System and method for realizing power grid frequency modulation based on intelligent socket

Abstract

The invention discloses a system and a method for realizing power grid frequency modulation based on an intelligent socket, relates to the technical field of intelligent frequency modulation, and solves the problems that a power grid cannot timely acquire accurate data of power consumption conditions of household appliances and cannot timely perform power grid frequency modulation due to slow response speed of a generator set and a large power plant in the prior art. Stable operation of the power grid is influenced; real-time data are periodically acquired through the intelligent socket and uploaded to a dispatching center of a power grid; constructing a frequency prediction model according to the voltage frequency, and obtaining the voltage frequency deviation in the next sampling period through the frequency prediction model; power needing to be adjusted of the household appliance is obtained through the voltage frequency deviation; setting a frequency modulation strategy, and judging whether power grid frequency modulation is completed; if yes, ending the judgment; if not, regenerating a frequency modulation instruction according to the frequency modulation strategy to perform power grid frequency modulation; the household electrical appliance service condition is captured in time, and frequency modulation is carried out on the power grid in time.

Description

Technical Field

[0001] The present invention belongs to the field of smart grids and relates to smart frequency modulation technology, in particular to a system and method for realizing grid frequency modulation based on smart sockets. Background Art

[0002] Household appliances controlled by smart sockets can adjust their power according to the real-time needs of the power grid, which helps to balance the supply and demand of the power grid and reduce fluctuations and instability in the power grid; during peak power consumption periods, smart sockets can automatically adjust the power of household appliances to reduce unnecessary energy consumption, thereby alleviating the load on the power grid and improving the stability and reliability of the power grid; smart sockets can identify the power consumption of household appliances and adjust their power according to actual needs, thereby reducing unnecessary energy consumption; for example, during the use of high-energy consumption equipment such as air conditioners and water heaters, smart sockets can automatically adjust the power of the equipment according to real-time usage to achieve energy-saving effects.

[0003] The existing grid frequency regulation means mainly rely on the mechanical inertia of generator sets and the automatic adjustment devices of large power plants. However, with the complexity of load demand and the widespread access to distributed energy, the response speed of generator sets and large power plants is slow, resulting in the grid being unable to obtain accurate data on the power consumption of household appliances in a timely manner and unable to perform grid frequency regulation in a timely manner, thus affecting the stable operation of the grid.

[0004] At the same time, using the traditional power generation side frequency regulation method to regulate the frequency of power grid equipment has a higher cost investment.

[0005] The present invention provides a system and method for realizing power grid frequency modulation based on smart sockets to solve the above technical problems. Summary of the invention

[0006] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes a system and method for realizing grid frequency modulation based on smart sockets, which is used to solve the technical problem that the generator sets and large power plants in the grid frequency modulation means in the prior art have slow response speeds, resulting in the grid being unable to obtain accurate data on the electricity consumption of household appliances in a timely manner, and unable to perform grid frequency modulation in a timely manner, thereby affecting the stable operation of the grid.

[0007] To achieve the above-mentioned purpose, a first aspect of the present invention provides a system for realizing power grid frequency modulation based on smart sockets, comprising: a data acquisition module, a frequency modulation decision module;

[0008] Data acquisition module: collects real-time data periodically through smart sockets and uploads it to the dispatching center of the power grid; the real-time data includes: current value, voltage frequency;

[0009] Frequency regulation decision module: Build a frequency prediction model based on the voltage frequency, and obtain the voltage frequency deviation in the next sampling period through the frequency prediction model; obtain the power that needs to be adjusted for household appliances through the voltage frequency deviation;

[0010] The dispatch center obtains the power that needs to be adjusted, sets the frequency regulation strategy, and determines whether the grid frequency regulation is completed; if yes, the determination is ended; if not, the frequency regulation instruction is regenerated according to the frequency regulation strategy to perform grid frequency regulation.

[0011] Preferably, the collecting of real-time data through the smart socket and uploading to the dispatching center of the power grid includes:

[0012] The smart socket has a built-in data sampling unit and a data transmission unit; the data sampling unit collects real-time data of household appliances in real time according to the set sampling frequency through the built-in voltage frequency sensor;

[0013] Determine whether there is abnormal data; if yes, upload the data to the cloud server immediately through the data transmission unit; if no, upload the data to the dispatching center of the power grid through the data transmission unit in a scheduled manner.

[0014] It should be noted that the sampling frequency is set according to the grid demand.

[0015] The present invention can proactively upload abnormal data to a cloud server immediately after determining that the data is generated, thereby facilitating management personnel to take timely measures to prevent electrical fires.

[0016] Preferably, the determining whether there is abnormal data includes:

[0017] The real-time current value is retrieved and marked as SI, the current change coefficient is set and marked as a, and the current threshold is calculated by the formula TI = SI × a%;

[0018] Calculate the absolute value of the difference between the real-time current value and the real-time current value of the previous cycle to obtain the current change value; determine whether a number of current change values ​​are less than the current threshold; if yes, determine the next current change value; if not, mark the detected real-time current value as abnormal data, and determine the next current change value;

[0019] The voltage frequency measured in real time is marked as f measured (t), standard voltage frequency is marked as f normal ; Where t is the statistical period;

[0020] By the formula Δf(t) = |f measured (t)—f normal |Calculate the voltage-frequency deviation value of the power grid;

[0021] Set the deviation threshold and mark it as b, and determine whether the voltage-frequency deviation value of the power grid is greater than or equal to b; if yes, the corresponding real-time voltage-frequency value is detected as abnormal data; if no, continue to determine.

[0022] It should be noted that the previous current value is the current value recorded in the previous sampling; the value of a depends on the staff's attention to the current based on the actual working situation. The greater the attention to the current, the smaller the value of a; the value of b depends on the staff's attention to the voltage frequency based on the actual working situation. The greater the attention to the current, the smaller the value of b.

[0023] The present invention calculates the current change value and the voltage frequency deviation value so that the system can timely discover abnormal changes in corresponding data; a and b are set according to the staff's attention to the current and voltage frequencies according to actual working conditions; this makes the system more flexible and can adapt to the monitoring needs of different working environments and power equipment.

[0024] Preferably, constructing a frequency prediction model according to the voltage-frequency change rate includes:

[0025] Retrieve the voltage-frequency deviation value Δf(t) of the power grid;

[0026] By formula The voltage frequency change rate is calculated;

[0027] Retrieve the frequency prediction model and obtain the historical voltage-frequency change rate of several cycles from the database; integrate the voltage-frequency change rate of several cycles and the current voltage-frequency change rate into a voltage-frequency sequence; input the voltage-frequency sequence into the frequency prediction model to obtain the corresponding voltage-frequency label;

[0028] The grid voltage frequency deviation value sampled in the next cycle is matched according to the voltage frequency label; wherein the frequency prediction model is constructed based on the artificial intelligence model; the voltage frequency label is set to a positive integer.

[0029] The present invention restores the voltage frequency to the standard frequency through frequency modulation; in order to perform frequency modulation control, the rate of change of frequency deviation over time is calculated through a formula, and the dynamic change of frequency deviation is analyzed to help analyze the frequency stability of the power grid; accurate voltage and frequency prediction helps power grid dispatchers to formulate reasonable power generation plans and load distribution strategies, ensure that the power grid can maintain a stable operating state under various working conditions, help reduce the frequency fluctuation and voltage instability of the power grid, and improve the overall operation quality of the power grid.

[0030] Preferably, the frequency prediction model is constructed based on an artificial intelligence model, including:

[0031] Acquire standard training data; wherein the standard training data includes standard input data consistent with the content attributes of the voltage frequency sequence, and standard output data consistent with the content attributes of the voltage frequency label;

[0032] The artificial intelligence model is trained using standard training data, and the trained artificial intelligence model is marked as a frequency prediction model; wherein the artificial intelligence model includes a convolutional neural network model or an autoregressive integrated moving average model.

[0033] Preferably, obtaining the power that needs to be adjusted for the household appliance through the voltage-frequency deviation includes:

[0034] Retrieve the voltage frequency deviation value in the next sampling period and mark it as Δf(t) h ; Obtain the power change values ​​of household appliances corresponding to several voltage-frequency deviation values ​​from the database and mark them as Kfreq ij , the voltage frequency deviation value is marked as Δf(t) k ; Wherein, j represents the number of power change values ​​of household appliances; j=1, 2, 3, ..., n; k represents the number of voltage-frequency deviation values, and k=j; i represents the type of household appliances, and the value range of i is a positive integer;

[0035] By formula The average proportionality constant was calculated;

[0036] By formula P adjust (t) i =Kfreq i ×Δf(t)1 calculates the power that needs to be adjusted for different types of household appliances.

[0037] The present invention calculates the average proportional constant, which is conducive to more accurately predicting the power changes of different types of household appliances under voltage-frequency deviation, so that the system can accurately adjust the power of household appliances according to the real-time voltage-frequency deviation value to avoid unnecessary energy waste; by adjusting the power of household appliances, the fluctuation of the grid load can be reduced, making the grid operation more stable, which helps to reduce the risk of grid failure and improve the stability of power supply.

[0038] Preferably, the setting of the frequency modulation strategy includes:

[0039] Obtain the power that needs to be adjusted for different types of household appliances; sort high-power household appliances from small to large according to the power used, and count the number of household appliances with the same power used to form a power usage table; allocate the number of household appliances that need to be adjusted for each type in turn according to the table; mark the ratio of the power that needs to be adjusted to the number of household appliances to be adjusted as the power that each household appliance needs to adjust.

[0040] It should be noted that high-power household appliances are household appliances that directly use 220 volts of alternating current and have a power greater than 1200 watts.

[0041] The present invention counts the number of all high-power household appliances capable of power regulation in a household and forms a table, and sequentially allocates the number of household appliances of each type that need to be regulated according to the table, so that each household appliance can perform power regulation under the same conditions, thereby avoiding unnecessary waste of resources.

[0042] Preferably, the determining whether the power grid frequency modulation is completed includes:

[0043] The frequency modulation strategy is retrieved, and the power that each household appliance needs to adjust is used as the frequency modulation instruction; the cloud server receives the frequency modulation instruction issued by the power grid dispatching center, decomposes the instruction and converts it into infrared control instruction and sends it to the smart socket;

[0044] The smart socket controls the corresponding household appliances to complete the grid frequency modulation according to the frequency modulation instructions, and feeds back the real-time data after frequency modulation to the grid dispatching center layer by layer through the network channel;

[0045] Re-acquire the real-time data of household appliances after frequency modulation, and determine whether there is abnormal data in the real-time data of household appliances; if yes, the grid frequency modulation is not completed; if no, the grid frequency modulation is completed.

[0046] The present invention monitors and adjusts the power of household appliances in real time. This mechanism can prevent power grid failures caused by overload or frequency fluctuations, help improve the safety and stability of power grid operation, ensure the reliability of power supply, and provide necessary support for the power grid; it also helps to reduce the impact of power grid failures on users and improve the emergency response capability of the power grid.

[0047] A second aspect of the present invention provides a method for realizing grid frequency modulation based on a smart socket, comprising:

[0048] The real-time data is collected periodically through the smart socket and uploaded to the dispatching center of the power grid; the real-time data includes: current value, voltage frequency;

[0049] A frequency prediction model is constructed according to the voltage frequency, and the voltage frequency deviation in the next sampling period is obtained through the frequency prediction model; the power that needs to be adjusted for household appliances is obtained through the voltage frequency deviation;

[0050] The dispatch center obtains the power that needs to be adjusted, sets the frequency regulation strategy, and determines whether the grid frequency regulation is completed; if yes, the determination is ended; if not, the frequency regulation instruction is regenerated according to the frequency regulation strategy to perform grid frequency regulation.

[0051] Compared with the prior art, the present invention has the following beneficial effects:

[0052] 1. The present invention has little impact on users' electricity consumption and can ensure the comfort of users' electricity consumption; the smart socket can also automatically adjust the power of household appliances according to the electricity consumption situation to achieve energy saving and consumption reduction; the smart socket can collect the current data and voltage frequency data of household appliances in real time and upload them to the cloud server, which provides the power grid dispatching center with accurate and timely power grid operation status information, which helps to achieve accurate power grid frequency modulation; by constructing a frequency prediction model, the system can predict the voltage frequency deviation within the next sampling period, which enables the power grid dispatching center to take measures in advance to adjust the power of household appliances and avoid the impact of frequency fluctuations on power grid operation.

[0053] 2 The present invention realizes real-time monitoring and rapid adjustment of voltage frequency and current through the intelligent socket network, which significantly improves the stability of voltage frequency; makes full use of users' household appliances, expands the available resources for grid frequency regulation, and reduces the dependence on traditional generator sets; the system can quickly generate frequency regulation instructions according to the prediction results, and send them to the intelligent sockets through the cloud server, and the intelligent sockets can immediately control household appliances to adjust power and achieve rapid response to grid frequency; by adjusting the power of household appliances, the system can optimize the configuration of power resources and ensure the smooth and reliable power supply, which helps to reduce power waste and loss and improve the utilization efficiency of power resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0055] Figure 1 A schematic diagram of the process of power grid frequency modulation according to the present invention;

[0056] Figure 2 It is a schematic diagram of the specific steps of data collection of the present invention;

[0057] Figure 3 It is a schematic diagram of the specific steps of frequency modulation decision making of the present invention. DETAILED DESCRIPTION

[0058] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than 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.

[0059] See also Figure 1, the first aspect of the present invention provides a system for realizing power grid frequency modulation based on smart sockets, including: a data acquisition module, a frequency modulation decision module;

[0060] Data acquisition module: collects real-time data periodically through smart sockets and uploads it to the dispatching center of the power grid; the real-time data includes: current value, voltage frequency;

[0061] Frequency regulation decision module: Build a frequency prediction model based on the voltage frequency, and obtain the voltage frequency deviation in the next sampling period through the frequency prediction model; obtain the power that needs to be adjusted for household appliances through the voltage frequency deviation;

[0062] The dispatch center obtains the power that needs to be adjusted, sets the frequency regulation strategy, and determines whether the grid frequency regulation is completed; if yes, the determination is ended; if not, the frequency regulation instruction is regenerated according to the frequency regulation strategy to perform grid frequency regulation.

[0063] See also Figure 2 ,Specific steps of data collection, the smart socket is embedded with a data sampling unit and a data transmission unit; the data sampling unit collects real-time data of household appliances in real time according to the set sampling frequency through a built-in voltage frequency sensor;

[0064] The real-time current value is marked as SI, the current change coefficient is set and marked as a, and the current threshold is calculated by the formula TI = SI × a%;

[0065] The absolute value of the real-time current value minus the previous current value is marked as the current change value; whether the current change value is less than the current threshold is determined; if yes, the determination is continued; if no, the corresponding real-time current data is detected as abnormal data;

[0066] The voltage frequency measured in real time is marked as f measured (t), standard voltage frequency is marked as f normal ; Where t is the statistical period;

[0067] By the formula Δf(t) = |f measured (t)—f normal |Calculate the voltage-frequency deviation value of the power grid;

[0068] Set the deviation threshold and mark it as b, and determine whether the voltage-frequency deviation value of the power grid is greater than or equal to b; if yes, the corresponding real-time voltage-frequency value is detected as abnormal data, and it is immediately uploaded to the cloud server through the data transmission unit; if no, continue to judge, and upload the data to the cloud server through the data transmission unit in a scheduled manner.

[0069] For example, a household currently contains several smart sockets, and the smart sockets have built-in data sampling units and data transmission units; the data sampling unit uses a built-in voltage frequency sensor to collect real-time data of household air conditioners in real time according to a set sampling frequency;

[0070] The real-time current value of the household air conditioner is 10A, and the staff is very concerned about the current of the household air conditioner at this time. Then, the specific value of a is obtained as 10 according to the specific value table of a (Table 1);

[0071] Table 1a specific value table

[0072] Degree of attention The specific value of a Severe 10 Moderate 20 Mild 30

[0073] Set the cycle to 1s, and calculate the current threshold of the household air conditioner to be 1 through the formula TI=SI×a%. Subtract the absolute value of the current value 10A in the previous second from the real-time current value 10.5A to get the current change value 0.5. If the current change value 0.5 is less than the current threshold value 1, the corresponding real-time current data is normal.

[0074] The staff is very concerned about the voltage frequency of the household air conditioner at this time, so the specific value of b is 0.01 according to the specific value table of b (Table 2);

[0075] Table 2b specific value table

[0076] Degree of attention The specific value of b Severe 0.01 Moderate 0.15 Mild 0.02

[0077] The voltage frequency measured in real time is marked as f measured (t) = 49.8 Hz, standard voltage frequency is marked as f normal =50Hz; by the formula Δf(t)=|f measured (t)—f normal |The calculated voltage-frequency deviation value of the power grid is 0.02 Hz. If the voltage-frequency deviation value of the power grid 0.02 is greater than or equal to 0.01, the corresponding real-time voltage-frequency value is detected as abnormal data and is immediately uploaded to the cloud server through the data transmission unit.

[0078] See also Figure 3 , the specific steps of frequency regulation decision are to obtain the voltage-frequency deviation value Δf(t) of the power grid;

[0079] By formula The voltage frequency change rate is calculated;

[0080] A frequency prediction model is constructed based on an artificial intelligence model to obtain the historical voltage-frequency change rate of several cycles from the database; the voltage-frequency change rate of several cycles and the current voltage-frequency change rate are integrated into a voltage-frequency sequence; the voltage-frequency sequence is input into the frequency prediction model to obtain the corresponding voltage-frequency label, and the grid voltage-frequency deviation value within the next cycle sampling is matched according to the voltage-frequency label and marked as Δf(t) h ; Among them, the frequency prediction model is built based on the artificial intelligence model; the voltage frequency label is set as a positive integer;

[0081] Obtain the power change values ​​of household appliances corresponding to several voltage-frequency deviation values ​​from the database and mark them as Kfreq ij , the voltage frequency deviation value is marked as Δf(t) k ; Wherein, j represents the number of power change values ​​of household appliances; j=1, 2, 3, ..., n; k represents the number of voltage-frequency deviation values, and k=j; i represents the type of household appliances, and the value range of i is a positive integer;

[0082] By formula The average proportionality constant was calculated;

[0083] By formula P adjust (t) i =Kfreq i ×Δf(t)1 calculates the power that needs to be adjusted for different types of household appliances;

[0084] Obtain the power that needs to be adjusted for different types of household appliances; sort the high-power household appliances in ascending order of power usage, and count the number of household appliances with the same power usage to form a power usage table; allocate the number of household appliances that need to be adjusted for each type in turn according to the table; divide the power that needs to be adjusted by the number of household appliances to be adjusted to obtain the power that each household appliance needs to be adjusted;

[0085] The frequency modulation strategy is retrieved, and the power that each household appliance needs to adjust is used as the frequency modulation instruction; the cloud server receives the frequency modulation instruction issued by the power grid dispatching center, decomposes the instruction and converts it into infrared control instruction and sends it to the smart socket; the smart socket controls the corresponding household appliances to complete the power grid frequency modulation according to the frequency modulation instruction, and feeds back the real-time data after frequency modulation to the power grid dispatching center layer by layer through the network channel;

[0086] Re-acquire the real-time data of household appliances after frequency modulation, and determine whether there is abnormal data in the real-time data of household appliances; if yes, the grid frequency modulation is not completed; if no, the grid frequency modulation is completed.

[0087] For example, the voltage-frequency deviation value Δf(t) of the power grid is retrieved;

[0088] By formula The voltage frequency change rate is calculated;

[0089] A frequency prediction model is constructed based on an artificial intelligence model, and the historical voltage frequency change rates of several cycles are obtained from the database; the voltage frequency change rates of several cycles and the current voltage frequency change rate are integrated into a voltage frequency sequence; the voltage frequency sequence is input into the frequency prediction model to obtain the corresponding voltage frequency label, and the corresponding voltage frequency type is matched according to the voltage frequency label; wherein, the frequency prediction model is constructed based on the artificial intelligence model; the voltage frequency label is set to a positive integer of 0.01Hz;

[0090] The household air conditioner is taken as the first household appliance to be calculated; when the voltage-frequency deviation value of the household air conditioner obtained from the database is 0.08Hz, the corresponding power change value of the air conditioner is 23w; when the voltage-frequency deviation value is 0.09Hz, the corresponding power change value of the air conditioner is 28w; when the voltage-frequency deviation value is 0.02Hz, the corresponding power change value of the air conditioner is 10w;

[0091] By formula The average proportional constant Kfreq is calculated i =366.2;

[0092] By formula P adjust (t) i =Kfreq i ×Δf(t)1 The power P that needs to be adjusted for household air conditioning is calculated adjust (t) i =366.2×0.01=3.66W;

[0093] According to the above formula, the power that needs to be adjusted for the electric pressure cooker is 5.06W, the power that needs to be adjusted for the refrigerator is 4.85W, and the power that needs to be adjusted for the induction cooker is 3.66W; the high-power household appliances are sorted in ascending order according to the power used, and the number of household appliances with the same power used is counted and integrated to form a power used table, as shown in Table (3);

[0094] Table (3) Power meter used

[0095] Home Appliance Type Power consumption of household appliances Number of household appliances Electric pressure cooker 2200W 1 refrigerator 2100W 1 induction cooker 1200W 1 air conditioner 1200W 2

[0096] From Table (3), we can see that the number of household appliances corresponding to the same power usage of 1200W is 3. Dividing the power to be adjusted 3.66W by the number of household appliances to be adjusted 3, we can get the power to be adjusted for each induction cooker and each air conditioner is 1.22W respectively;

[0097] The frequency modulation strategy is retrieved, and the power that each household appliance needs to adjust is used as the frequency modulation instruction; the cloud server receives the frequency modulation instruction issued by the power grid dispatching center, decomposes the instruction and converts it into infrared control instruction and sends it to the smart socket; the smart socket controls the corresponding household appliances to complete the power grid frequency modulation according to the frequency modulation instruction, and feeds back the real-time data after frequency modulation to the power grid dispatching center layer by layer through the network channel;

[0098] The real-time data of household appliances after frequency modulation is re-acquired. If there is no abnormal data in the real-time data of household appliances, the frequency modulation of the power grid is completed.

[0099] A second aspect of the present invention provides a method for realizing power grid frequency modulation based on a smart socket, comprising:

[0100] The real-time data is collected periodically through the smart socket and uploaded to the dispatching center of the power grid; the real-time data includes: current value, voltage frequency;

[0101] A frequency prediction model is constructed according to the voltage frequency, and the voltage frequency deviation in the next sampling period is obtained through the frequency prediction model; the power that needs to be adjusted for household appliances is obtained through the voltage frequency deviation;

[0102] The dispatch center obtains the power that needs to be adjusted, sets the frequency regulation strategy, and determines whether the grid frequency regulation is completed; if yes, the determination is ended; if not, the frequency regulation instruction is regenerated according to the frequency regulation strategy to perform grid frequency regulation.

[0103] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0104] The working principle of the present invention is as follows: the present invention collects real-time data periodically through the smart socket and uploads it to the dispatching center of the power grid; constructs a frequency prediction model according to the voltage frequency, and obtains the voltage frequency deviation in the next sampling period through the frequency prediction model; obtains the power that needs to be adjusted for household appliances through the voltage frequency deviation; the dispatching center obtains the power that needs to be adjusted, sets the frequency modulation strategy, and determines whether the power grid frequency modulation is completed; if yes, the judgment is ended; if not, the frequency modulation instruction is regenerated according to the frequency modulation strategy to perform power grid frequency modulation.

[0105] The above embodiments are only used to illustrate the technical method 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 method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A system for realizing power grid frequency modulation based on smart sockets, characterized in that: include: Data acquisition module, frequency modulation decision module; Data acquisition module: collects real-time data periodically through smart sockets and uploads it to the dispatching center of the power grid; The real-time data include: current value, voltage frequency; Frequency regulation decision module: Build a frequency prediction model based on the voltage frequency, and obtain the voltage frequency deviation in the next sampling period through the frequency prediction model; obtain the power that needs to be adjusted for household appliances through the voltage frequency deviation; The dispatch center obtains the power that needs to be adjusted, sets the frequency regulation strategy, and determines whether the grid frequency regulation is completed; if yes, the determination is ended; if not, the frequency regulation instruction is regenerated according to the frequency regulation strategy to perform grid frequency regulation.

2. According to claim 1, a system for realizing power grid frequency modulation based on smart sockets is characterized in that: The real-time data is collected through the smart socket and uploaded to the dispatching center of the power grid, including: The smart socket has a built-in data sampling unit and a data transmission unit; the data sampling unit collects real-time data of household appliances in real time according to the set sampling frequency through the built-in voltage frequency sensor; Determine whether there is abnormal data; if yes, upload the data to the cloud server immediately through the data transmission unit; if no, upload the data to the dispatching center of the power grid through the data transmission unit in a scheduled manner.

3. The system for realizing power grid frequency modulation based on smart socket according to claim 2, characterized in that: The determining whether there is abnormal data includes: The real-time current value is retrieved and marked as SI, the current change coefficient is set and marked as a, and the current threshold is calculated by the formula TI = SI × a%; Calculate the absolute value of the difference between the real-time current value and the real-time current value of the previous cycle to obtain the current change value; determine whether a number of current change values ​​are less than the current threshold; if yes, determine the next current change value; if not, mark the detected real-time current value as abnormal data, and determine the next current change value; The voltage frequency measured in real time is marked as f measured (t), standard voltage frequency is marked as f normal ; Where t is the statistical period; By the formula Δf(t) = |f measured (t)—f normal |Calculate the voltage-frequency deviation value of the power grid; Set the deviation threshold and mark it as b, and determine whether the voltage-frequency deviation value of the power grid is greater than or equal to b; if yes, the corresponding real-time voltage-frequency value is detected as abnormal data; if no, continue to determine.

4. A system for realizing grid frequency modulation based on smart sockets according to claim 1 or 3, characterized in that: The step of constructing a frequency prediction model according to the voltage-frequency change rate includes: Retrieve the voltage-frequency deviation value Δf(t) of the power grid; By formula The voltage frequency change rate is calculated; Retrieve the frequency prediction model and obtain the historical voltage-frequency change rate of several cycles from the database; integrate the voltage-frequency change rate of several cycles and the current voltage-frequency change rate into a voltage-frequency sequence; input the voltage-frequency sequence into the frequency prediction model to obtain the corresponding voltage-frequency label; The grid voltage frequency deviation value sampled in the next cycle is matched according to the voltage frequency label; wherein the frequency prediction model is constructed based on the artificial intelligence model; the voltage frequency label is set to a positive integer.

5. The system for realizing power grid frequency modulation based on smart socket according to claim 4, characterized in that: The frequency prediction model is constructed based on an artificial intelligence model, including: Acquire standard training data; wherein the standard training data includes standard input data consistent with the content attributes of the voltage frequency sequence, and standard output data consistent with the content attributes of the voltage frequency label; The artificial intelligence model is trained using standard training data, and the trained artificial intelligence model is marked as a frequency prediction model; wherein the artificial intelligence model includes a convolutional neural network model or an autoregressive integrated moving average model.

6. The system for realizing power grid frequency modulation based on smart socket according to claim 1, characterized in that: The method of obtaining the power required to be adjusted by the household appliance through the voltage-frequency deviation includes: Retrieve the voltage frequency deviation value in the next sampling period and mark it as Δf(t) h ; Obtain the power change values ​​of household appliances corresponding to several voltage-frequency deviation values ​​from the database and mark them as Kfreq ij , the voltage frequency deviation value is marked as Δf(t) k ; Wherein, j represents the number of power change values ​​of household appliances; j=1, 2, 3, ..., n; k represents the number of voltage-frequency deviation values, and k=j; i represents the type of household appliances, and the value range of i is a positive integer; By formula The average proportionality constant was calculated; By formula P adjust (t) i =Kfreq i ×Δf(t)1 calculates the power that needs to be adjusted for different types of household appliances.

7. The system for realizing power grid frequency modulation based on smart socket according to claim 1, characterized in that: The setting of the frequency modulation strategy includes: Obtain the power that needs to be adjusted for different types of household appliances; sort high-power household appliances from small to large according to the power used, and count the number of household appliances with the same power used to form a power usage table; allocate the number of household appliances that need to be adjusted for each type in turn according to the table; mark the ratio of the power that needs to be adjusted to the number of household appliances to be adjusted as the power that each household appliance needs to adjust.

8. The system for realizing power grid frequency modulation based on smart socket according to claim 1, characterized in that: The determining whether the power grid frequency modulation is completed includes: The frequency modulation strategy is retrieved, and the power that each household appliance needs to adjust is used as the frequency modulation instruction; the cloud server receives the frequency modulation instruction issued by the power grid dispatching center, decomposes the instruction and converts it into infrared control instruction and sends it to the smart socket; The smart socket controls the corresponding household appliances to complete the grid frequency modulation according to the frequency modulation instructions, and feeds back the real-time data after frequency modulation to the grid dispatching center layer by layer through the network channel; Re-acquire the real-time data of household appliances after frequency modulation, and determine whether there is abnormal data in the real-time data of household appliances; if yes, the grid frequency modulation is not completed; if no, the grid frequency modulation is completed.

9. A method for realizing power grid frequency modulation based on smart sockets, applied to a system for realizing power grid frequency modulation based on smart sockets as claimed in any one of claims 1 to 8, characterized in that: include: The real-time data is collected periodically through the smart socket and uploaded to the dispatching center of the power grid; The real-time data include: current value, voltage frequency; A frequency prediction model is constructed according to the voltage frequency, and the voltage frequency deviation in the next sampling period is obtained through the frequency prediction model; the power that needs to be adjusted for household appliances is obtained through the voltage frequency deviation; The dispatch center obtains the power that needs to be adjusted, sets the frequency regulation strategy, and determines whether the power grid frequency regulation is completed; If yes, the judgment ends; if no, the frequency regulation instruction is regenerated according to the frequency regulation strategy to perform grid frequency regulation.

Images