CN111082401A - Self-learning mechanism-based power distribution network fault recovery method - Google Patents
Self-learning mechanism-based power distribution network fault recovery method Download PDFInfo
- Publication number
- CN111082401A CN111082401A CN201911116644.6A CN201911116644A CN111082401A CN 111082401 A CN111082401 A CN 111082401A CN 201911116644 A CN201911116644 A CN 201911116644A CN 111082401 A CN111082401 A CN 111082401A
- Authority
- CN
- China
- Prior art keywords
- fault
- similarity
- network
- scheme
- self
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02H—EMERGENCY PROTECTIVE CIRCUIT ARRANGEMENTS
- H02H7/00—Emergency protective circuit arrangements specially adapted for specific types of electric machines or apparatus or for sectionalised protection of cable or line systems, and effecting automatic switching in the event of an undesired change from normal working conditions
- H02H7/26—Sectionalised protection of cable or line systems, e.g. for disconnecting a section on which a short-circuit, earth fault, or arc discharge has occured
- H02H7/261—Sectionalised protection of cable or line systems, e.g. for disconnecting a section on which a short-circuit, earth fault, or arc discharge has occured involving signal transmission between at least two stations
- H02H7/262—Sectionalised protection of cable or line systems, e.g. for disconnecting a section on which a short-circuit, earth fault, or arc discharge has occured involving signal transmission between at least two stations involving transmissions of switching or blocking orders
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02H—EMERGENCY PROTECTIVE CIRCUIT ARRANGEMENTS
- H02H3/00—Emergency protective circuit arrangements for automatic disconnection directly responsive to an undesired change from normal electric working condition with or without subsequent reconnection ; integrated protection
- H02H3/02—Details
- H02H3/06—Details with automatic reconnection
- H02H3/066—Reconnection being a consequence of eliminating the fault which caused disconnection
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Abstract
The invention discloses a power distribution network fault recovery method based on a self-learning mechanism, wherein when a power grid normally operates, expected accident simulation is carried out according to a risk evaluation result, and a self-learning database based on an accident plan and a historical fault recovery scheme is further constructed; after the fault occurs, extracting fault characteristics, calculating the similarity between the current fault and the stored fault in the database, and sequencing the current fault and the stored fault in the database from high to low; and rapidly and reliably realizing the task of power supply recovery by using the power supply recovery scheme matched with the similar fault. The invention converts the traditional complex and time-consuming online optimization problem into the similarity evaluation problem of the limited fault state, greatly reduces the real-time calculation amount while ensuring the quality of the fault recovery scheme, thereby improving the power supply recovery decision speed and the scheme performance and upgrading the power supply recovery system into an intelligent control system with self-learning, self-perfection and continuous evolution capabilities.
Description
Technical Field
The invention relates to a power distribution network fault recovery method based on a self-learning mechanism, and belongs to the field of power system automation and power distribution network fault recovery.
Background
The distribution network in the power system undertakes the task of distributing electric energy to thousands of households, the power supply reliability and the electric energy quality of power consumers are directly influenced, along with the development of social economy and the continuous improvement of living standard, the improvement of the power supply reliability of the distribution network is widely regarded, the power supply recovery is used as the core function of self-healing control of the intelligent distribution network, the power supply transfer of power loss loads is completed through network reconstruction after system faults, and the method has important significance for improving the power supply reliability of the power grid.
The power supply recovery of a power distribution network needs to comprehensively consider factors such as power loss load, switching action times, load balance, voltage quality, network loss and the like, is a multi-target multi-constraint nonlinear combined optimization problem, most of the existing researches adopt an online decision power supply recovery mode, and a large number of solution algorithms with high speed and excellent performance are promoted, wherein a hybrid algorithm has the advantages of different algorithms and has good global optimization tendency and convergence speed, more and more learners adopt the hybrid algorithm to solve the power supply recovery problem, such as cycle 28278and the like (cycle , coma solving, Zhengbain, and the like; power distribution network fault reconstruction based on the hybrid algorithm is matched with island operation [ J ] power grid technology, 2015,39(1):136 and 142 ]) to bring the power failure load after power failure division into a target function, and a recovery strategy for realizing reasonable matching of network reconstruction and island division based on a binary particle swarm and a differential evolution hybrid algorithm is provided, for example, Huan jiajia et al (Huan jiajia, huangshao, huangshaoshao, application of ant colony algorithm based on immune principle in power distribution network recovery [ J ]. power system protection and control, 2008, 17: 41-44.) aiming at the problem that the ant colony algorithm is easy to fall into local optimum and difficult to converge, a selection mechanism and a diversity strategy of antibody concentration in the immune algorithm are introduced, the global search capability of the ant colony algorithm is enhanced, and the early maturing of the algorithm is effectively prevented.
For the same network, the topological structure, the operation mode and the fault condition of the same network have high similarity at different moments, the power supply recovery scheme of similar faults is reasonably selected and utilized, and the power supply recovery decision speed and the scheme quality can be greatly improved.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the method overcomes the defects of the prior art, can overcome the defects of low speed and poor scheme performance of the traditional online decision-making mode, and can effectively utilize the processing experience of expected accidents and similar historical faults, thereby providing the power distribution network fault recovery method based on the self-learning mechanism.
The technical scheme adopted by the invention for solving the technical problem is as follows:
a power distribution network fault recovery method based on a self-learning mechanism comprises the following steps:
the method comprises the following steps: constructing a self-learning database; when the power distribution network normally operates, an expected accident set is reasonably formulated according to a risk evaluation result, and expected accident simulation is sequentially carried out on high-risk equipment and positions according to the sequence of risks from high to low, so that a self-learning database based on the expected accident simulation and a historical fault processing scheme is constructed, and a power transfer scheme with similar faults can be directly utilized after the faults occur;
step two: similar fault state evaluation and matching; after the fault occurs, extracting the current network fault characteristics, and sequentially calculating the network topology similarity and the load distribution similarity of the current fault and the storage fault in the database so as to obtain the similarity of the current fault and the storage fault;
step three: generating a fault recovery scheme; and sequentially verifying whether the power supply switching scheme for storing the faults is suitable for the current fault condition according to the sequence of similarity from large to small, and if various constraint conditions are met, executing the power supply switching scheme for similar faults to quickly finish the task of power supply recovery.
In the first step, the self-learning database is constructed and comprises two parts of an expected accident simulation scheme and a historical fault processing scheme:
(1) expected accident simulation
The process of the expected accident simulation based on risk assessment is as follows:
step 1: under a normal state, carrying out risk assessment on the network operation state, and searching for the vulnerability with the highest risk level or the most prone to failure;
step 2: sorting different positions and equipment of the system from big to small according to risk degrees, and determining an expected accident set;
step 3: preferentially formulating a fault recovery scheme of the high-risk equipment by adopting an MOPSO algorithm, and providing a record for rapidly recovering power supply after a fault;
(2) historical fault handling scheme
In an actual power distribution network, the same equipment may fail for multiple times at different moments, when the network structure and the load level are similar, the fault characteristics and the power supply recovery scheme at the same position have high similarity, and after the power distribution network finishes transferring power, the fault information and the corresponding processing scheme are stored in the self-learning database every time, so that guidance can be provided for subsequent fault recovery.
The information stored in the database includes: network structure before failure, load distribution, failure conditions (location of failure, loss of power condition), and final power restoration scheme.
In the second step, the load distribution before the fault of the power distribution network reflects the power consumption demand of the user, and the power consumption demand can not change in a large scale in a short time before and after the fault, so that the load demand after the fault recovery is the same as that before the fault; the load distribution is represented by the line current, and then the Load Distribution Similarity (LDS) evaluation function is:
wherein I and L represent load distribution sequences of different states, and b is the number of lines
The singular value sequence of the power distribution network adjacency matrix and the network topological structure are corresponding to each other, and the topological structure same as the original network can be obtained after dimensionality reduction, compression and reconstruction processing are carried out on the singular value sequence, so that the singular value sequence of the network adjacency matrix can be used as a topological similarity evaluation index;
the network topology similarity evaluation function is defined as that the distance between two network singular value sequences is reciprocal to measure, namely the closer the distance between the singular value sequences is, the higher the similarity is, and two n-dimensional singular value sequences X are set as (X)1,x2,…xn) And Y ═ Y1,y2,…yn) Then, the Network Topology Similarity (NTS) evaluation formula is:
in the formula, k represents that only the front k dimension of the sequence is taken for similarity evaluation, and the value is determined according to the actual network and the sequence dimension.
In the second step, on the basis of analyzing the similarity of the network structure and the load distribution, a linear weighting method is used for establishing a fault similarity evaluation function (SIM), and the calculation formula is as follows:
SIM＝k1NTS+k2LDS (3)
in the formula, NTS is network topology similarity, LDS is load distribution similarity, k1And k2Are the weights of the two, respectively, and k1+k2＝1。
In the third step, after the fault similarity evaluation is completed, the power supply conversion is completed by using a similar fault recovery scheme, and the specific steps are as follows:
step 1: calculating a fault similarity SIM after a fault occurs, and generating a fault similarity arrangement vector SIM (n-dimensional vector) in a descending order, wherein i is 0;
step 2: enabling i to be i +1, judging whether i is smaller than n, and if so, continuing the next step; otherwise, outputting no similar fault, and returning to finish;
step 3: judging whether sim (i) is more than 0.8, if so, continuing the next step; otherwise, the database has no similar network state, and the end is returned;
step 4: selecting a power supply recovery scheme when the same position in the network i fails as a scheme i; step 5: judging whether the scheme i meets the trend requirement, if so, executing the scheme; otherwise, return to Step3 for continued execution.
The invention has the following positive beneficial effects:
the invention provides a power distribution network power supply recovery method based on a self-learning mechanism, which directly utilizes a power transfer scheme of similar expected accidents and historical faults by evaluating and matching similar fault states after faults and converting a complex and time-consuming online optimization problem into a similarity evaluation problem of a limited number of network states, thereby quickly and reliably completing a power supply recovery task and upgrading a power distribution network power supply recovery system into an intelligent system with self-learning, self-perfecting and continuous evolution capabilities.
Drawings
FIG. 1 is a schematic flow chart of a power distribution network fault recovery method based on a self-learning mechanism according to the present invention;
FIG. 2 is a flow chart of expected accident simulation in the method for recovering the fault of the power distribution network based on the self-learning mechanism;
fig. 3 is a system diagram of IEEE33 nodes in the present invention.
Detailed Description
The invention will be further explained and explained with reference to the accompanying drawings, fig. 1, fig. 2, fig. 3 and the specific embodiments:
a power distribution network fault recovery method based on a self-learning mechanism comprises the following steps:
the method comprises the following steps: constructing a self-learning database; when the power distribution network normally operates, an expected accident set is reasonably formulated according to a risk evaluation result, and expected accident simulation is sequentially carried out on high-risk equipment and positions according to the sequence of risks from high to low, so that a self-learning database based on the expected accident simulation and a historical fault processing scheme is constructed, and a power transfer scheme with similar faults can be directly utilized after the faults occur;
step two: similar fault state evaluation and matching; after the fault occurs, extracting the current network fault characteristics, and sequentially calculating the network topology similarity and the load distribution similarity of the current fault and the storage fault in the database so as to obtain the similarity of the current fault and the storage fault;
step three: generating a fault recovery scheme; and sequentially verifying whether the power supply switching scheme for storing the faults is suitable for the current fault condition according to the sequence of similarity from large to small, and if various constraint conditions are met, executing the power supply switching scheme for similar faults to quickly finish the task of power supply recovery.
In the first step, the self-learning database is constructed and comprises two parts of an expected accident simulation scheme and a historical fault processing scheme:
(1) expected accident simulation
The process of the expected accident simulation based on risk assessment is as follows:
step 1: under a normal state, carrying out risk assessment on the network operation state, and searching for the vulnerability with the highest risk level or the most prone to failure;
step 2: sorting different positions and equipment of the system from big to small according to risk degrees, and determining an expected accident set;
step 3: preferentially formulating a fault recovery scheme of the high-risk equipment by adopting an MOPSO algorithm, and providing a record for rapidly recovering power supply after a fault;
(2) historical fault handling scheme
In an actual power distribution network, the same equipment may fail for multiple times at different moments, when the network structure and the load level are similar, the fault characteristics and the power supply recovery scheme at the same position have high similarity, and after the power distribution network finishes transferring power, the fault information and the corresponding processing scheme are stored in the self-learning database every time, so that guidance can be provided for subsequent fault recovery.
In the second step, the load distribution before the fault of the power distribution network reflects the power consumption demand of the user, and the power consumption demand can not change in a large scale in a short time before and after the fault, so that the load demand after the fault recovery is the same as that before the fault; the load distribution is represented by the line current, and then the Load Distribution Similarity (LDS) evaluation function is:
wherein I and L represent load distribution sequences of different states, and b is the number of lines
The singular value sequence of the power distribution network adjacency matrix and the network topological structure are corresponding to each other, and the topological structure same as the original network can be obtained after dimensionality reduction, compression and reconstruction processing are carried out on the singular value sequence, so that the singular value sequence of the network adjacency matrix can be used as a topological similarity evaluation index;
the network topology similarity evaluation function is defined as that the distance between two network singular value sequences is reciprocal to measure, namely the closer the distance between the singular value sequences is, the higher the similarity is, and two n-dimensional singular value sequences X are set as (X)1,x2,…xn) And Y ═ Y1,y2,…yn) Then, the Network Topology Similarity (NTS) evaluation formula is:
in the formula, k represents that only the front k dimension of the sequence is taken for similarity evaluation, and the value is determined according to the actual network and the sequence dimension.
In the second step, on the basis of analyzing the similarity of the network structure and the load distribution, a linear weighting method is used for establishing a fault similarity evaluation function (SIM), and the calculation formula is as follows:
SIM＝k1NTS+k2LDS (3)
in the formula, NTS is network topology similarity, LDS is load distribution similarity, k1And k2Are the weights of the two, respectively, and k1+k2＝1。
In the third step, after the fault similarity evaluation is completed, the power supply conversion is completed by using a similar fault recovery scheme, and the specific steps are as follows:
step 1: calculating a fault similarity SIM after a fault occurs, and generating a fault similarity arrangement vector SIM (n-dimensional vector) in a descending order, wherein i is 0;
step 2: enabling i to be i +1, judging whether i is smaller than n, and if so, continuing the next step; otherwise, outputting no similar fault, and returning to finish;
step 3: judging whether sim (i) is more than 0.8, if so, continuing the next step; otherwise, the database has no similar network state, and the end is returned;
step 4: selecting a power supply recovery scheme when the same position in the network i fails as a scheme i;
step 5: judging whether the scheme i meets the trend requirement, if so, executing the scheme; otherwise, return to Step3 for continued execution.
In the following, the present invention is described by way of example with reference to the IEEE33 node power distribution network simulation model shown in fig. 3, where the system has 33 load nodes, 37 lines (divided into 32 sectionalizing switches and 5 tie switches), and distributed power sources with capacities of 300kW, 500kW and 500kW are connected to nodes 13, 18 and 31, respectively, and the load classification conditions are shown in table 1:
TABLE 1 System load rating situation
(1) Assuming that the line 4 has a fault, the topological similarity between the 9 networks and the original network is calculated, and the result after the normalization processing is shown in table 2:
TABLE 2 topological similarity between similar and original networks
(2) The load distribution similarity between the different load levels and the original load level in each network structure was calculated, and the calculation results were normalized and shown in table 3.
TABLE 3 load distribution similarity under different load demands
(3) Substituting into formula (3), the weight coefficient is set to k1＝0.6，k2The failure similarity under different networks and different load requirements was calculated as 0.4, and the results are shown in table 4.
TABLE 4 Fault similarity for different networks and different load demands
As can be seen from table 4, the similarity of the network 1 and the network 3 at the above 5 load levels is greater than 0.8, and the failure recovery schemes have reference values.
(4) And sorting the states with the similarity SIM being greater than 0.8 in the table from large to small, and verifying whether the fault recovery scheme meets the conditions one by one. The power restoration scheme for line 4 failure at the "1/4-" load level for network 1 is preferably selected, with the results shown in table 5.
Table 5 similar failure recovery scheme verification
As can be seen from table 5, the network 1 has 5 power restoration schemes with the line 4 failed at the load level of "1/4", and all satisfy the power flow requirement, so that the power restoration scheme can be used for power restoration of the current failure.
According to the method, the similarity between the current fault and the stored fault in the database is calculated and sequenced by using a similar fault state evaluation and matching method, and a power supply recovery task is quickly and reliably completed by using a similar expected accident and historical fault processing scheme; the power supply recovery decision based on the self-learning mechanism is characterized in that the traditional complex time-consuming online optimization problem is converted into the similarity evaluation problem of a limited network state by learning and referring to a similar fault processing scheme, the scheme quality is guaranteed, and the real-time calculation amount is greatly reduced, so that the power supply recovery decision speed and the scheme performance are improved. The introduction of a self-learning mechanism upgrades the power supply recovery system into an intelligent control system with self-learning, self-perfecting and continuous evolution capabilities.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention in any way, and all simple modifications, equivalent variations and modifications made to the above embodiment according to the technical spirit of the present invention are within the scope of the technical solution of the present invention.
Claims (5)
1. A power distribution network fault recovery method based on a self-learning mechanism is characterized by comprising the following steps:
the method comprises the following steps: constructing a self-learning database; when the power distribution network normally operates, an expected accident set is reasonably formulated according to a risk evaluation result, and expected accident simulation is sequentially carried out on high-risk equipment and positions according to the sequence of risks from high to low, so that a self-learning database based on the expected accident simulation and a historical fault processing scheme is constructed, and a power transfer scheme with similar faults can be directly utilized after the faults occur;
step two: similar fault state evaluation and matching; after the fault occurs, extracting the current network fault characteristics, and sequentially calculating the network topology similarity and the load distribution similarity of the current fault and the storage fault in the database so as to obtain the similarity of the current fault and the storage fault;
step three: generating a fault recovery scheme; and sequentially verifying whether the power supply switching scheme for storing the faults is suitable for the current fault condition according to the sequence of similarity from large to small, and if various constraint conditions are met, executing the power supply switching scheme for similar faults to quickly finish the task of power supply recovery.
2. The method for recovering the power distribution network fault based on the self-learning mechanism as claimed in claim 1, wherein: in the first step, the self-learning database is constructed and comprises two parts of an expected accident simulation scheme and a historical fault processing scheme:
(1) expected accident simulation
The process of the expected accident simulation based on risk assessment is as follows:
step 1: under a normal state, carrying out risk assessment on the network operation state, and searching for the vulnerability with the highest risk level or the most prone to failure;
step 2: sorting different positions and equipment of the system from big to small according to risk degrees, and determining an expected accident set;
step 3: preferentially formulating a fault recovery scheme of the high-risk equipment by adopting an MOPSO algorithm, and providing a record for rapidly recovering power supply after a fault;
(2) historical fault handling scheme
In an actual power distribution network, the same equipment may fail for multiple times at different moments, when the network structure and the load level are similar, the fault characteristics and the power supply recovery scheme at the same position have high similarity, and after the power distribution network finishes transferring power, the fault information and the corresponding processing scheme are stored in the self-learning database every time, so that guidance can be provided for subsequent fault recovery.
3. The method for recovering the power distribution network fault based on the self-learning mechanism as claimed in claim 1, wherein: in the second step, the load distribution before the fault of the power distribution network reflects the power consumption demand of the user, and the power consumption demand can not change in a large scale in a short time before and after the fault, so that the load demand after the fault recovery is the same as that before the fault; the load distribution is represented by the line current, and then the Load Distribution Similarity (LDS) evaluation function is:
wherein I and L represent load distribution sequences of different states, and b is the number of lines
The singular value sequence of the power distribution network adjacency matrix and the network topological structure are corresponding to each other, and the topological structure same as the original network can be obtained after dimensionality reduction, compression and reconstruction processing are carried out on the singular value sequence, so that the singular value sequence of the network adjacency matrix can be used as a topological similarity evaluation index;
the network topology similarity evaluation function is defined as that the distance between two network singular value sequences is reciprocal to measure, namely the closer the distance between the singular value sequences is, the higher the similarity is, and two n-dimensional singular value sequences X are set as (X)1,x2,…xn) And Y ═ Y1,y2,…yn) Then, the Network Topology Similarity (NTS) evaluation formula is:
in the formula, k represents that only the front k dimension of the sequence is taken for similarity evaluation, and the value is determined according to the actual network and the sequence dimension.
4. The method for recovering the power distribution network fault based on the self-learning mechanism as claimed in claim 3, wherein: in the second step, on the basis of analyzing the similarity of the network structure and the load distribution, a linear weighting method is used for establishing a fault similarity evaluation function (SIM), and the calculation formula is as follows:
SIM＝k1NTS+k2LDS (3)
in the formula, NTS is network topology similarity, LDS is load distribution similarity, k1And k2Are the weights of the two, respectively, and k1+k2＝1。
5. The method for recovering the power distribution network fault based on the self-learning mechanism as claimed in claim 1, wherein: in the third step, after the fault similarity evaluation is completed, the power supply conversion is completed by using a similar fault recovery scheme, and the specific steps are as follows:
step 1: calculating a fault similarity SIM after a fault occurs, and generating a fault similarity arrangement vector SIM (n-dimensional vector) in a descending order, wherein i is 0;
step 2: enabling i to be i +1, judging whether i is smaller than n, and if so, continuing the next step; otherwise, outputting no similar fault, and returning to finish;
step 3: judging whether sim (i) is more than 0.8, if so, continuing the next step; otherwise, the database has no similar network state, and the end is returned;
step 4: selecting a power supply recovery scheme when the same position in the network i fails as a scheme i;
step 5: judging whether the scheme i meets the trend requirement, if so, executing the scheme; otherwise, return to Step3 for continued execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911116644.6A CN111082401B (en) | 2019-11-15 | 2019-11-15 | Self-learning mechanism-based power distribution network fault recovery method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911116644.6A CN111082401B (en) | 2019-11-15 | 2019-11-15 | Self-learning mechanism-based power distribution network fault recovery method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111082401A true CN111082401A (en) | 2020-04-28 |
| CN111082401B CN111082401B (en) | 2022-07-08 |
Family
ID=70311116
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911116644.6A Active CN111082401B (en) | 2019-11-15 | 2019-11-15 | Self-learning mechanism-based power distribution network fault recovery method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111082401B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112467686A (en) * | 2020-11-04 | 2021-03-09 | 深圳供电局有限公司 | Power distribution network fault recovery method and device, control equipment and storage medium |
| CN112865090A (en) * | 2021-01-30 | 2021-05-28 | 上海电力大学 | Intelligent power distribution network fault recovery method based on organism immunity mechanism |
| CN113052473A (en) * | 2021-03-31 | 2021-06-29 | 贵州电网有限责任公司 | Power grid risk analysis method based on fault rate and static safety analysis |
| WO2022083540A1 (en) * | 2020-10-20 | 2022-04-28 | 华为技术有限公司 | Method, apparatus, and system for determining fault recovery plan, and computer storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101958536A (en) * | 2010-09-20 | 2011-01-26 | 中国电力科学研究院 | Distribution network failure isolation and quick power service restoration decision support system |
| CN103944162A (en) * | 2014-04-15 | 2014-07-23 | 国网辽宁省电力有限公司沈阳供电公司 | Power distribution network fault recovery method based on real-time contingency sets |
| CN109474067A (en) * | 2018-08-14 | 2019-03-15 | 国网浙江省电力有限公司湖州供电公司 | A kind of dispatching of power netwoks troubleshooting aid decision-making method |
| CN109729175A (en) * | 2019-01-22 | 2019-05-07 | 中国人民解放军国防科技大学 | Edge cooperative data unloading method under unstable channel condition |
| US20190305589A1 (en) * | 2016-11-10 | 2019-10-03 | China Electric Power Research Institute Company Limited | Distribution network risk identification system and method and computer storage medium |
-
2019
- 2019-11-15 CN CN201911116644.6A patent/CN111082401B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101958536A (en) * | 2010-09-20 | 2011-01-26 | 中国电力科学研究院 | Distribution network failure isolation and quick power service restoration decision support system |
| CN103944162A (en) * | 2014-04-15 | 2014-07-23 | 国网辽宁省电力有限公司沈阳供电公司 | Power distribution network fault recovery method based on real-time contingency sets |
| US20190305589A1 (en) * | 2016-11-10 | 2019-10-03 | China Electric Power Research Institute Company Limited | Distribution network risk identification system and method and computer storage medium |
| CN109474067A (en) * | 2018-08-14 | 2019-03-15 | 国网浙江省电力有限公司湖州供电公司 | A kind of dispatching of power netwoks troubleshooting aid decision-making method |
| CN109729175A (en) * | 2019-01-22 | 2019-05-07 | 中国人民解放军国防科技大学 | Edge cooperative data unloading method under unstable channel condition |
Non-Patent Citations (1)
| Title |
|---|
| 郭晓斌: "基于拓扑相似性分析的配电网网架可靠性评估", 《高电压技术》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022083540A1 (en) * | 2020-10-20 | 2022-04-28 | 华为技术有限公司 | Method, apparatus, and system for determining fault recovery plan, and computer storage medium |
| EP4221004A4 (en) * | 2020-10-20 | 2024-02-21 | Huawei Tech Co Ltd | Method, apparatus, and system for determining fault recovery plan, and computer storage medium |
| CN112467686A (en) * | 2020-11-04 | 2021-03-09 | 深圳供电局有限公司 | Power distribution network fault recovery method and device, control equipment and storage medium |
| CN112467686B (en) * | 2020-11-04 | 2023-09-01 | 深圳供电局有限公司 | Power distribution network fault recovery method, device, control equipment and storage medium |
| CN112865090A (en) * | 2021-01-30 | 2021-05-28 | 上海电力大学 | Intelligent power distribution network fault recovery method based on organism immunity mechanism |
| CN112865090B (en) * | 2021-01-30 | 2023-09-26 | 上海电力大学 | Intelligent power distribution network fault recovery method based on organism immune mechanism |
| CN113052473A (en) * | 2021-03-31 | 2021-06-29 | 贵州电网有限责任公司 | Power grid risk analysis method based on fault rate and static safety analysis |
| CN113052473B (en) * | 2021-03-31 | 2024-03-22 | 贵州电网有限责任公司 | Power grid risk analysis method based on fault rate and static safety analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111082401B (en) | 2022-07-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111082401B (en) | Self-learning mechanism-based power distribution network fault recovery method | |
| CN112217202B (en) | Distributed new energy, energy storage and power distribution network planning method considering flexibility investment | |
| CN107516170B (en) | Difference self-healing control method based on equipment failure probability and power grid operation risk | |
| CN110969347B (en) | Power transmission network structure morphology assessment method | |
| CN103324980A (en) | Wind power station wind speed prediction method | |
| CN110837915B (en) | Low-voltage load point prediction and probability prediction method for power system based on hybrid integrated deep learning | |
| CN111551825B (en) | Self-adaptive power distribution network fault positioning method based on fault current path | |
| CN111191918A (en) | Service route planning method and device for smart power grid communication network | |
| CN105512783A (en) | Comprehensive evaluation method used for loop-opening scheme of electromagnetic looped network | |
| CN104123684A (en) | Power distribution network economy reconstructing method considering network loss and reliability | |
| WO2023005700A1 (en) | Model-data-hybrid-driven electrical grid reliability rapid calculation method and device | |
| CN110910026B (en) | Cross-provincial power transmission line loss intelligent management and decision method and system | |
| CN111654392A (en) | Low-voltage distribution network topology identification method and system based on mutual information | |
| CN113468745B (en) | Method and system for rapidly evaluating reliability of power distribution network based on historical faults | |
| Grigoras et al. | Energy losses estimation in electrical distribution networks with a decision trees-based algorithm | |
| CN108122054B (en) | Graph calculation-based real-time calculation method for topology of power system | |
| CN113627655B (en) | Method and device for simulating and predicting pre-disaster fault scene of power distribution network | |
| CN110571791B (en) | Optimal configuration method for power transmission network planning under new energy access | |
| CN111092425B (en) | Net rack clustering analysis method and system based on topological characteristics | |
| Kaiyuan et al. | Reliability study for distribution network considering adverse weather | |
| CN111784086A (en) | Power supply scheme evaluation method and system for direct-current power distribution and utilization system | |
| Yin et al. | Prediction of Distribution Network Line Loss Based on Grey Relation Analysis and XGboost | |
| CN110175413B (en) | Power distribution network reconstruction method and device based on R2 index multi-target particle swarm algorithm | |
| CN112446521B (en) | Multi-objective planning method for wind power plant access system considering economy and safety | |
| CN109598330B (en) | Minimum collision set method considering topology characteristics of power distribution network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |