Distribution network real-time fault power failure monitoring method and system based on multi-source data fusion

Abstract

The invention discloses a distribution network real-time fault power failure monitoring method based on multi-source data fusion. The method comprises the following steps: obtaining distribution network data; according to the power distribution network data, associating an electric energy meter, a power user and a distribution transformer relationship, and matching with the power-off and power-on data of the electric energy meter to obtain real-time power-off and power-on data of the user and the distribution transformer equipment; judging the power failure type of the distribution transformer according to the real-time power failure and recovery data of the user to obtain a judgment result; and according to a judgment result, carrying out authenticity judgment, and if the power failure is true, sending a maintenance early warning to the corresponding area to complete monitoring of the power distribution network. The invention also discloses a system for realizing the distribution network real-time fault power failure monitoring method based on multi-source data fusion. According to the method, the power failure range judgment from bottom to top is adopted, and the accuracy and granularity of power failure range judgment are improved. According to the method, the monitoring efficiency is greatly improved, power failure repair work can be effectively assisted, and the stability of the power distribution network is enhanced.

Description

Technical Field

[0001] The present invention belongs to the field of fault power outage monitoring, and in particular relates to a distribution network real-time fault power outage monitoring method and system based on multi-source data fusion. Background Art

[0002] With the progress and development of the economy and society, the demand for electricity in all walks of life is growing, and higher requirements are put forward for power reliability. With the continuous deepening of distribution network construction, the power supply mode of distribution network has gradually evolved from the traditional tree-shaped unidirectional power supply to the mesh multi-power supply circuit power supply. Therefore, the monitoring of real-time fault power outages and the judgment of the impact range are no longer limited to the monitoring of line tripping, circuit breaker opening and closing, and equipment failure.

[0003] The causes of distribution network power outages are classified according to voltage levels, mainly into high, medium and low voltage faults. High-level faults will have a certain impact on low-level faults, and the scope of impact has changed from the original absolute impact to uncertain impact due to the complexity of the distribution network grid structure.

[0004] Traditional power outage analysis mainly focuses on equipment faults, such as whole-line tripping, branch line circuit breaker opening and closing, and distribution transformer failure. The impact of multiple power supply circuits has led to the traditional one-size-fits-all approach no longer being applicable. Ignoring the impact of business logic between different voltage levels and adopting split or single-level power outage fault analysis and judgment is not comprehensive enough. Using a single data source for power outage fault analysis and judgment can no longer achieve accurate fault location. Summary of the invention

[0005] One of the objectives of the present invention is to provide a distribution network real-time fault power outage monitoring method based on multi-source data fusion.

[0006] A second object of the present invention is to provide a system for implementing the distribution network real-time fault power outage monitoring method based on multi-source data fusion.

[0007] The present invention provides a distribution network real-time fault power outage monitoring method based on multi-source data fusion, comprising the following steps:

[0008] S1. Obtain distribution network data;

[0009] S2. According to the distribution network data obtained in step S1, the power meter, power user and distribution transformer relationship are associated and matched with the power outage and restoration data of the power meter to obtain the real-time power outage and restoration data of the user and the distribution transformer equipment;

[0010] S3. According to the real-time user outage and power restoration data obtained in step S2, the type of distribution transformer outage is judged to obtain the judgment result;

[0011] S4. Perform a authenticity judgment based on the judgment result obtained in step S3. If the power outage is true, a maintenance warning is issued to the corresponding area to complete the monitoring of the distribution network.

[0012] The distribution network data in step S1 includes power consumption meter data, distribution transformer interruption and power outage event data, distribution transformer current and voltage curve data, automation master station feeder outgoing line switch tripping data, automation master station feeder outgoing line switch protection signal data, circuit breaker branch switch tripping data and circuit breaker branch switch protection signal data.

[0013] Step S3 is specifically as follows: based on the real-time user and distribution transformer equipment power outage and restoration data obtained in step S2, the type of power outage in the distribution network is judged twice; the first judgment is whether the power outage belongs to a distribution transformer power outage; the second judgment is whether the power outage is a branch line power outage or a main line power outage; and the judgment result is obtained.

[0014] The first judgment specifically includes the following steps:

[0015] 1) Divide the time wheel and number the time periods according to the preset time;

[0016] 2) According to the time period number obtained in step 1), users with the same time period number and the same power outage time under the same distribution transformer are aggregated to obtain the number of faulty users x;

[0017] 3) Compare the number of faulty users x obtained in step 2) with the number of users y actually connected to the distribution transformer in the topological relationship: if the fault proportion x / y is greater than or equal to 75%, it is judged as a suspected distribution transformer power outage and enters the second judgment; if the fault proportion x / y is less than 75%, no second judgment is performed, but the proportion of faulty users in each phase is judged according to the distribution phase signal to which it belongs. If the proportion of single-phase faulty users is greater than or equal to 80%, it is judged that a power outage occurs in this phase of the distribution transformer, otherwise it is judged as a discrete user power outage.

[0018] The second judgment specifically includes the following steps:

[0019] A) Divide the time wheel and number it according to the preset time as a time period;

[0020] B) according to the time period number obtained in step A), the distribution transformers with the same power outage time and the same time period number are aggregated to obtain the number of faulty distribution transformers x';

[0021] C) Make a judgment based on the faulty variable x' obtained in step B):

[0022] If the faulty distribution variable x' is equal to 1 and the number of power outage faults occurring on that day is equal to 1, it is determined to be a single distribution single power outage;

[0023] If the fault distribution variable x' is equal to 1 and the fault number signal on that day is greater than 1, it is determined to be a single distribution with multiple power outages;

[0024] If the number of clusters under the same line is greater than 1 and the number of faulty distribution transformers under each cluster is equal to 1, it is determined to be a multiple distribution single power outage;

[0025] If the number of clusters under the same line is greater than 1, and the number of faulty distribution transformers under each cluster is greater than 2 and less than 80% of the number of actual connected distribution transformers on the line, it is determined to be a branch power outage;

[0026] If the number of clusters under the same line is equal to 1, and the number of faulty distribution transformers x' is greater than or equal to 80% of the actual number of distribution transformers connected to the line or x' is greater than or equal to 90% of the actual number of users covered by the line, it is determined that the entire line is out of power.

[0027] The authenticity judgment in step S4 is specifically as follows:

[0028] For a single-phase power outage or a discrete user power outage, the user fault authenticity is determined based on the user's real-time current and voltage curves at time interval t obtained in step S1. For a single-phase or discrete user whose three-phase current and voltage have not obtained real-time streaming data for two or more points, the results are matched with the judgment result obtained in step S3. If there is no data for the three-phase current and voltage after the power outage occurs, it is determined that the power outage is true, otherwise it is determined that the power outage is not true.

[0029] In the case where the power outage type is a distribution transformer power outage, the real-time current and voltage curves of the distribution transformer at the time interval t obtained in step S1 are used to determine the authenticity of the distribution transformer fault. For the distribution transformer where no real-time flow data of the three-phase current and voltage at two or more points are obtained continuously, the distribution transformer is matched with the judgment result obtained in step S3. If there is no data of the three-phase current and voltage after the power outage occurs, it is determined that the power outage is true, otherwise it is determined that the power outage is not true;

[0030] In the case of a branch line outage or a full line outage, each distribution line in the branch line or the full line is first judged according to the authenticity of the distribution transformer outage, and then the corresponding line 10kV circuit breaker branch switch tripping and protection signals are associated to perform double signal superposition and judgment. If the signal superposition matches successfully, it is judged that the power outage is true, otherwise it is judged that the power outage is not true;

[0031] The present invention also provides a system for implementing the distribution network real-time fault power outage monitoring method based on multi-source data fusion, comprising a data acquisition module, a data processing module, a power outage type judgment module, and a authenticity judgment module;

[0032] The data acquisition module acquires the distribution network data and uploads the data to the data processing module;

[0033] The data processing module associates the power meter, power users and distribution transformer relationship according to the received data, matches it with the power outage and restoration data of the power meter, obtains the real-time power outage and restoration data of the user, and uploads the data to the power outage type judgment module;

[0034] The power outage type judgment module judges the power outage type according to the received data, obtains the judgment result, and uploads the data to the authenticity judgment module;

[0035] The authenticity judgment module makes an authenticity judgment based on the received data. If the power outage is true, a maintenance warning is issued to the corresponding area to complete the monitoring of the distribution network.

[0036] The present invention discloses a distribution network real-time fault power outage monitoring method and system based on multi-source data fusion. The method of the present invention adopts bottom-up power outage scope judgment, which improves the accuracy and granularity of power outage scope judgment. The method of the present invention adopts different levels of signals for fusion analysis, and judges the authenticity of the power outage, which increases the authenticity of the early warning. The method of the present invention greatly improves the monitoring efficiency, can effectively assist the power outage repair work, and enhances the stability of the distribution network. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a schematic diagram of the process of the present invention;

[0038] Figure 2 It is a schematic diagram of the structure of the system of the present invention. DETAILED DESCRIPTION

[0039] The present invention provides a distribution network real-time fault power outage monitoring method based on multi-source data fusion, and its flow chart is as follows: Figure 1 As shown, the following steps are included:

[0040] S1. Obtain distribution network data;

[0041] The distribution network data includes electricity consumption collection energy meter data, distribution transformer interruption and power outage event data, distribution transformer current and voltage curve data, automation master station feeder outgoing line switch tripping data, automation master station feeder outgoing line switch protection signal data, circuit breaker branch switch tripping data and circuit breaker branch switch protection signal data.

[0042] S2. According to the distribution network data obtained in step S1, the power meter, power user and distribution transformer relationship are associated and matched with the power outage and restoration data of the power meter to obtain the real-time power outage and restoration data of the user and the distribution transformer equipment;

[0043] S3. According to the real-time user power outage and power restoration data obtained in step S2, the type of power outage in the distribution transformer is judged to obtain a judgment result, specifically: according to the real-time user and distribution transformer equipment power outage and power restoration data obtained in step S2, the type of power outage in the distribution network is judged twice; the first judgment is made as to whether the power outage belongs to a distribution transformer power outage; the second judgment is made as to whether the power outage is a branch line power outage or a main line power outage; and the judgment result is obtained.

[0044] The first judgment specifically includes the following steps:

[0045] 1) Divide the time wheel and number the time periods according to the preset time;

[0046] 2) According to the time period number obtained in step 1), users with the same time period number and the same power outage time under the same distribution transformer are aggregated to obtain the number of faulty users x;

[0047] 3) Compare the number of faulty users x obtained in step 2) with the number of users y actually connected to the distribution transformer in the topological relationship: if the fault proportion x / y is greater than or equal to 75%, it is judged as a suspected distribution transformer power outage and enters the second judgment; if the fault proportion x / y is less than 75%, no second judgment is performed, but the proportion of faulty users in each phase is judged according to the distribution phase signal to which it belongs. If the proportion of single-phase faulty users is greater than or equal to 80%, it is judged that a power outage occurs in this phase of the distribution transformer, otherwise it is judged as a discrete user power outage.

[0048] The second judgment specifically includes the following steps:

[0049] A) Divide the time wheel and number it according to the preset time as a time period;

[0050] B) according to the time period number obtained in step A), the distribution transformers with the same power outage time and the same time period number are aggregated to obtain the number of faulty distribution transformers x';

[0051] C) Make a judgment based on the faulty variable x' obtained in step B):

[0052] If the faulty distribution variable x' is equal to 1 and the number of power outage faults occurring on that day is equal to 1, it is determined to be a single distribution single power outage;

[0053] If the fault distribution variable x' is equal to 1 and the fault number signal on that day is greater than 1, it is determined to be a single distribution with multiple power outages;

[0054] If the number of clusters under the same line is greater than 1 and the number of faulty distribution transformers under each cluster is equal to 1, it is determined to be a multiple distribution single power outage;

[0055] If the number of clusters under the same line is greater than 1, and the number of faulty distribution transformers under each cluster is greater than 2 and less than 80% of the number of actual connected distribution transformers on the line, it is determined to be a branch power outage;

[0056] If the number of clusters under the same line is equal to 1, and the number of faulty distribution transformers x' is greater than or equal to 80% of the actual number of distribution transformers connected to the line or x' is greater than or equal to 90% of the actual number of users covered by the line, it is determined that the entire line is out of power.

[0057] S4. According to the judgment result obtained in step S3, a authenticity judgment is made. If the power outage is true, a maintenance warning is issued to the corresponding area to complete the monitoring of the distribution network;

[0058] The authenticity judgment is specifically as follows:

[0059] For a single-phase power outage or a discrete user power outage, the user fault authenticity is determined based on the user's real-time current and voltage curves at time interval t obtained in step S1. For a single-phase or discrete user whose three-phase current and voltage have not obtained real-time streaming data for two or more points, the results are matched with the judgment result obtained in step S3. If there is no data for the three-phase current and voltage after the power outage occurs, it is determined that the power outage is true, otherwise it is determined that the power outage is not true.

[0060] In the case where the power outage type is a distribution transformer power outage, the real-time current and voltage curves of the distribution transformer at the time interval t obtained in step S1 are used to determine the authenticity of the distribution transformer fault. For the distribution transformer where no real-time flow data of the three-phase current and voltage at two or more points are obtained continuously, the distribution transformer is matched with the judgment result obtained in step S3. If there is no data of the three-phase current and voltage after the power outage occurs, it is determined that the power outage is true, otherwise it is determined that the power outage is not true;

[0061] In the case of a branch line outage or a full line outage, each distribution line in the branch line or the full line is first judged according to the authenticity of the distribution transformer outage, and then the corresponding line 10kV circuit breaker branch switch tripping and protection signals are associated to perform double signal superposition and judgment. If the signal superposition matches successfully, it is judged that the power outage is true, otherwise it is judged that the power outage is not true;

[0062] The present invention also provides a system for implementing the distribution network real-time fault power outage monitoring method based on multi-source data fusion, comprising a data acquisition module, a data processing module, a power outage type judgment module, and a authenticity judgment module;

[0063] The data acquisition module acquires the distribution network data and uploads the data to the data processing module;

[0064] The data processing module associates the power meter, power users and distribution transformer relationship according to the received data, matches it with the power outage and restoration data of the power meter, obtains the real-time power outage and restoration data of the user, and uploads the data to the power outage type judgment module;

[0065] The power outage type judgment module judges the power outage type according to the received data, obtains the judgment result, and uploads the data to the authenticity judgment module;

[0066] The authenticity judgment module makes an authenticity judgment based on the received data. If the power outage is true, a maintenance warning is issued to the corresponding area to complete the monitoring of the distribution network.

Claims

1. A distribution network real-time fault power outage monitoring method based on multi-source data fusion, characterized in that: The following steps are involved: S1. Obtain distribution network data; S2. According to the distribution network data obtained in step S1, the power meter, power user and distribution transformer relationship are associated and matched with the power outage and restoration data of the power meter to obtain the real-time power outage and restoration data of the user and the distribution transformer equipment; S3. According to the real-time user outage and power restoration data obtained in step S2, the type of distribution transformer outage is judged to obtain the judgment result; S4. Perform a authenticity judgment based on the judgment result obtained in step S3. If the power outage is true, a maintenance warning is issued to the corresponding area to complete the monitoring of the distribution network.

2. The method for real-time fault and power outage monitoring of distribution network based on multi-source data fusion according to claim 1 is characterized in that: The distribution network data in step S1 includes power consumption meter data, distribution transformer interruption and power outage event data, distribution transformer current and voltage curve data, automation master station feeder outgoing line switch tripping data, automation master station feeder outgoing line switch protection signal data, circuit breaker branch switch tripping data and circuit breaker branch switch protection signal data.

3. The method for real-time fault and power outage monitoring of distribution network based on multi-source data fusion according to claim 2 is characterized in that: Step S3 specifically comprises: according to the real-time user and distribution transformer equipment power outage and restoration data obtained in step S2, the type of power outage in the distribution network is judged twice; the first judgment is whether the power outage belongs to the distribution transformer power outage; the second judgment is whether the power outage is a branch line power outage or a main line power outage; Get the judgment result.

4. The method for real-time fault and power outage monitoring of distribution network based on multi-source data fusion according to claim 3 is characterized in that: The first judgment specifically includes the following steps: 1) Divide the time wheel and number the time periods according to the preset time; 2) According to the time period number obtained in step 1), users with the same time period number and the same power outage time under the same distribution transformer are aggregated to obtain the number of faulty users x; 3) Compare the number of faulty users x obtained in step 2) with the number of users y actually connected to the distribution transformer in the topological relationship: if the fault proportion x / y is greater than or equal to 75%, it is judged as a suspected distribution transformer power outage and enters the second judgment; if the fault proportion x / y is less than 75%, no second judgment is performed, but the proportion of faulty users in each phase is judged according to the distribution phase signal to which it belongs. If the proportion of single-phase faulty users is greater than or equal to 80%, it is judged that a power outage occurs in this phase of the distribution transformer, otherwise it is judged as a discrete user power outage.

5. The method for real-time fault and power outage monitoring of distribution network based on multi-source data fusion according to claim 4 is characterized in that: The second judgment specifically includes the following steps: A) Divide the time wheel and number it according to the preset time as a time period; B) according to the time period number obtained in step A), the distribution transformers with the same power outage time and the same time period number are aggregated to obtain the number of faulty distribution transformers x'; C) Make a judgment based on the faulty variable x' obtained in step B): If the faulty distribution variable x' is equal to 1 and the number of power outage faults occurring on that day is equal to 1, it is determined to be a single distribution single power outage; If the fault distribution variable x' is equal to 1 and the fault number signal on that day is greater than 1, it is determined to be a single distribution with multiple power outages; If the number of clusters under the same line is greater than 1 and the number of faulty distribution transformers under each cluster is equal to 1, it is determined to be a multiple distribution single power outage; If the number of clusters under the same line is greater than 1, and the number of faulty distribution transformers under each cluster is greater than 2 and less than 80% of the number of actual connected distribution transformers on the line, it is determined to be a branch power outage; If the number of clusters under the same line is equal to 1, and the number of faulty distribution transformers x' is greater than or equal to 80% of the actual number of distribution transformers connected to the line or x' is greater than or equal to 90% of the actual number of users covered by the line, it is determined that the entire line is out of power.

6. The method for real-time fault and power outage monitoring of distribution network based on multi-source data fusion according to claim 5 is characterized in that: The authenticity judgment in step S4 is specifically as follows: for a power outage type of single-phase power outage or discrete user power outage, the authenticity of the user fault is judged according to the user's real-time current and voltage curve at the time interval t obtained in step S1. For a single-phase or discrete user whose three-phase current and voltage have not obtained real-time flow data at two or more points, the data is matched with the judgment result obtained in step S3. If there is no data for the three-phase current and voltage after the power outage occurs, it is judged that the power outage is true, otherwise it is judged that the power outage is not true. In the case where the power outage type is a distribution transformer power outage, the real-time current and voltage curves of the distribution transformer at the time interval t obtained in step S1 are used to determine the authenticity of the distribution transformer fault. For the distribution transformer where no real-time flow data of the three-phase current and voltage at two or more points are obtained continuously, the distribution transformer is matched with the judgment result obtained in step S3. If there is no data of the three-phase current and voltage after the power outage occurs, it is determined that the power outage is true, otherwise it is determined that the power outage is not true; For the case where the distribution transformer type is a branch line power outage or a full line power outage, first judge each distribution in the branch line or the full line according to the authenticity of the distribution transformer power outage, and then associate the corresponding line 10kV circuit breaker branch switch tripping and protection signal, and perform double signal superposition judgment. If the signal superposition matches successfully, it is judged that the power outage is true, otherwise it is judged that the power outage is not true.

7. A method for real-time fault and power outage monitoring of distribution network based on multi-source data fusion according to any one of claims 1 to 6, characterized in that: It includes a data acquisition module, a data processing module, a power outage type judgment module, and a authenticity judgment module; The data acquisition module acquires the distribution network data and uploads the data to the data processing module; The data processing module associates the power meter, power users and distribution transformer relationship according to the received data, matches it with the power outage and restoration data of the power meter, obtains the real-time power outage and restoration data of the user, and uploads the data to the power outage type judgment module; The power outage type judgment module judges the power outage type according to the received data, obtains the judgment result, and uploads the data to the authenticity judgment module; The authenticity judgment module makes an authenticity judgment based on the received data. If the power outage is true, a maintenance warning is issued to the corresponding area to complete the monitoring of the distribution network.

Images