents the load threshold, Response(u) represents the responsiveness of user u to changes in electricity prices, and R thresholdrepresents the threshold of responsiveness, RenewableEnergyUsage(u) represents the proportion of renewable energy used by user u, and E threshold represents the threshold of renewable energy use, EVUsage(u) indicates whether user u uses an electric vehicle, T threshold Indicates the threshold for electric vehicle use.

[0083] Personalized electricity pricing strategies include designing appropriate electricity pricing strategies based on the characteristics of each group.

[0084] The electricity price strategy for the high-load user group includes increasing the electricity price to 1.3 times the original price during the peak load period of the power grid, and reducing the electricity price to 0.65 times the original price during the low load period of the power grid.

[0085] The electricity price strategy for low-load user groups includes reducing the electricity price to 0.45 times the original price during off-peak hours;

[0086] The electricity price strategy for high-responsiveness user groups includes providing customized electricity prices according to the users' actual responsiveness during high-load periods.

[0087] The electricity price strategy for renewable energy user groups includes providing a subsidy of 1.15 times the original electricity price per kilowatt-hour when they deliver excess electricity to the grid.

[0088] The electricity price strategy for electric vehicle user groups includes reducing the electricity price to 0.85 times the original price during periods of low grid load.

[0089] Furthermore, by clustering the user's electricity consumption data, users are divided into different groups according to their electricity consumption behavior characteristics, electricity consumption time periods and load characteristics, so as to achieve accurate identification and management of user electricity consumption patterns. Based on the clustering results, personalized electricity price strategies can be designed for different groups to improve the efficiency of power grid operation, promote the use of renewable energy and optimize power distribution. For example, for high-load user groups, by increasing electricity prices during peak hours and reducing electricity prices during off-peak hours, users are encouraged to use electricity during periods with low grid load, thereby alleviating grid pressure; while for low-load user groups, lower electricity price incentives are provided during off-peak hours to encourage them to increase electricity consumption during low-load hours. In addition, according to the characteristics of high-responsiveness users, renewable energy users and electric vehicle users, corresponding electricity price strategies are designed to encourage them to respond to grid dispatch more effectively and maximize social and economic benefits.

[0090] S3: According to the real-time load status of the power grid, the electricity price is dynamically adjusted using preset rules.

[0091] Utilize user electricity consumption data collected in real time by sensors to monitor the real-time load status of the power grid and set the load threshold of the power grid.

[0092] The setting of the grid load threshold includes training a regression model using historical data, predicting a dynamic adjustment factor, and calculating peak and valley load thresholds, which are expressed as follows:

[0093]

[0094] in, Represents the estimated value vector of the regression coefficients, including β0,β1,…,β n , used to describe the relationship between independent variables and dependent variables; X represents the independent variable matrix, including historical load data L t and related external influencing factors; X T represents the transpose of the independent variable matrix X, and Y represents the dependent variable vector; represents the dynamic adjustment factor at time t predicted by the regression model, represents the intercept term of the regression model, represents the regression coefficient, L t represents the grid load data at time t, X t1 ,X t2 ,…,X tn Represents external influencing factors related to grid load; L peak (t) represents the peak load threshold at time t, μ represents the mean of historical load data, κ represents the load threshold adjustment coefficient, σ represents the standard deviation of historical load data, and L valley (t) represents the valley load threshold at time t.

[0095] The rule engine includes that when the load of the power grid exceeds the set peak load threshold, the electricity price is automatically increased to 1.35 times the original electricity price.

[0096] When the load of the power grid is lower than the set low load threshold, the electricity price is automatically reduced to 0.45 times the original price.

[0097] When the grid load increases sharply, the electricity price will automatically increase to 1.5 times the original price.

[0098] When the grid load drops sharply, the electricity price will automatically drop to 0.35 times the original price.

[0099] Furthermore, by real-time monitoring of the load status of the power grid, combining historical data and regression models to predict dynamic adjustment factors, intelligent regulation of electricity prices can be achieved. Peak and valley load thresholds are set to ensure that when the power grid is overloaded or underloaded, electricity prices can be automatically adjusted to optimize the allocation of power resources and improve the stability and responsiveness of the power grid. When the power grid load exceeds the peak load threshold, the electricity price is increased to curb excessive power consumption and avoid power grid overload; when the power grid load is lower than the valley load threshold, the electricity price is reduced to encourage power consumption and help the power grid balance the load. In addition, setting electricity price adjustment rules for sharp load changes further enhances the flexibility and adaptability of power grid load regulation, ensures the smooth operation of the power grid and energy efficiency, and ultimately achieves load response and electricity price optimization in smart grids.

[0100] Embodiment 2 is an embodiment of the present invention, which provides a smart grid real-time electricity price adjustment system, including:

[0101] The data module collects user electricity consumption data in real time through sensors and performs pre-processing.

[0102] Divide the module, cluster the user's electricity consumption data, divide the users into different groups, and design personalized electricity price strategies.

[0103] The adjustment module dynamically adjusts the electricity price using preset rules according to the real-time load status of the power grid.

[0104] Embodiment 3, an embodiment of the present invention, is different from the first two embodiments in that:

[0105] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0106] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0107] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0108] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0109] Embodiment 4 is the fourth embodiment of the present invention. This embodiment provides a method for adjusting the real-time electricity price of a smart grid. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0110] This embodiment conducts a 6-month smart grid real-time electricity price adjustment test in a certain area of ​​a provincial capital city. The test area covers 2,000 residential users, 200 commercial users and 50 industrial users in the area. First, smart meters and electricity behavior collection sensors (model ET-8600) are installed at each user's power supply equipment, and the sampling frequency is set to once every 5 minutes. These sensors can accurately collect users' real-time power consumption, voltage, current, power factor and other data. At the same time, load monitoring equipment (model LM-2400) is installed at 10 important distribution nodes in the region for real-time monitoring of the load status of the regional power grid.

[0111] To ensure the accuracy and integrity of the data, a distributed data collection system and cloud storage solution were used. The data collection system uses a dual backup mechanism to transmit data through both 4G and wired networks. The collected data was preprocessed using an ETL tool (Talend Open Studio), including: cleaning up detected obvious abnormal values ​​(such as negative values ​​or data that exceeds 3 times the user's historical maximum power consumption); linear interpolation to supplement missing data caused by temporary disconnection of the collection equipment; and converting data from different sources into a standard format (the power consumption unit is unified as kWh, and the timestamp is unified as the YYYY-MM-DD HH:mm:ss format in the UTC+8 time zone).

[0112] After data preprocessing, the improved hierarchical clustering algorithm is used to group users. Considering the differences in electricity consumption characteristics of different users, a multi-dimensional feature extraction method is designed, including: calculating the average daily electricity consumption of users in the past 30 days, electricity consumption fluctuation coefficient (standard deviation / average value), peak electricity consumption ratio, load response capacity index (calculated through historical electricity price adjustment response data) and other features. At the same time, information such as users' use of renewable energy (such as whether photovoltaic equipment is installed) and electric vehicle charging needs is also collected.

[0113]

[0114] Through the analysis of the test data, it can be clearly seen that the real-time electricity price adjustment method of the smart grid of the present invention has achieved significant results in various user groups. First, from the perspective of electricity consumption, all user groups have achieved different degrees of energy saving after implementing the new electricity price adjustment strategy. Among them, the average daily electricity consumption of the high-load user group has dropped from 580.5kWh to 486.2kWh, a decrease of 16.2%, which shows that the differentiated electricity price strategy can effectively guide users to optimize their electricity consumption behavior.

[0115] It is particularly noteworthy that the improvement effect of the peak-to-valley ratio is the most significant. Taking the high-responsiveness user group as an example, the peak-to-valley ratio has dropped from 2.1 to 1.4, a decrease of 33.3%, which shows that this group has a strong response ability to electricity price signals and can actively transfer electricity load from peak hours to valley hours. The load response rate of the renewable energy user group under the new strategy has increased from 18.6% to 38.4%, an increase of 19.8 percentage points, which is closely related to the renewable energy power subsidy policy it has obtained.

[0116] In terms of energy saving rate, each user group has achieved significant improvement. Among them, the energy saving effect of the renewable energy user group is the most outstanding, with the energy saving rate increasing from 15.8% to 35.6%, which shows that the electricity price strategy of the present invention has successfully encouraged users to use more clean energy. Under the guidance of the preferential policy of charging during off-peak hours, the energy saving rate of the electric vehicle user group increased by 14.4 percentage points to 26.8%.

[0117] The user satisfaction data also fully demonstrates the implementation effect of the present invention. The satisfaction scores of all user groups have been significantly improved, with an average improvement of 0.9 points. This shows that the present invention not only optimizes the grid load, but also improves the user's electricity experience. In particular, the satisfaction of the high-responsiveness user group has increased from 3.6 points to 4.5 points, indicating that the personalized electricity price strategy can well meet the needs of different users.

[0118] By comparing with the existing technology, the present invention has obvious advantages in the following aspects: first, the multi-dimensional user grouping method can more accurately characterize the user's electricity consumption characteristics compared with the traditional single classification method; second, the personalized electricity price strategy design takes into account the user's responsiveness and behavioral characteristics, avoiding the "one size fits all" problem of the traditional method; third, the dynamic adjustment mechanism can respond quickly according to the real-time load status of the power grid, which is more flexible than the peak and valley electricity prices in fixed time periods. The test data shows that the present invention not only significantly improves the load distribution of the power grid, but also achieves a dual improvement in user energy saving and satisfaction, and has significant practical value.

[0119] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for adjusting the real-time electricity price of a smart grid, characterized in that: include: Collect user electricity consumption data in real time through sensors and perform pre-processing; Cluster user electricity consumption data, divide users into different groups, and design personalized electricity price strategies; According to the real-time load status of the power grid, the electricity price is dynamically adjusted using preset rules.

2. The smart grid real-time electricity price adjustment method according to claim 1, characterized in that: The user electricity consumption data includes electricity consumption data, electricity consumption period data, load demand data, electricity consumption behavior characteristics, historical data, renewable energy data and electricity price response data; Preprocessing includes cleaning missing values, duplicate data, and outliers from user electricity consumption data through ETL tools; Unify the units and formats of user electricity consumption data, and conduct multi-source data fusion and data quality checks.

3. The smart grid real-time electricity price adjustment method according to claim 2, characterized in that: The user classification into different groups includes clustering the power consumption behavior characteristics, power consumption time periods and load characteristics using a hierarchical clustering algorithm based on the collected user power consumption data. The formula is expressed as follows: Among them, D total represents the total clustering metric, M represents the total number of samples, and w ij represents the weight between sample i and sample j, d i,j represents the distance metric between sample i and sample j, α represents the parameter that controls the influence of distance metric on clustering quality, and D cluster represents the clustering metric, β represents the parameter that controls the influence of the clustering metric on the total metric, n represents the dimension of the feature space, and w k represents the weight of the kth feature, f k (x i ) represents the value of the kth feature on sample i, f k (x j ) represents the value of the kth feature on sample j, x i represents all eigenvalues ​​of sample i, x j represents all eigenvalues ​​of sample j, μ k Represents the cluster center value of the kth feature; The electricity consumption behavior characteristics include daily total electricity consumption, maximum load, and electricity consumption fluctuation; The electricity consumption period includes peak electricity consumption period and off-peak electricity consumption period; The load characteristics include load curve and load stability.

4. The smart grid real-time electricity price adjustment method according to claim 3, characterized in that: Dividing users into different groups also includes, based on the clustering results, dividing users into high-load user group, low-load user group, high-responsiveness user group, renewable energy user group and electric vehicle user group. The formula is expressed as: Among them, G(u) represents the group to which user u belongs, Load(u) represents the total load of user u, and L threshold represents the load threshold, Response(u) represents the responsiveness of user u to changes in electricity prices, and R threshold represents the threshold of responsiveness, RenewableEnergyUsage(u) represents the proportion of renewable energy used by user u, and E threshold represents the threshold of renewable energy use, EVUsage(u) indicates whether user u uses an electric vehicle, T threshold Indicates the threshold for electric vehicle use.

5. The smart grid real-time electricity price adjustment method according to claim 4, characterized in that: The personalized electricity price strategy includes designing a suitable electricity price strategy according to the characteristics of each group; The electricity price strategy for the high-load user group includes increasing the electricity price to 1.3 times the original price during the peak load period of the power grid, and reducing the electricity price to 0.65 times the original price during the low load period of the power grid; The electricity price strategy for low-load user groups includes reducing the electricity price to 0.45 times the original price during off-peak hours; The electricity price strategy for the high-responsiveness user group includes providing customized electricity prices according to the actual responsiveness of users during high-load periods; The electricity price strategy for renewable energy user groups includes providing a subsidy of 1.15 times the original electricity price per kilowatt-hour when they deliver excess electricity to the grid; The electricity price strategy for electric vehicle user groups includes reducing the electricity price to 0.85 times the original price during periods of low grid load.

6. The smart grid real-time electricity price adjustment method according to claim 5, characterized in that: According to the real-time load status of the power grid, the electricity price is dynamically adjusted using preset rules, including using the user electricity consumption data collected in real time by sensors to monitor the real-time load status of the power grid and set the load threshold of the power grid; The setting of the grid load threshold includes training a regression model using historical data, predicting a dynamic adjustment factor, and calculating peak and valley load thresholds, which are expressed as follows: in, Represents the estimated value vector of the regression coefficients, including β0,β1,…,β n , used to describe the relationship between independent variables and dependent variables; X represents the independent variable matrix, including historical load data L t and related external influencing factors; X T represents the transpose of the independent variable matrix X, and Y represents the dependent variable vector; represents the dynamic adjustment factor at time t predicted by the regression model, represents the intercept term of the regression model, represents the regression coefficient, L t represents the grid load data at time t, X t1 ,X t2 ,…,X tn Represents external influencing factors related to grid load; L peak (t) represents the peak load threshold at time t, μ represents the mean of historical load data, κ represents the load threshold adjustment coefficient, σ represents the standard deviation of historical load data, and L valley (t) represents the valley load threshold at time t.

7. The smart grid real-time electricity price adjustment method according to claim 6, characterized in that: Dynamically adjusting the electricity price using preset rules according to the real-time load status of the power grid also includes establishing a rule engine based on the load threshold of the power grid to automatically adjust the electricity price; The rule engine includes that when the load on the power grid exceeds the set peak load threshold, the electricity price is automatically increased to 1.35 times the original price; When the load of the power grid is lower than the set off-peak load threshold, the electricity price is automatically reduced to 0.45 times the original price; When the grid load increases dramatically, the electricity price will automatically increase to 1.5 times the original price; When the grid load drops sharply, the electricity price will automatically drop to 0.35 times the original price.

8. A smart grid real-time electricity price adjustment system using the method according to any one of claims 1 to 7, characterized in that: The data module collects user electricity consumption data in real time through sensors and performs pre-processing; Divide the module, cluster the user's electricity consumption data, divide the users into different groups, and design personalized electricity price strategies; The adjustment module dynamically adjusts the electricity price using preset rules according to the real-time load status of the power grid.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the smart grid real-time electricity price adjustment method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the smart grid real-time electricity price adjustment method according to any one of claims 1 to 7 are implemented.

Images