Data mining system and method based on big data in smart power grid

Abstract

The invention relates to the technical field of intelligent power grid management and optimization, in particular to a data mining system and method based on big data in an intelligent power grid, and the system comprises a data collection module which is used for collecting the power utilization data of a user in real time; the data abnormity analysis module is used for judging the abnormal condition of the real-time power consumption data of the user; the energy supply analysis module is used for evaluating the energy supply condition; the energy consumption analysis module is used for judging the load density of the electric quantity area and the importance and demand of the power supply area; the balance analysis module is used for judging the balance state condition of the power grid in real time; the imbalance decision module is used for judging the supply and demand conditions, the electric quantity area and the power supply area in the abnormal imbalance state and outputting a decision; and the decision output module is used for drawing a power supply distribution condition table and outputting dispatching instructions and emergency measure suggestions to the power generation equipment. The operation efficiency of the power grid is improved, and the stability and reliability of power supply are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of smart grid management and optimization, and particularly to a data mining system and method based on big data in a smart grid. Background Art

[0002] With the proposal and development of the smart grid, the power system has gradually achieved intelligence, automation, and interactivity. The smart grid requires comprehensive monitoring and control of all links of the power system, and the user power consumption information acquisition system is an important part of the smart grid. With the increase in energy consumption and the rise in energy costs, the demand for refined energy management by enterprises and users is becoming increasingly urgent. The user power consumption information acquisition system can provide real-time and accurate power consumption data, help users optimize their power consumption behavior, and reduce energy costs. The continuous development of sensor technology, communication technology, and data processing technology provides technical support for the user power consumption information acquisition system. These technologies enable the system to efficiently and accurately collect and transmit user power consumption data, and perform in-depth data mining and analysis.

[0003] Chinese Patent Publication No.: CN113054669B discloses a method for adaptive self-balancing of peak load shifting and valley filling in a distribution network based on blockchain technology. This method combines blockchain technology with peak load shifting and valley filling regulation in the distribution network. Through technical means such as smart contracts and smart meters, it can monitor the distribution network capacity and load curve in real time, adaptively adjust the user power consumption behavior, and achieve the balanced operation of the power grid. Without affecting the normal power consumption of users, this method can effectively and quickly reduce the load peak of the power grid, improve the safety and stability margin of the power grid operation, thereby saving power resources and reducing operating costs. However, this method lacks methods for power supply regulation and emergency power supply in high-load and low-load density areas. Summary of the Invention

[0004] Therefore, the present invention provides a data mining system and method based on big data in a smart grid to overcome the problems of low operation efficiency of the power grid, unstable power supply, large energy consumption, and high operating costs caused by the lack of power supply regulation and emergency power supply methods in high-load and low-load density areas in the prior art.

[0005] To achieve the above object, on the one hand, the present invention provides a data mining system based on big data in a smart grid, and the system includes: A data acquisition module for real-time collection of user power consumption data to obtain real-time user power consumption data; A data anomaly analysis module for judging the anomaly value of real-time user power consumption data, judging the duration of the anomaly value of real-time user power consumption data, and judging the category of abnormal real-time user power consumption data; An energy supply analysis module for analyzing and calculating the power generation efficiency of a generator; An energy consumption analysis module for judging the load density of an electricity region, judging the importance of a power supply region, and judging the demand of a power supply region; A balance analysis module for judging the real-time balance state of a power grid; An imbalance decision module for identifying the imbalance state of a power grid, judging the supply-demand situation according to the energy supply data and energy consumption data under an abnormal imbalance state, judging the imbalance situation between a high-load density electricity region and a low-load density electricity region according to the imbalance time of the load density electricity region, comparing the imbalance situations between important power supply regions and non-important power supply regions according to the effective power and the preset effective power, outputting according to the comparison result, and adjusting the power supply ratio between a high-demand power supply region and a non-high-demand power supply region in an important power supply region; A decision output module for drawing a power supply distribution situation table, outputting a scheduling instruction to a power generation device, and outputting emergency measure suggestions.

[0006] Furthermore, when the data acquisition module collects user electricity consumption data in real time, the DEWETRON customer data acquisition system is used to collect user electricity consumption data in real time to obtain real-time user electricity consumption data, and the real-time user electricity consumption data includes user electricity consumption and power supply.

[0007] Furthermore, when the data anomaly analysis module judges the anomaly value of real-time user electricity consumption data, according to the real-time user electricity consumption data t and the historical user electricity consumption data t1, the difference T1 is calculated, and T1=t−t1 is set. The difference T1 is compared with a preset positive value T0 and a preset negative value T2, and the anomaly value of real-time user electricity consumption data is judged according to the comparison result, where: When T1≥0, the data anomaly analysis module compares the difference T1 with the preset positive value T0 and judges the data anomaly value according to the comparison result, where: If T1>T0, the data anomaly analysis module determines that the real-time user electricity consumption data is abnormal and records the data in the data anomaly set U; If T1≤T0, the data anomaly analysis module determines that the real-time user electricity consumption data is normal; When T1<0, the data anomaly analysis module compares the difference T1 with the preset negative value T2 and judges the data anomaly value according to the comparison result, where: If T1≥T2, the data anomaly analysis module determines that the real-time user electricity consumption data is normal; When T1 < T2, the data anomaly analysis module determines that the real-time user power consumption data is abnormal, and records the abnormal real-time user power consumption data in the data anomaly set U.

[0008] Further, when the data anomaly analysis module judges the duration of the real-time user power consumption data anomaly value, it compares the duration Tmin of the real-time user power consumption data anomaly value with the preset value Tmin0, and judges the duration of the abnormal data according to the comparison result, where: When Tmin ≤ Tmin0, the data anomaly analysis module determines that the duration of the real-time user power consumption data anomaly value is normal; When Tmin > Tmin0, the data anomaly analysis module determines that the duration of the real-time user power consumption data anomaly value is abnormal.

[0009] Further, when the data anomaly analysis module judges the category of the abnormal real-time user power consumption data, it compares the abnormal value X1 of the real-time user power consumption data with the maximum error value X0 of the historical data, and judges the category of the abnormal real-time user power consumption data according to the comparison result, where: When X1 > X0, the data anomaly analysis module determines that the category of the abnormal real-time user power consumption data is caused by a power meter failure; When X1 = 0, the data anomaly analysis module determines that the category of the abnormal real-time user power consumption data is caused by a power meter failure; When 0 < X1 < X0, the data anomaly analysis module determines that the category of the abnormal real-time user power consumption data is caused by substation line loss. Use data visualization and an oscilloscope to compare the waveform and numerical changes section by section from the input end to find the abnormal part, and use the backup power supply for emergency power supply.

[0010] Further, when the energy supply analysis module analyzes and calculates the power generation efficiency of the generator, according to the electric energy We output by the generator and the heat Qin input by fuel combustion, the power generation efficiency η is calculated. It is set that ; The power generation efficiency η is compared with the preset power generation efficiency η 0, and the power generation efficiency of the generator is judged according to the comparison result, where: When η ≥ η 0, the energy supply analysis module determines that the power generation efficiency meets the standard; When η < η 0, the energy supply analysis module determines that the power generation efficiency does not meet the standard, and increases the operating pressure and temperature of the generator until the power generation efficiency meets the standard.

[0011] Further, when the energy consumption analysis module demarcates the high load density power region and the low load density power region, according to the regional power consumption load F and the regional area S, calculate the regional load density value ρ, set ρ = F / S, compare the regional load density value with the preset regional density value ρ0, and analyze the regional load density according to the comparison result, where: When ρ > ρ0, the energy consumption analysis module determines that this region belongs to the high load density power region; When ρ ≤ ρ0, the energy consumption analysis module determines that this region belongs to the low load density power region.

[0012] Further, when the energy consumption analysis module differentiates the important power supply region and the non-important power supply region, according to the average load Pa and the maximum load Pmax, calculate the average load rate LR, set ; according to the minimum load Pmin and the maximum load Pmax, calculate the peak-valley difference P0, set P0 = Pmax - Pmin; Compare the average load rate LR1 and the peak-valley difference P1 of the power supply region S1 with the average load rate LR2 and the peak-valley difference P2 of the power supply region S2, and judge the important power supply region and the non-important power supply region according to the comparison result, where: When LR1 ≤ LR2, no judgment result is output; When LR1 > LR2, if P1 < P2, the energy consumption analysis module determines that the power supply region S1 is the important power supply region and the power supply region S2 is the non-important power supply region; If P1 > P2, the energy consumption analysis module determines that the power supply region S2 is the important power supply region and the power supply region S1 is the non-important power supply region.

[0013] Further, when the energy consumption analysis module differentiates the high-demand power supply region and the non-high-demand power supply region, compare the user power consumption L with the preset power consumption L0, and judge the high-demand power supply region and the non-high-demand power supply region according to the comparison result, where: When L > L0, the energy consumption analysis module determines it as the high-demand power supply region; When L ≤ L0, the energy consumption analysis module determines it as the non-high-demand power supply region.

[0014] Further, when the balance analysis module judges the balance state of the current power grid, according to the power generation power P of the i-th power generation unit Gi , the total number n of power generation units, the power consumption load power P of the j-th Lj , the total number m of power consumption loads, and the power loss P during the transmission and distribution of the power grid s , calculate the power: ; Extract the latest power generation power data, power consumption load power data, and power loss data from the database according to the power time interval, substitute them into the power calculation formula for calculation, and set as A1, as A0, where: When |A1 - A0| < 1, the balance analysis module determines that the current power grid is in a power balance state; When |A1 - A0| ≥ 1, the balance analysis module determines that the current power grid is in a power imbalance state.

[0015] Furthermore, when the imbalance decision module identifies the imbalance state, the obtained power imbalance time Td is compared with the preset power imbalance time Tdo, and the imbalance state is identified according to the comparison result, where: When Td ≤ Tdo, the imbalance decision module determines that the imbalance state is normal; When Td > Tdo, the imbalance decision module determines that the imbalance state is abnormal.

[0016] Furthermore, when the imbalance decision module judges the supply and demand situation based on the energy supply data and energy consumption data in the abnormal imbalance state, the energy supply data PG is compared with the energy consumption data Ph, the supply and demand situation is judged according to the comparison result, and the output is made according to the judgment result, where: When PG < Ph, the imbalance decision module determines that the supply is less than the demand and does not output the judgment result; When PG ≥ Ph, the imbalance decision module determines that the supply is greater than the demand, calculates the excess supply power value C according to the energy supply data PG and the energy consumption data Ph, sets C = PG - Ph, compares the excess supply power value C with the maximum storage power Cmax, and judges the power supply situation according to the comparison result, where: If C ≤ Cmax, the imbalance decision module determines that the excess power supply is input into the storage library; If C > Cmax, the imbalance decision module determines to reduce the power generation efficiency.

[0017] Furthermore, when the imbalance decision module judges the imbalance situation between the high load density power region and the low load density power region according to the obtained load density power region imbalance time, the obtained high load density power region imbalance time T2 and the obtained low load density power region imbalance time T3 are compared with the preset imbalance time Tmax, and the imbalance situation between the high load density power region and the low load density power region is judged according to the comparison result, where: When T2 ≤ Tmax, the unbalance decision module determines that the unbalance state in the high load density power region is normal; When T3 ≤ Tmax, the unbalance decision module determines that the unbalance state in the low load density power region is normal; When T3 > Tmax, the unbalance decision module determines that the unbalance state in the low load density power region is abnormal and calls the reserve power to supply electricity emergently; When T2 > Tmax, the unbalance decision module determines that the unbalance state in the high load density power region is abnormal.

[0018] Further, when the unbalance decision module judges the unbalance conditions in the important power supply area and the non-important power supply area, according to the voltage amplitude V of node i i and the voltage phase angle difference θ between node i and node j ij the active power P flowing from node i to node j is calculated. ij Set , compare the active power Pc1 in the important power supply area and the active power Pc2 in the non-important power supply area in the high load density power region with the preset active power Pc, and judge the unbalance conditions in the important power supply area and the non-important power supply area according to the comparison result, where: When Pc2 < Pc, the unbalance decision module determines that there is an active power imbalance in the non-important power supply area and calls the reserve power to provide emergency power supply; When Pc1 < Pc, the unbalance decision module determines that there is an active power imbalance in the important power supply area.

[0019] Further, when the unbalance decision module adjusts the ratio between the high-demand power supply area and the non-high-demand power supply area in the important power supply area, set the daily demand of the high-demand power supply area as Q1, and the daily demand of the non-high-demand power supply area as Q2. When there is a power supply imbalance, the unbalance demand of the high-demand power supply area is Qc1, and the unbalance demand of the non-high-demand power supply area is Qc2. Introduce the first weight parameter β and the second weight parameter α, where: α + β = 1, α < β; At this time, the power supply of the high-demand area is Qc1 = β × Q1, and the power supply of the non-high-demand area is Qc2 = α × Q2.

[0020] Further, when the decision output module draws the power supply distribution table, it displays the power allocation situation between regions in the forms of tables and graphs, creates a power supply distribution matrix, where the rows represent power supply regions and the columns represent power receiving regions, and the elements in the power supply distribution matrix represent the power transmission power from one region to another. The power supply distribution matrix is combined with the power grid topology map, and the power transmission direction and flow are marked on the power grid topology map.

[0021] Further, when the decision output module outputs a scheduling instruction to the power generation equipment, it outputs the operation requirements for the power generation equipment in the form of an instruction list, and the scheduling instruction is directly sent by the decision output module to the control system of the power generation equipment.

[0022] Further, when the decision output module outputs emergency measure suggestions, in case of an emergency, the decision output module outputs emergency measure suggestions, and the emergency measure suggestions are timely notified to the administrator through text messages and the alarm system.

[0023] On the other hand, the present invention also provides a data mining method for an intelligent power grid, including: Step S1, collecting real-time user power consumption data to obtain real-time user power consumption data; Step S2, judging the outliers of the real-time user power consumption data, judging the duration of the outliers of the real-time user power consumption data, and also judging the categories of the abnormal real-time user power consumption data; Step S3, analyzing and calculating the power generation efficiency of the generator; Step S4, judging the load density of the power quantity region, judging the importance of the power supply region, and also judging the demand of the power supply region Step S5, judging the real-time balance state of the power grid; Step S6, identifying the unbalanced state of the power grid, and judging the supply and demand situation based on the energy supply data and energy consumption data under the abnormal unbalanced state; Step 7, judging the imbalance situation between the high-load density power quantity region and the low-load density power quantity region according to the unbalanced time of the load density power quantity region; Step S8, comparing the imbalance situations between the important power supply regions and the non-important power supply regions according to the effective power and the preset effective power, and outputting according to the comparison result; Step S9, adjusting the power supply quantity ratio between the high-demand power supply regions and the non-high-demand power supply regions in the important power supply regions; Step S10, drawing the power supply distribution table, outputting a scheduling instruction to the power generation equipment, and also outputting emergency measure suggestions.

[0024] Compared with the prior art, the beneficial effects of the present invention are as follows. The system collects real-time user power consumption data through the data collection module, obtains the user power consumption data in real time, and ensures the timeliness and accuracy of the data. The system analyzes the abnormal situation of the real-time user power consumption data through the data anomaly analysis module and outputs a solution, which helps to timely discover and repair potential vulnerabilities and errors in the system, and improve the stability and reliability of the system. The system analyzes and calculates the power generation efficiency of the generator through the energy supply analysis module, formulates a reasonable energy allocation plan, ensures the full utilization of energy, and reduces energy waste. The system judges the load density of the power consumption area and the importance and demand of the power supply area through the energy consumption analysis module, and can effectively divide the user power consumption area in detail for zonal power supply. The system judges the balance state of the power grid in real time through the balance analysis module, can timely discover the unbalanced state in the power grid, and thus quickly take measures to adjust it to ensure the stable operation of the power grid. The system judges the supply and demand situation, power consumption area and power supply area in the abnormal unbalanced state through the unbalanced decision module and outputs a decision, which helps to formulate a reasonable power supply distribution strategy and optimize the overall operation efficiency of the power grid. The system draws a power supply distribution situation table through the decision output module and outputs a scheduling instruction and an emergency measure suggestion to the power generation equipment. It can output accurate scheduling instructions to the power generation equipment according to the real-time demand of the power grid and the power supply distribution situation, and make emergency measure suggestions in case of emergency to ensure the safe and stable operation of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a schematic structural diagram of the data mining system of the smart grid in this embodiment; Figure 2 It is a schematic flow diagram of the data mining method of the smart grid in this embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] In order to make the purpose and advantages of the present invention clearer, the present invention will be further described below in conjunction with embodiments; it should be understood that the specific embodiments described here are only used to explain the present invention and are not used to limit the present invention.

[0027] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principle of the present invention and do not limit the protection scope of the present invention.

[0028] It should be noted that in the description of the present invention, unless otherwise clearly defined and limited, the terms "installation", "connection", and "coupling" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the communication inside two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0029] Please refer to Figure 1 as shown in the figure, which is a schematic structural diagram of the data mining system of the smart grid in this embodiment. The system includes: A data acquisition module for real-time acquisition of user power consumption data to obtain real-time user power consumption data; A data anomaly analysis module for judging the anomaly values of real-time user power consumption data, judging the duration of the anomaly values of real-time user power consumption data, and judging the types of abnormal real-time user power consumption data. The data anomaly analysis module is connected to the data acquisition module; A power supply analysis module for analyzing and calculating the power generation efficiency of the generator. The power supply analysis module is connected to the data acquisition module; A power consumption analysis module for judging the load density of the power consumption area, judging the importance of the power supply area, and judging the demand of the power supply area. The power consumption analysis module is connected to the power supply analysis module and the data acquisition module; A balance analysis module for real-time judgment of the balance state of the power grid. The balance analysis module is connected to the power consumption analysis module and the power supply analysis module; An imbalance decision module for identifying the imbalance state of the power grid, judging the supply and demand situation according to the power supply data and power consumption data under the abnormal imbalance state, judging the imbalance situation between the high-load density power consumption area and the low-load density power consumption area according to the imbalance time of the load density power consumption area obtained, comparing the imbalance situations between the important power supply area and the non-important power supply area according to the effective power and the preset effective power, outputting according to the comparison result, and adjusting the power supply ratio between the high-demand power supply area and the non-high-demand power supply area in the important power supply area. The imbalance decision module is connected to the power supply analysis module, the power consumption analysis module, and the balance analysis module; A decision output module for drawing a power supply distribution situation table, outputting a scheduling instruction to the power generation equipment, and outputting emergency measure suggestions. The decision output module is connected to the imbalance decision module.

[0030] Specifically, the system is applied to the power dispatching and control system. By combining with the customer data acquisition system, it analyzes and processes the collected user electricity consumption data, outputs power supply requirements, realizes zonal power supply, formulates accurate power supply plans according to the electricity consumption characteristics of different business forms, improves the operation efficiency of the power grid, ensures the stability and reliability of power supply, and saves energy and reduces operation costs at the same time. In particular, the system collects real-time user electricity consumption data through the data acquisition module, obtains real-time user electricity consumption data in real time, and ensures the timeliness and accuracy of the data. The system analyzes the abnormal conditions of real-time user electricity consumption data through the data anomaly analysis module and outputs solutions, which helps to timely discover and repair potential vulnerabilities and errors in the system, and improve the stability and reliability of the system. The system analyzes and calculates the power generation efficiency of the generator through the energy supply analysis module, formulates a reasonable energy configuration plan, ensures the full utilization of energy, can save resources and reduce operation costs. The system judges the load density of the power consumption area and the importance and demand of the power supply area through the energy consumption analysis module, and can effectively divide the user electricity consumption area in detail for zonal power supply. The system judges the balance state of the power grid in real time through the balance analysis module, can timely discover the unbalanced state in the power grid, and thus quickly take measures for adjustment to ensure the stable operation of the power grid. The system judges the supply and demand situation, power consumption area and power supply area under the abnormal unbalanced state through the unbalanced decision module and outputs a decision, which helps to formulate a reasonable power supply distribution strategy and improve the overall economy and efficiency of the power grid. The system draws a power supply distribution situation table through the decision output module and outputs dispatching instructions and emergency measure suggestions to the power generation equipment. It can output accurate dispatching instructions to the power generation equipment according to the real-time demand of the power grid and the power supply distribution situation, and make emergency measure suggestions in case of emergency to ensure the safe and stable operation of the power grid.

[0031] Specifically, when the data acquisition module collects user electricity consumption data in real time, the DEWETRON customer data acquisition system is used to collect user electricity consumption data in real time, and real-time user electricity consumption data is obtained. The real-time user electricity consumption data includes user electricity consumption and power supply.

[0032] Specifically, the real-time user electricity consumption data refers to the real-time collected user power consumption information, such as the user's power supply voltage level and electricity bill expenditure. The DEWETRON customer data acquisition system refers to a data acquisition, conditioning and analysis system, and its Chinese translation is Dewetron. The user electricity consumption refers to the actual electricity consumption of the user's electrical equipment, and the power supply refers to the electricity supplied by power plants, power supply areas and power grids to users.

[0033] Specifically, the data acquisition module can provide accurate user electricity consumption data, enabling the system to efficiently and accurately collect and transmit user electricity consumption data, and perform in-depth data mining and analysis.

[0034] Specifically, when the data anomaly analysis module determines the anomaly value of real-time user electricity consumption data, it calculates the difference T1 based on the real-time user electricity consumption data t and the historical user electricity consumption data t1, sets T1 = t - t1, compares the difference T1 with the preset positive value T0 and the preset negative value T2, and determines the anomaly value of real-time user electricity consumption data according to the comparison result, where: When T1 ≥ 0, the data anomaly analysis module compares the difference T1 with the preset positive value T0 and determines the anomaly value of the data according to the comparison result, where: If T1 > T0, the data anomaly analysis module determines that the real-time user electricity consumption data is abnormal and records this data in the data anomaly set U; If T1 ≤ T0, the data anomaly analysis module determines that the real-time user electricity consumption data is normal; When T1 < 0, the data anomaly analysis module compares the difference T1 with the preset negative value T2 and determines the anomaly value of the data according to the comparison result, where: If T1 ≥ T2, the data anomaly analysis module determines that the real-time user electricity consumption data is normal; If T1 < T2, the data anomaly analysis module determines that the real-time user electricity consumption data is abnormal and records this abnormal real-time user electricity consumption data in the data anomaly set U.

[0035] Specifically, the anomaly value of real-time user electricity consumption data refers to the observed value different from other data points in the real-time user electricity consumption data set. The historical user electricity consumption data refers to the user electricity consumption data generated by the user's electricity consumption behavior within a preset historical time interval. In this embodiment, the specific value of the preset historical time interval is not limited, and those skilled in the art can freely set it according to actual needs, as long as it meets the requirement of collecting historical user electricity consumption data. For example, if the preset historical time interval is set to one hour, then the historical electricity consumption data of users within one hour is collected.

[0036] Specifically, the data anomaly analysis module can quickly analyze the user electricity consumption data, compare the real-time user electricity consumption data with the historical data, and can timely detect the anomalies in the user electricity consumption data.

[0037] Specifically, when the data anomaly analysis module determines the duration of the abnormal value of real-time user electricity consumption data, it compares the duration Tmin of the abnormal value of real-time user electricity consumption data with a preset value Tmin0, and determines the duration of the abnormal data according to the comparison result, where: When Tmin ≤ Tmin0, the data anomaly analysis module determines that the duration of the abnormal value of real-time user electricity consumption data is normal; When Tmin > Tmin0, the data anomaly analysis module determines that the duration of the abnormal value of real-time user electricity consumption data is abnormal.

[0038] Specifically, the duration of the abnormal value of real-time user electricity consumption data refers to the time length from when the data is determined to be abnormal until the data anomaly analysis module makes a time judgment. The preset value Tmin0 refers to the preset duration interval for judging the duration of the abnormal value of real-time user electricity consumption data. In this embodiment, the specific value of the preset duration interval is not limited, and those skilled in the relevant art can freely set it according to actual needs, as long as it meets the requirement of judging the duration of the abnormal value of real-time user electricity consumption data. For example, the duration interval can be set to one hour, then the preset value Tmin0 = 1 hour.

[0039] Specifically, the data anomaly analysis module can effectively distinguish the data anomaly situations caused by accidental factors, avoiding unnecessary subsequent in-depth investigations and false alarms.

[0040] Specifically, when the data anomaly analysis module determines the category of abnormal real-time user electricity consumption data, it compares the abnormal value X1 of real-time user electricity consumption data with the maximum error value X0 of historical data, and determines the category of abnormal real-time user electricity consumption data according to the comparison result, where: When X1 > X0, the data anomaly analysis module determines that the category of the abnormal real-time user electricity consumption data is caused by a power meter failure; When X1 = 0, the data anomaly analysis module determines that the category of the abnormal real-time user electricity consumption data is caused by a power meter failure; When 0 < X1 < X0, the data anomaly analysis module determines that the category of the abnormal real-time user electricity consumption data is caused by the line loss of the transformer substation area. Use data visualization and an oscilloscope to compare the waveform and numerical changes section by section from the input end to find the abnormal part, and use the backup power supply for emergency power supply.

[0041] Specifically, the electric energy meter refers to an instrument used to measure electric energy. The substation line refers to the power line used to connect the transformer and the user end within its power supply substation area. Data visualization refers to presenting the operation data generated during the operation of the system through visual elements. The operation data includes voltage, current, power, frequency, and equipment status. The visual elements include graphs, charts, maps, and dashboards. In this embodiment, the method of using data visualization and an oscilloscope to find the abnormal part is not limited, and those skilled in the art can freely set it according to actual needs, as long as the requirement of finding the abnormal part is met. For example, it can be set to use data visualization and an oscilloscope to compare the waveform and numerical changes section by section from the input end to find the abnormal part. The oscilloscope refers to an electronic instrument for observing and measuring the waveform of an electrical signal. The electrical signal waveform refers to the graphical representation of the voltage and current changing with time. The backup power supply refers to the power supply that can automatically be put into operation when the main power supply cannot meet the power supply demand.

[0042] Specifically, the data anomaly analysis module judges the types of abnormal data, can accurately locate the types of abnormal data, distinguishes between electric energy meter faults and substation line loss problems, helps to further narrow down the fault range. After it is judged that the abnormal data is caused by substation line loss, it can promptly use the backup power supply for emergency power supply, reduce the impact on users caused by line anomalies, and ensure the basic power consumption needs of users.

[0043] Specifically, when the energy supply analysis module analyzes and calculates the power generation efficiency of the generator, according to the electric energy We output by the generator and the heat Qin input by fuel combustion, the power generation efficiency η is calculated, and it is set that, ; The power generation efficiency η is compared with the preset power generation efficiency η 0, and the power generation efficiency of the generator is judged according to the comparison result, where: When η ≥ η 0, the energy supply analysis module determines that the power generation efficiency meets the standard; When η < η 0, the energy supply analysis module determines that the power generation efficiency does not meet the standard, and increases the operating pressure and temperature of the generator until the power generation efficiency meets the standard.

[0044] Specifically, the power generation efficiency refers to the efficiency of the generator in converting the input energy into electrical energy. The generator is a mechanical device that converts energy into mechanical energy and then converts the mechanical energy into electrical energy. In this embodiment, the type of the generator is not specifically limited, and those skilled in the art can freely set it according to the actual situation, as long as the requirement for judging the power generation efficiency is met. For example, the generator can be set as a thermal power generator.

[0045] Specifically, the energy supply analysis module analyzes and calculates the power generation efficiency, and can accurately obtain the power generation efficiency of the generator, which helps to discover potential problems in the process of energy utilization, so as to carry out targeted optimization.

[0046] Specifically, when the energy consumption analysis module delimits the high-load density power region and the low-load density power region, according to the regional power consumption load F and the regional area S, the regional load density value ρ is calculated, and ρ = F / S is set. The regional load density value is compared with the preset regional density value ρ0, and the regional load density is analyzed according to the comparison result, where: When ρ > ρ0, the energy consumption analysis module determines that this region belongs to the high-load density power region; When ρ ≤ ρ0, the energy consumption analysis module determines that this region belongs to the low-load density power region.

[0047] Specifically, the regional load density refers to the total sum of the power consumption of all users in this region, the regional area refers to the target geographical area range, such as residential areas, hospitals and commercial gathering areas. The high-load density power region refers to the geographical area with relatively higher power consumption demand compared with the low-load density power region within the power grid coverage. The low-load density power region refers to the region with relatively lower power consumption demand compared with the high-load density power region within the power grid supply range.

[0048] Specifically, the energy consumption analysis module delimits the high-load density power region and the low-load density power region, which helps to further refine the management and maintenance of the power grid. In the high-load density power region, the power grid construction can be strengthened to improve the power supply capacity and power supply quality. In the low-load density power region, the power grid investment can be reduced to optimize the resource allocation.

[0049] Specifically, when the energy consumption analysis module differentiates the important power supply area and the non-important power supply area, according to the average load Pa and the maximum load Pmax, the average load rate LR is calculated, and it is set that, ; According to the minimum load Pmin and the maximum load Pmax, the peak-valley difference P0 is calculated, and P0 = Pmax - Pmin is set; Compare the average load factor LR1 and the peak-to-valley difference P1 of the power supply area S1 with the average load factor LR2 and the peak-to-valley difference P2 of the power supply area S2, and judge the important power supply area and the non-important power supply area according to the comparison result, where: When LR1 ≤ LR2, the judgment result is not output; When LR1 > LR2, if P1 < P2, the energy consumption analysis module determines that the power supply area S1 is an important power supply area and the power supply area S2 is a non-important power supply area; If P1 > P2, the energy consumption analysis module determines that the power supply area S2 is an important power supply area and the power supply area S1 is a non-important power supply area.

[0050] Specifically, the important power supply area refers to the area in the power grid system where power outages cause serious consequences, such as casualties. The power supply reliability requirements for the important power supply area are high, and power supply needs to be guaranteed preferentially. The non-important power supply area refers to the area where the power supply reliability requirements are relatively lower than those of the important power supply area and does not require preferential power supply guarantee.

[0051] Specifically, the energy consumption analysis module differentiates between the important power supply area and the non-important power supply area. By accurately positioning the important power supply area, it ensures the power consumption needs of key infrastructure and important users, helps to formulate a reasonable power grid dispatching plan, optimize the power grid power flow distribution, thereby reducing power grid losses and improving energy utilization efficiency.

[0052] Specifically, when the energy consumption analysis module differentiates between the high-demand power supply area and the non-high-demand power supply area, compare the user power consumption L with the preset power consumption L0, and judge the high-demand power supply area and the non-high-demand power supply area according to the comparison result, where: When L > L0, the energy consumption analysis module determines it as the high-demand power supply area; When L ≤ L0, the energy consumption analysis module determines it as the non-high-demand power supply area.

[0053] Specifically, the user power consumption refers to the total power consumption of the user within a preset time interval. In this embodiment, the specific value of the preset time interval is not limited, and those skilled in the relevant art can freely set it according to actual needs, as long as it meets the requirement of counting the user power consumption. For example, if the preset time interval is set to one day, then count the user power consumption within one day. The preset power consumption refers to the preset user power consumption used to differentiate between the high-demand power supply area and the non-high-demand power supply area. In this embodiment, the specific value of the preset power consumption is not limited, and those skilled in the relevant art can freely set it according to actual needs, as long as it meets the requirement of differentiating between the high-demand power supply area and the non-high-demand power supply area. For example, the preset power consumption can be set to L0 = 12 kw / h.

[0054] Specifically, the energy consumption analysis module differentiates between high-demand power supply areas and non-high-demand power supply areas. In high-demand power supply areas, power supply is prioritized, and power grid construction and maintenance are strengthened to ensure the stability and reliability of power supply. In non-high-demand power supply areas, power resources can be flexibly allocated to reduce operating costs.

[0055] Specifically, when the balance analysis module determines the balance state of the current power grid, according to the power generation power Pi of the i-th power generation unit Gi , the total number n of power generation units, the power consumption load power Pj of the j-th Lj , the total number m of power consumption loads, and the power loss Pl during the transmission and distribution of the power grid s , the power is calculated as follows: ; According to the power time interval, the latest power generation power data, power consumption load power data, and power loss data are extracted from the database and substituted into the power calculation formula for calculation. Set as A1, as A0, where: When |A1 - A0| < 1, the balance analysis module determines that the current power grid is in a power balance state; When |A1 - A0| ≥ 1, the balance analysis module determines that the current power grid is in a power imbalance state.

[0056] Specifically, the power generation unit refers to a basic component unit in the power system, such as a thermal power generation unit and a nuclear power generation unit. The power generation power refers to the electric energy generated by the power generation equipment per unit time. The power consumption load power refers to the work done by the current and voltage of the power consumption equipment within the time interval. The total number of power consumption loads refers to the total power consumed by all power consumption equipment connected to the power system during the target time period. The power loss refers to the phenomenon of energy loss when energy is transmitted from the power generation end to the power consumption end in the power grid and during internal distribution in the power grid. The power time interval refers to the time interval used to extract the latest power generation power data, power consumption load power data, and power loss data from the database. In this embodiment, the value of the power time interval is not specifically limited, and those skilled in the art can freely set it according to the actual situation as long as it meets the requirement of calculating the power, such as setting the power time interval to 10 minutes.

[0057] Specifically, when the balance analysis module determines the balance state of the current power grid, it can obtain various data in the power grid in real time, thereby realizing the dynamic monitoring of the power grid state and ensuring the stable operation of the power grid.

[0058] Specifically, when the imbalance decision-making module identifies the imbalance state, it compares the power imbalance time Td with the preset power imbalance time Tdo, and identifies the imbalance state according to the comparison result, where: When Td ≤ Tdo, the imbalance decision-making module determines that the imbalance state is normal; When Td > Tdo, the imbalance decision-making module determines that the imbalance state is abnormal.

[0059] Specifically, the imbalance state refers to the power imbalance state determined by the balance analysis module for the current power grid, and the power imbalance time refers to the time when the power grid is in the imbalance state.

[0060] Specifically, when the imbalance decision-making module identifies an abnormal imbalance state and takes corresponding adjustment measures, it can effectively prevent the occurrence of power grid accidents and ensure the safe and stable operation of the power grid.

[0061] Specifically, when the imbalance decision-making module judges the supply-demand situation based on the energy supply data and energy consumption data under the abnormal imbalance state, it compares the energy supply data PG with the energy consumption data Ph, judges the supply-demand situation according to the comparison result, and outputs according to the judgment result, where: When PG < Ph, the imbalance decision-making module determines that the supply is less than the demand and does not output the judgment result; When PG ≥ Ph, the imbalance decision-making module determines that the supply is greater than the demand. According to the energy supply data PG and the energy consumption data Ph, it calculates the excess supply power value C, sets C = PG - Ph, compares the excess supply power value C with the maximum energy storage value Cmax, and judges the power supply situation according to the comparison result, where: If C ≤ Cmax, the imbalance decision-making module determines that the excess power supply is input into the storage library; If C > Cmax, the imbalance decision-making module determines to reduce the power generation efficiency.

[0062] Specifically, the energy supply data refers to the electrical energy data provided by the power system to users, the energy consumption data refers to the electrical energy data consumed by the power system during operation, and the storage library refers to a power storage system that stores electricity and releases it when needed.

[0063] Specifically, by real-time monitoring and judging the supply-demand relationship, the imbalance decision-making module can ensure that the power system stores excess electrical energy in a timely manner when the supply is greater than the demand, which helps to reduce energy waste and improve energy utilization efficiency.

[0064] Specifically, when the imbalance decision module determines the imbalance between the high load density power region and the low load density power region based on the obtained imbalance time of the load density power region, the obtained imbalance time T2 of the high load density power region and the obtained imbalance time T3 of the low load density power region are compared with the preset imbalance time Tmax, and the imbalance between the high load density power region and the low load density power region is determined according to the comparison result, where: When T2 ≤ Tmax, the imbalance decision module determines that the imbalance state of the high load density power region is normal; When T3 ≤ Tmax, the imbalance decision module determines that the imbalance state of the low load density power region is normal; When T3 > Tmax, the imbalance decision module determines that the imbalance state of the low load density power region is abnormal, and calls the reserve power to supply electricity urgently; When T2 > Tmax, the imbalance decision module determines that the imbalance state of the high load density power region is abnormal.

[0065] Specifically, the imbalance time of the high load density power region refers to the time when the high load density power region is in an unbalanced state, the imbalance time of the low load density power region refers to the time when the low load density power region is in an unbalanced state, and the preset imbalance time refers to the preset time interval of the unbalanced state used to determine the imbalance between the high load density power region and the low load density power region. In this embodiment, the preset time interval of the imbalance is not limited, and those skilled in the relevant art can freely set it according to actual needs, as long as it meets the requirement of determining the imbalance between the high load density power region and the low load density power region. For example, the preset imbalance time Tmax can be set to 1 hour.

[0066] Specifically, when the imbalance decision module determines that the imbalance state of the low load density power region is abnormal, it calls the reserve power to supply electricity urgently to ensure that the region can obtain sufficient power supply in the case of power supply and demand imbalance, and avoid power interruption and power outage events.

[0067] Specifically, when the imbalance decision module determines the imbalance between the important power supply region and the non-important power supply region, according to the voltage amplitude V of node i i and the voltage phase angle difference θ between node i and node j ij the active power P flowing from node i to node j is calculated, and it is set that ij calculate, set , compare the active power Pc1 of the important power supply area and the active power Pc2 of the non-important power supply area in the high load density power area with the preset active power Pc, and judge the imbalance situation of the important power supply area and the non-important power supply area according to the comparison result, where: When Pc2 < Pc, the imbalance decision module determines that there is an active power imbalance in the non-important power supply area and calls the reserve power to provide emergency power supply; When Pc1 < Pc, the imbalance decision module determines that there is an active power imbalance in the important power supply area.

[0068] Specifically, the active power refers to the actual consumed AC electrical energy per unit time, such as thermal energy and mechanical energy. The voltage amplitude is a key physical quantity representing the magnitude of the AC voltage and represents the maximum value that the AC voltage can reach within one cycle. The voltage phase angle difference refers to the difference between the phase angles of two AC voltages with the same frequency in an AC circuit.

[0069] Specifically, the imbalance decision module obtains the active power of the important power supply area and the non-important power supply area in real time and compares it with the preset value. When it detects an active power imbalance in the non-important power supply area, the imbalance decision module can immediately call the reserve power to provide emergency power supply, which helps to reduce power grid failures and power outages caused by power imbalance and improve the reliability and stability of the power grid.

[0070] Specifically, when the imbalance decision module adjusts the ratio of the high-demand power supply area and the non-high-demand power supply area in the important power supply area, set the daily demand of the high-demand power supply area as Q1 and the daily demand of the non-high-demand power supply area as Q2. When there is a power supply imbalance, the imbalance demand of the high-demand power supply area is Qc1 and the imbalance demand of the non-high-demand power supply area is Qc2. Introduce the first weight parameter β and the second weight parameter α, where: α + β = 1, α < β; At this time, the power supply of the high-demand area is Qc1 = β × Q1, and the power supply of the non-high-demand area is Qc2 = α × Q2.

[0071] Specifically, the high-demand power supply area refers to an area with a large power demand and a tight power supply. The non-high-demand power supply area refers to an area with a relatively lower power demand and a relatively sufficient power supply compared to the high-demand power supply area. The first weight parameter β refers to a parameter for proportionally adjusting the power supply quantity to the high-demand power supply area in the case of power supply imbalance. In this embodiment, the value of the first weight parameter β is not specifically limited, and those skilled in the art can freely set it according to the actual situation, as long as it meets the requirement of proportionally adjusting the high-demand power supply area and the non-high-demand power supply area. For example, β = 0.7 can be set. The second weight parameter α refers to a parameter for proportionally adjusting the power supply quantity to the non-high-demand power supply area in the case of power supply imbalance. In this embodiment, the value of the second weight parameter α is not specifically limited, and those skilled in the art can freely set it according to the actual situation, as long as it meets the requirement of proportionally adjusting the high-demand power supply area and the non-high-demand power supply area. For example, α = 0.3 can be set.

[0072] Specifically, in the case of power supply imbalance in the important power supply area, the high-demand power supply area will receive more power supply, which helps to alleviate its power shortage problem, and appropriately reduce the power supply quantity to the non-high-demand area to avoid power waste and improve its energy utilization efficiency.

[0073] Specifically, when the decision output module draws the power supply distribution table, it shows the power allocation situation between regions in the form of a table and a graph, makes a power supply distribution matrix, where the rows represent the power supply areas and the columns represent the power receiving areas, and the elements in the power supply distribution matrix represent the power transmission power from one area to another area. The power supply distribution matrix is combined with the power grid topology map, and the direction and flow of power transmission are marked on the power grid topology map; When the decision output module outputs a scheduling instruction to the power generation equipment, it outputs the operation requirements for the power generation equipment in the form of an instruction list, and the scheduling instruction is directly sent by the decision output module to the control system of the power generation equipment; When the decision output module outputs emergency measure suggestions, in case of an emergency, the decision output module outputs emergency measure suggestions, and the emergency measure suggestions are timely notified to the administrator through text messages and the alarm system.

[0074] Specifically, the power supply distribution situation table refers to a form for displaying the power allocation situation among regions, such as tables and graphs. The power supply distribution matrix refers to an important tool for describing the connection relationships and parameters among elements in the power supply system. The power grid topology diagram refers to a schematic diagram of the physical layout structure composed of power grid nodes and the transmission lines connected thereto. The dispatching instruction refers to the specific operation requirements generated by the decision-making output module and sent to the power generation equipment. The instruction list refers to the requirements for operating the power generation equipment generated by the decision-making output module. The gas turbine refers to an internal combustion power machine that converts the energy of fuel into useful work. The emergency situation refers to a sudden situation that poses a threat to people, property, and the environment, such as a large-scale power outage and extreme weather affecting the power grid. The emergency measure suggestions refer to a series of action guidelines and solutions proposed for the current emergency situation, such as activating the emergency diesel generator in Region I to supply power to important facilities and cutting off the non-essential load branch lines in Region J. The administrator refers to a person who has the management responsibility for power grid equipment.

[0075] Please refer to Figure 2 as shown, which is a schematic flowchart of the data mining method for the smart power grid in this embodiment. The method includes: Step S1, collect real-time user power consumption data to obtain real-time user power consumption data; Step S2, judge the outliers of the real-time user power consumption data, judge the duration of the outliers of the real-time user power consumption data, and also judge the categories of the abnormal real-time user power consumption data; Step S3, analyze and calculate the power generation efficiency of the generator; Step S4, judge the load density of the power quantity area, judge the importance of the power supply area, and also judge the demand of the power supply area; Step S5, judge the real-time balance state of the power grid; Step S6, identify the unbalanced state of the power grid, and judge the supply-demand situation based on the energy supply data and energy consumption data under the abnormal unbalanced state; Step 7, judge the unbalanced situation between the high-load density power quantity area and the low-load density power quantity area according to the unbalanced time of the load density power quantity area obtained; Step S8, compare the unbalanced situations between the important power supply area and the non-important power supply area according to the effective power and the preset effective power, and output according to the comparison result; Step S9, adjust the power supply ratio between the high-demand power supply area and the non-high-demand power supply area in the important power supply area; Step S10, draw the power supply distribution situation table, issue dispatching instructions to the power generation equipment, and also output emergency measure suggestions.

[0076] So far, the technical solution of the present invention has been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easily understood by those skilled in the art that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A data mining system based on big data in a smart grid, characterized in that: The system comprises: The data collection module is used to collect the user's electricity consumption data in real time to obtain the real-time user electricity consumption data; The data anomaly analysis module is used to judge the abnormal value of real-time user power consumption data, the duration of the abnormal value of real-time user power consumption data, and the category of abnormal real-time user power consumption data; Energy supply analysis module, used to analyze and calculate the power generation efficiency of the generator; Energy consumption analysis module, used to judge the load density of the power area, the importance of the power supply area, and the demand for the power supply area; Balance analysis module, used to make real-time judgment on the balance status of the power grid; An imbalance decision module is used to identify the imbalance state of the power grid, and to judge the supply and demand situation according to the energy supply data and energy consumption data under the abnormal imbalance state, and to judge the imbalance situation between the high load density power area and the low load density power area according to the obtained load density power area imbalance time, and to compare the imbalance situation between the important power supply area and the non-important power supply area according to the effective power and the preset effective power, and to output according to the comparison result, and to adjust the power supply ratio of the important power supply area to the high demand power supply area and the non-high demand power supply area; The decision output module is used to draw a power supply distribution table, output dispatch instructions to power generation equipment, and output emergency measures suggestions.

2. The data mining system for smart grid according to claim 1, characterized in that: When the data anomaly analysis module judges the abnormal value of the real-time user power consumption data, the difference T1 is calculated according to the real-time user power consumption data t and the historical user power consumption data t1, and T1=t-t1 is set. The difference T1 is compared with the preset positive value T0 and the preset negative value T2, and the abnormal value of the real-time user power consumption data is judged according to the comparison result, wherein: When T1≥0, the data anomaly analysis module compares the difference T1 with the preset positive value T0, and determines the data anomaly according to the comparison result, where: If T1>T0, the data anomaly analysis module determines that the real-time user power consumption data is abnormal, and records the data in the data anomaly set U; If T1≤T0, the data anomaly analysis module determines that there is no anomaly in the real-time user power consumption data; When T1<0, the data anomaly analysis module compares the difference T1 with the preset negative value T2, and determines the data anomaly according to the comparison result, wherein: If T1≥T2, the data anomaly analysis module determines that there is no anomaly in the real-time user power consumption data; If T1<T2, the data anomaly analysis module determines that the real-time user power consumption data is abnormal, and records the abnormal real-time user power consumption data in the data anomaly set U.

3. The data mining system for smart grid according to claim 2, characterized in that: When the data anomaly analysis module determines the duration of the abnormal value of the real-time user power consumption data, the duration Tmin of the abnormal value of the real-time user power consumption data is compared with the preset value Tmin0, and the duration of the abnormal data is determined according to the comparison result, wherein: When Tmin≤Tmin0, the data anomaly analysis module determines that the duration of the abnormal value of the real-time user power consumption data is normal; When Tmin>Tmin0, the data anomaly analysis module determines that the duration of the abnormal value of the real-time user power consumption data is abnormal; When the data anomaly analysis module determines the category of abnormal real-time user power consumption data, the abnormal value X1 of the real-time user power consumption data is compared with the maximum error value X0 of the historical data, and the category of the abnormal real-time user power consumption data is determined according to the comparison result, wherein: When X1>X0, the data anomaly analysis module determines that the abnormal real-time user power consumption data category is caused by a power meter failure; When X1=0, the data anomaly analysis module determines that the abnormal real-time user power consumption data category is caused by a power meter failure; When 0<X1<X0, the data anomaly analysis module determines that the abnormal real-time user electricity consumption data category is caused by line loss in the substation area, and uses data visualization and an oscilloscope to compare the waveform and numerical changes from the input end section by section to find the abnormal part and use the backup power supply for emergency power supply.

4. The data mining system for smart grid according to claim 1, characterized in that: When the energy supply analysis module analyzes and calculates the power generation efficiency of the generator, the power generation efficiency is calculated based on the electric energy We output by the generator and the heat Qin input by the fuel combustion. η Calculate, set, ; The power generation efficiency η With preset power generation efficiency η 0, and judge the power generation efficiency of the generator according to the comparison result, where: when η ≥ η At 0, the energy supply analysis module determines that the power generation efficiency meets the standard; when η < η At 0, the energy supply analysis module determines that the power generation efficiency does not meet the standard, and increases the operating pressure and temperature of the generator until the power generation efficiency meets the standard.

5. The data mining system for smart grid according to claim 1, characterized in that: When the energy consumption analysis module defines the high load density power area and the low load density power area, the regional load density value ρ is calculated according to the regional power load F and the regional area S, and ρ=F / S is set. The regional load density value is compared with the preset regional density value ρ0, and the regional load density is analyzed according to the comparison result, wherein: When ρ>ρ0, the energy consumption analysis module determines that the area belongs to a high load density power area; When ρ≤ρ0, the energy consumption analysis module determines that the area belongs to a low load density power area.

6. The data mining system for smart grid according to claim 5, characterized in that: When the energy consumption analysis module distinguishes between important power supply areas and non-important power supply areas, the average load rate LR is calculated according to the average load Pa and the maximum load Pmax, and is set. ; According to the minimum load Pmin and the maximum load Pmax, calculate the peak-to-valley difference P0, and set P0=Pmax-Pmin; The average load rate LR1 and the peak-to-valley difference P1 of the power supply area S1 are compared with the average load rate LR2 and the peak-to-valley difference P2 of the power supply area S2, and the important power supply areas and the non-important power supply areas are judged according to the comparison results, where: When LR1≤LR2, the judgment result is not output; When LR1>LR2, if P1<P2, the energy consumption analysis module determines that the power supply area S1 is an important power supply area, and the power supply area S2 is a non-important power supply area; If P1>P2, the energy consumption analysis module determines that the power supply area S2 is an important power supply area and the power supply area S1 is a non-important power supply area; When the energy consumption analysis module distinguishes between high power demand areas and non-high power demand areas, the user power consumption L is compared with the preset power consumption L0, and the high power demand areas and non-high power demand areas are determined according to the comparison results, wherein: When L>L0, the energy consumption analysis module determines that it is a high power demand area; When L≤L0, the energy consumption analysis module determines that the area is not a high power demand area.

7. The data mining system for smart grid according to claim 1, characterized in that: When the balance analysis module determines the balance state of the current power grid, according to the power generation power P of the i-th power generation unit Gi , the total number of power generation units n, the jth power load power P Lj , the total number of power loads m and the power loss P of the power grid during transmission and distribution s , calculate the power: ； According to the power time interval, the latest power generation data, power load power data and power loss data are extracted from the database, and substituted into the power calculation formula for calculation. For A1, is A0, where: When |A1-A0|<1, the balance analysis module determines that the current power grid is in a power balance state; When |A1-A0|≥1, the balance analysis module determines that the current power grid is in a power imbalance state.

8. The data mining system for smart grid according to claim 1, characterized in that: When the imbalance decision module identifies the imbalance state, the obtained power imbalance time Td is compared with the preset power imbalance time Tdo, and the imbalance state is identified according to the comparison result, wherein: When Td≤Tdo, the imbalance decision module determines that the imbalance state is normal; When Td>Tdo, the imbalance decision module determines that the imbalance state is abnormal; When the imbalance decision module judges the supply and demand situation according to the energy supply data and the energy consumption data in the abnormal imbalance state, the energy supply data PG is compared with the energy consumption data Ph, the supply and demand situation is judged according to the comparison result, and the judgment result is output, wherein: When PG<Ph, the imbalance decision module determines that supply is less than demand and does not output the judgment result; When PG≥Ph, the imbalance decision module determines that supply exceeds demand, calculates the extra supply power value C according to the energy supply data PG and the energy consumption data Ph, sets C=PG-Ph, compares the extra supply power value C with the maximum power storage value Cmax, and judges the power supply situation according to the comparison result, where: If C≤Cmax, the imbalance decision module determines that the excess power supply is input into the storage reservoir; If C>Cmax, the unbalanced decision module determines to reduce the power generation efficiency; When the imbalance decision module judges the imbalance between the high load density power area and the low load density power area according to the obtained load density power area imbalance time, the obtained high load density power area imbalance time T2 and the obtained low load density power area imbalance time T3 are compared with the preset imbalance time Tmax, and the imbalance between the high load density power area and the low load density power area is judged according to the comparison result, wherein: When T2≤Tmax, the unbalanced decision module determines that the unbalanced state in the high load density power area is normal; When T3≤Tmax, the imbalance decision module determines that the imbalance state in the low load density power area is normal; When T3>Tmax, the imbalance decision module determines that the imbalance state of the low load density power area is abnormal, and calls the reserve power for emergency power supply; When T2>Tmax, the unbalanced decision module determines that the unbalanced state in the high load density power area is abnormal; When the imbalance decision module determines the imbalance between the important power supply area and the non-important power supply area, according to the voltage amplitude V of the node i i The voltage phase difference θ between node i and node j ij Active power P flowing from node i to node j ij Calculate and set , compare the active power Pc1 of the important power supply area in the high load density power area and the active power Pc2 of the non-important power supply area with the preset active power Pc, and judge the imbalance between the important power supply area and the non-important power supply area according to the comparison result, wherein: When Pc2<Pc, the imbalance decision module determines that active power imbalance occurs in the non-important power supply area, and calls on the reserve power to provide emergency power supply; When Pc1<Pc, the imbalance decision module determines that active power imbalance occurs in the important power supply area; When the imbalance decision module makes proportional adjustments to the high-demand power supply area and the non-high-demand power supply area in the important power supply area, the daily demand of the high-demand power supply area is set to Q1, and the daily demand of the non-high-demand power supply area is set to Q2. When power supply imbalance occurs, the unbalanced demand of the high-demand power supply area is Qc1, and the unbalanced demand of the non-high-demand power supply area is Qc2. A first weight parameter β and a second weight parameter α are introduced, wherein: α＋β=1，α＜β; At this time, the power supply in the high-demand area is Qc1=β×Q1, and the power supply in the non-high-demand area is Qc2=α×Q2.

9. The data mining system for smart grid according to claim 1, characterized in that: When the decision output module draws the power supply distribution table, the power allocation between the regions is displayed in the form of tables and graphs, and a power supply distribution matrix is ​​made. The rows represent the power supply areas, the columns represent the power receiving areas, and the elements in the power supply distribution matrix represent the power transmitted from one area to another area. The power supply distribution matrix cooperates with the power grid topology map, and the direction and flow of power transmission are marked on the power grid topology map; When the decision output module outputs the dispatch instruction to the power generation equipment, the operation requirements for the power generation equipment are output in the form of an instruction list, and the dispatch instruction is directly sent by the decision output module to the control system of the power generation equipment; When the decision output module outputs the emergency measure suggestion, when an emergency occurs, the decision output module outputs the emergency measure suggestion, and the emergency measure suggestion is promptly notified to the administrator via SMS and alarm system.

10. A method for a data mining system for a smart grid as claimed in claims 1 to 9, characterized in that: include: Step S1, collecting user electricity consumption data in real time to obtain real-time user electricity consumption data; Step S2, determining the abnormal value of the real-time user power consumption data, determining the duration of the abnormal value of the real-time user power consumption data, and determining the category of the abnormal real-time user power consumption data; Step S3, analyzing and calculating the power generation efficiency of the generator; Step S4: determine the load density of the power area, the importance of the power supply area, and the demand for the power supply area. Step S5, making a real-time judgment on the balance state of the power grid; Step S6, identifying the unbalanced state of the power grid, and judging the supply and demand situation based on the energy supply data and energy consumption data under the abnormal unbalanced state; Step 7, judging the imbalance between the high load density power area and the low load density power area according to the obtained load density power area imbalance time; Step S8, comparing the imbalance between the important power supply area and the non-important power supply area according to the effective power and the preset effective power, and outputting according to the comparison result; Step S9, adjusting the power supply ratio between the high-demand power supply area and the non-high-demand power supply area in the important power supply area; Step S10, draw a power supply distribution table, output dispatch instructions to power generation equipment, and output emergency measures suggestions.

Images