CN117575537B - Distribution network power failure plan management system and method - Google Patents
Distribution network power failure plan management system and method Download PDFInfo
- Publication number
- CN117575537B CN117575537B CN202311729084.8A CN202311729084A CN117575537B CN 117575537 B CN117575537 B CN 117575537B CN 202311729084 A CN202311729084 A CN 202311729084A CN 117575537 B CN117575537 B CN 117575537B
- Authority
- CN
- China
- Prior art keywords
- power
- node
- power outage
- module
- power failure
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims description 18
- 238000012546 transfer Methods 0.000 claims abstract description 53
- 238000012423 maintenance Methods 0.000 claims abstract description 27
- 238000007726 management method Methods 0.000 claims abstract description 21
- 238000012544 monitoring process Methods 0.000 claims abstract description 15
- 239000013598 vector Substances 0.000 claims description 57
- 239000011159 matrix material Substances 0.000 claims description 19
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000013507 mapping Methods 0.000 claims description 12
- 238000012937 correction Methods 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 230000005283 ground state Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a distribution network power failure plan management system and a distribution network power failure plan management method, which relate to the technical field of power distribution management and comprise the following steps: the power grid monitoring system comprises a terminal data platform, a power outage area identification module, a transfer strategy generation module and a real-time monitoring module, wherein the real-time monitoring module monitors current real-time data of a power grid and sends the current real-time data to the terminal data platform for storage; the terminal data platform stores data, and simultaneously receives and overhauls and displays a power failure plan; the power outage area identification module establishes a power grid topology model according to the maintenance plan of the terminal data platform and the stored data, and identifies the power outage area by detecting power outage nodes; the power failure strategy generation module generates an optimal power failure plan according to the power failure nodes corresponding to the power failure area, and transmits the optimal power failure plan to the terminal data platform for display.
Description
Technical Field
The invention relates to the technical field of power distribution management, in particular to a power distribution network power failure plan management system and method.
Background
At present, as the economy is changed from high-speed development to a new stage of high-quality development, the requirements of society on power supply reliability are higher and higher. The power outage time is reduced, the electricity consumption experience of a user is improved, and the electricity consumption business environment is optimized, so that the power supply enterprise has a great challenge, and higher requirements are also provided for the management level of the power supply enterprise. On one hand, the power supply enterprises must strengthen the construction of the grid frame, and on the other hand, the power supply enterprises start from comprehensive power failure, so that the influence caused by planned power failure is reduced.
However, the power outage overhaul needs to make a scientific and reasonable power outage plan. At present, a power outage plan is manually established, and because of information barriers among various departments and various operation teams, effective communication and information exchange are lacked when the power outage plan is established, so that repeated power outage arrangements can exist when power outage plans of different departments and teams are arranged; at the same time, a designer typically makes a plurality of outage plans, compares and selects the best outage plan to implement. But the formulator typically starts from its actual business needs when making the selection. When the power outage plans of the main distribution network are coordinated, mutual exclusivity and coordination between equipment power outage time optimization and overhaul risks are considered. How to consider the outage time and the maintenance risk at the same time and generate an optimal outage plan becomes a problem to be solved urgently.
Disclosure of Invention
In view of the above, the invention provides a distribution network power outage plan management system and a distribution network power outage plan management method, which are used for improving the circulation efficiency of the processes of reporting, approving, issuing and the like of a power outage plan by carrying out informatization collection, automatic summarization, intelligent balance and risk assessment on the maintenance plan.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
A distribution network outage plan management system, comprising: the power grid monitoring system comprises a terminal data platform, a power outage area identification module, a transfer strategy generation module and a real-time monitoring module, wherein the real-time monitoring module monitors current real-time data of a power grid and sends the current real-time data to the terminal data platform for storage; the terminal data platform stores the real-time data, the historical transfer data and the section data, and simultaneously receives and displays the published maintenance plan and the published power failure plan in real time; the power outage area identification module establishes a power grid topology model according to an overhaul plan issued by the terminal data platform and stored data, and identifies the power outage area by detecting power outage nodes; and the transfer strategy generation module generates an optimal transfer strategy according to the transfer node of the power outage area corresponding to the power outage node, and transmits the optimal transfer strategy to the terminal data platform for display, wherein the optimal transfer strategy is the power outage plan.
Preferably, the power outage area identification module specifically includes:
The model building module is used for building a power grid topology model according to the section data, the real-time data and the nodes needing to be overhauled in the overhauling plan;
The equation construction module is used for constructing a Newton-Laportson method power flow calculation equation of the power grid topological model, solving partial derivatives of the power flow calculation equation, constructing a Jacobian matrix and constructing an unbalance amount; meanwhile, defining a correction equation, setting a convergence condition, converging the Newton-Laporton method power flow calculation equation, outputting the voltage of each node when the convergence condition is reached, and re-entering an equation construction module when the convergence condition is not reached;
The node selection module is used for evaluating the influence of the electric equipment maintenance on the full-power-grid ground state power flow according to the change condition of the voltage of each node before and after the connection of the maintenance equipment, the change of the node load rate after the maintenance and the change of the node load rate before and after the maintenance acquired in the power-grid topology model, setting an influence threshold value, and when the influence exceeds the influence threshold value, bringing the node into a power failure node;
And the power outage area determining module is used for setting a power outage event identifier according to the power outage node and the power grid topology model and further determining the power outage area.
Preferably, the power outage area determining module specifically includes:
the data acquisition module acquires the power grid topological model and sends the power grid topological model to the range determination module;
The identification module is used for acquiring the power failure node, setting a power failure event identification, and sending the power failure event identification of the power failure node to the range determination module;
The range determining module is used for receiving the power outage event identification of the power outage node sent by the data acquisition module and the power outage node sent by the identification module, and adding the power outage event identification of the power outage node in the given range of the maintenance plan to the node corresponding to the power outage node in the power grid topology model; based on a preset blackout event rule, determining an influence node range which is influenced by the blackout event corresponding to the blackout event, starting from the current node of the power grid topology model to the end node, and executing the following processes for each node added with the blackout event identifier: determining adjacent nodes of the nodes within the range of the affected node based on the power grid topology model, and adding a blackout event identifier if the adjacent nodes are blackout nodes; and determining each ending node added with the power outage event identifier as an influence range of the power outage event identifier corresponding to the power outage event, wherein the influence range is the power outage area.
Preferably, the forwarding policy generating module specifically includes:
The word vector acquisition module is used for marking parts of speech for the power outage items in the power dispatching knowledge graph, then carrying out named entity identification, and automatically marking a data set to generate a corpus; in the corpus, word2vector is input by taking sentences as big units and words as small units to obtain word embedded vectors, the word embedded vectors are input into Bi-LSTM network, and word vectors are output;
the power failure node processing module is used for acquiring corresponding power failure nodes and power transfer nodes in the power failure area, inputting the word2vector by taking the power failure nodes as large units and the power transfer nodes as small units to obtain word embedding vectors to be processed, inputting the word embedding vectors into a Bi-LSTM network, and outputting the word embedding vectors to be processed to obtain word vectors to be processed;
the result splicing module calculates attention a similarity matrix according to the word vector and the word vector to be processed, then performs threshold attention alignment respectively, and splices results;
And the transfer strategy selection module is used for respectively calculating the average value of the spliced results, mapping the average value into a vector with a fixed length through the feedforward neural network, respectively mapping the vector into a vector with a fixed dimension through the MLP, mapping the vector with the fixed dimension into a predicted value through the MLP layer, presetting a matching threshold, and selecting a transfer power node with the maximum predicted value and exceeding the matching threshold.
A distribution network power failure plan management method comprises the following steps:
s1: monitoring current real-time data of the power grid in real time and sending the current real-time data to a terminal data platform for storage;
s2: the terminal data platform stores the real-time data, the historical transfer data and the section data, and simultaneously receives and displays the published maintenance plan and the published power failure plan in real time;
S3: establishing a power grid topology model according to a maintenance plan issued by the terminal data platform and stored data, and identifying a power outage area by detecting power outage nodes;
S4: and generating an optimal transfer strategy according to the transfer node of the power outage area corresponding to the power outage node, and transmitting the optimal transfer strategy to the terminal data platform for display, wherein the optimal transfer strategy is the power outage plan.
Compared with the prior art, the invention discloses a distribution network power failure plan management system and method, which have the following beneficial effects:
1. the power outage scope of equipment overhaul influence is determined through the access section data, repeated power outage of overhaul equipment can be effectively reduced, and the power outage plan management level of the distribution network is improved.
2. Through carrying out combination trend calculation to the power outage plan of same time section based on artificial intelligence degree of depth study to combine historical data and real-time data to develop the target check, intelligent evaluation decision-making, build power outage plan self-service balance system, accurate discernment power outage risk, online self-service balance can realize convenience, self-service, the intellectuality of power outage plan balance.
3. The power failure plan full-level optimization execution system is constructed, the power failure, operation, permission, work and power transmission full-flow zero time difference management and control are promoted, and the transparency, the compliance and the accuracy of full-level optimization execution can be realized.
4. And developing an evaluation system construction, and making quantitative scoring rules from aspects of specification declaration, safety risk, rigid execution and the like to strengthen power failure planning behavior evaluation management.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic structural view of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The embodiment of the invention discloses a distribution network power failure plan management system, as shown in fig. 1, comprising: the power grid monitoring system comprises a terminal data platform, a power outage area identification module, a transfer strategy generation module and a real-time monitoring module, wherein the real-time monitoring module monitors current real-time data of a power grid and sends the current real-time data to the terminal data platform for storage; the terminal data platform stores real-time data, historical transfer data and section data, and simultaneously receives and displays a published maintenance plan and a published power failure plan in real time; the power outage area identification module establishes a power grid topology model according to the overhaul plan issued by the terminal data platform and the stored data, and carries out power outage area identification by detecting power outage nodes; and the transfer strategy generation module generates an optimal transfer strategy according to the transfer node of the power outage area corresponding to the power outage node, and transmits the optimal transfer strategy to the terminal data platform for display, wherein the optimal transfer strategy is the power outage plan.
In one embodiment, the power outage area identification module specifically comprises:
the model building module is used for building a power grid topology model according to the section data, the real-time data and the nodes needing to be overhauled in the overhauling plan;
The equation construction module is used for constructing a Newton-Laportson method power flow calculation equation of the power grid topological model, solving partial derivatives of the power flow calculation equation, constructing a Jacobian matrix and constructing an unbalance amount; meanwhile, defining a correction equation, setting a convergence condition, converging a Newton-Laporton method power flow calculation equation, outputting the voltage of each node when the convergence condition is reached, and re-entering an equation construction module when the convergence condition is not reached;
In a specific embodiment, a node admittance matrix Y is constructed by combining a power grid topology model and operation parameters; counting the active power P (v, 0) of each node and the reactive power Q (v, 0) of each node; setting the voltage of each node, enabling the voltage of a V node in a power grid topological model to be V (V, 1), and constructing a complex expression form of V (V, 1) as a V (V, 1) expression; v is ordinal number, v is more than or equal to 1 and less than or equal to N, and N is the total number of balance nodes, PQ nodes and PV nodes contained in the power grid topology model;
Substituting the V (V, 1) expression and the node admittance matrix Y into a nonlinear equation, solving a bias derivative through the equation, constructing a Jacobian matrix A, and constructing an unbalance b; the unbalance amount b is used for describing the deviation between the calculated value of the target item and the fixed known value, and the target item comprises one or more of active power, reactive power and voltage amplitude;
Defining a correction equation a×g=b, and solving a correction amount g by quantum calculation;
updating the voltage V (V, 1) of the unbalanced node according to the correction amount g, and judging whether the quantum Newton-Laporton method power flow calculation reaches a convergence condition or not; if yes, outputting the voltages of all nodes; if not, judging whether t reaches the set iteration upper limit value; if yes, outputting the voltages of all nodes; if not, the t is updated to be t+1, and then the nonlinear equation is carried in again;
Outputting the voltage V (V, 1) of all nodes to finish the load flow calculation of the quantum Newton-Laportson method; the voltage V (V, 1) of the PQ node and the PV node is the voltage V (V, 1) after iterative updating, and the voltage V (V, 1) of the balance node is the voltage V (V, 1) set in the power grid topological model.
The element Y (vk, 1) of the kth column and the v row in the admittance matrix Y is the mutual admittance of the kth node and the v node in the power grid topological model, and when v=k, Y (vk, 1) is the self admittance of the kth node; y (vk, 1) is a complex number; k is more than or equal to 1 and less than or equal to N;
Y(vk,1)＝G(vk)+j×B(vk)
Wherein G (vk) is the real part of Y (vk, 1), B (vk) is the imaginary part of Y (vk, 1), G (vk) is the conductance of the power grid branch between the v-th node and the k-th node in the power grid topology model, and B (vk) is the susceptance of the power grid branch between the v-th node and the k-th node in the power grid topology model;
The nonlinear equation is:
V(v,1)×∑k∈[1,N][Y(vk,2)×Y(k,2)]＝P(v)+j×Q(v)
wherein V (k, 1) represents the voltage of a kth node in the power grid topological model, and V (k, 2) is the conjugate complex number of V (k, 1); y (vk, 2) is the complex conjugate of Y (vk, 1); p (v) is the active power calculated value of the v-th node in the power grid topological model, Q (v) is the reactive power calculated value of the v-th node in the power grid topological model, N is the number of nodes in the power grid topological model, and Sigma k∈[1,N] represents that the lower limit value of k is 1 and the upper limit value of k is N when summing;
The Jacobian matrix A is constructed by substituting the expression of V (V, 1) and the node admittance matrix Y into a nonlinear equation, then obtaining the expression of the active power P (V) of the PQ node and the active power P (V) of the PV node and the expression of the reactive power Q (V) of the PQ node, respectively solving the bias derivatives of the independent variables of the expression of V (V, 1) by the P (V) and the Q (V), and constructing the Jacobian matrix A according to the bias derivative calculation equation.
In one embodiment, A is converted to classical state A (1) and b is converted to classical state b (1); a (1) is a Hermitian matrix, A (1) is a real symmetric matrix, A (1) E R M×M, and M is a set value; b (1) is a unit vector of M dimension; reconstructing a correction equation, solving the reconstructed correction equation through a quantum computer to obtain a quantum state g (1) containing a correction vector g, and obtaining a solution of g through quantum inverse coding;
The reconstructed correction equation is:
A(1)×g(1)＝b(1)；
b(1)＝[b/|b|,0]T；
g(1)＝[0,g/|b|]T；
wherein, G (1) ∈R M;AH is the conjugate transpose of A.
The node selection module is used for evaluating the influence of the electric equipment maintenance on the ground state power flow of the whole power grid according to the change condition of the voltage of each node before and after the connection of the maintenance equipment and the change of the load rate of the node after the maintenance and the load rate of the node before and after the maintenance acquired in the power grid topology model, setting an influence threshold value, and when the influence exceeds the influence threshold value, bringing the node into a power failure node;
And the power outage area determining module is used for setting a power outage event identifier according to the power outage node and the power grid topology model and further determining the power outage area.
In one embodiment, the power outage area determination module specifically comprises:
The data acquisition module acquires a power grid topology model and sends the power grid topology model to the range determination module;
The identification module is used for acquiring the power failure node, setting a power failure event identification, and sending the power failure event identification of the power failure node to the range determination module;
The range determining module is used for receiving the power grid topology model sent by the data acquisition module and the power outage event identification of the power outage node sent by the identification module, and adding the power outage event identification of the power outage node in the given range of the maintenance plan to the node corresponding to the power outage node in the power grid topology model; based on a preset blackout event rule, determining an influence node range which is influenced by the blackout event corresponding to the blackout event, starting from the current node of the power grid topology model to the end node, and executing the following processes for each node added with the blackout event identifier: determining adjacent nodes of the nodes within the range of the affected node based on the power grid topology model, and adding a blackout event identifier if the adjacent nodes are blackout nodes; and determining each end node added with the power outage event identification as an influence range of the power outage event corresponding to the power outage event identification, wherein the influence range is the power outage area.
In a particular embodiment, determining neighboring nodes of a node within an affected node range based on a power grid topology model includes:
Under the condition that the influence node range is an upper-level adjacent node, determining each upper-level adjacent node of the node based on a topological structure diagram;
Under the condition that the influence node range is a lower-level adjacent node, determining each lower-level adjacent node of the node based on a topological structure diagram;
In the case where the scope of the influencing node is a lower-level neighboring node and a lower-level neighboring node, then each upper-level neighboring node and each lower-level neighboring node of the node are determined based on the grid topology model.
In a specific embodiment, the forwarding policy generation module specifically includes:
The word vector acquisition module is used for marking parts of speech for the power outage items in the power dispatching knowledge graph, then carrying out named entity identification, and automatically marking a data set to generate a corpus; in the corpus, word2vector is input by taking sentences as big units and words as small units to obtain word embedded vectors, the word embedded vectors are input into Bi-LSTM network, and word vectors are output;
The power failure node processing module is used for acquiring corresponding power failure nodes and power conversion nodes in a power failure area, inputting word2vector by taking the power failure nodes as large units and the power conversion nodes as small units to obtain word embedding vectors to be processed, inputting the word embedding vectors into a Bi-LSTM network, and outputting the word embedding vectors to be processed to obtain word vectors to be processed;
the result splicing module calculates attention a similarity matrix according to the word vector and the word vector to be processed, then performs threshold attention alignment respectively, and splices the results;
In one embodiment, a attention similarity matrix is computed, a dot product is computed using the word vector to compute attention the similarity matrix, and a matrix with a computed dot product result less than the threshold gate is represented as 0.
And the transfer strategy selection module is used for respectively calculating the average value of the spliced results, mapping the average value into a vector with a fixed length through the feedforward neural network, respectively mapping the vector into a vector with a fixed dimension through the MLP, mapping the vector with the fixed dimension into a predicted value through the MLP layer, presetting a matching threshold, and selecting a transfer power node with the maximum predicted value and exceeding the matching threshold.
A distribution network power failure plan management method comprises the following steps:
s1: monitoring current real-time data of the power grid in real time and sending the current real-time data to a terminal data platform for storage;
S2: the terminal data platform stores real-time data, historical transfer data and section data, and simultaneously receives and displays a published maintenance plan and a published power failure plan in real time;
S3: establishing a power grid topology model according to a maintenance plan issued by a terminal data platform and stored data, and identifying a power outage area by detecting power outage nodes;
s4: and generating an optimal transfer strategy according to the transfer node of the power outage area corresponding to the power outage node, and transmitting the optimal transfer strategy to a terminal data platform for display, wherein the optimal transfer strategy is the power outage plan.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (4)
1. A distribution network outage plan management system, comprising: the power grid monitoring system comprises a terminal data platform, a power outage area identification module, a transfer strategy generation module and a real-time monitoring module, wherein the real-time monitoring module monitors current real-time data of a power grid and sends the current real-time data to the terminal data platform for storage; the terminal data platform stores the real-time data, the historical transfer data and the section data, and simultaneously receives and displays the published maintenance plan and the published power failure plan in real time; the power outage area identification module establishes a power grid topology model according to an overhaul plan issued by the terminal data platform and stored data, and identifies the power outage area by detecting power outage nodes; the transfer strategy generation module generates an optimal transfer strategy according to the transfer node of the power outage area corresponding to the power outage node, and transmits the optimal transfer strategy to the terminal data platform for display, wherein the optimal transfer strategy is a power outage plan;
the transfer strategy generation module specifically comprises:
The word vector acquisition module is used for marking parts of speech for the power outage items in the power dispatching knowledge graph, then carrying out named entity identification, and automatically marking a data set to generate a corpus; in the corpus, word2vector is input by taking sentences as big units and words as small units to obtain word embedded vectors, the word embedded vectors are input into Bi-LSTM network, and word vectors are output;
the power failure node processing module is used for acquiring corresponding power failure nodes and power transfer nodes in the power failure area, inputting the word2vector by taking the power failure nodes as large units and the power transfer nodes as small units to obtain word embedding vectors to be processed, inputting the word embedding vectors into a Bi-LSTM network, and outputting the word embedding vectors to be processed to obtain word vectors to be processed;
the result splicing module calculates attention a similarity matrix according to the word vector and the word vector to be processed, then performs threshold attention alignment respectively, and splices results;
And the transfer strategy selection module is used for respectively calculating the average value of the spliced results, mapping the average value into a vector with a fixed length through the feedforward neural network, respectively mapping the vector into a vector with a fixed dimension through the MLP, mapping the vector with the fixed dimension into a predicted value through the MLP layer, presetting a matching threshold, and selecting a transfer power node with the maximum predicted value and exceeding the matching threshold.
2. The distribution network outage planning management system according to claim 1, wherein the outage area identification module specifically comprises:
The model building module is used for building a power grid topology model according to the section data, the real-time data and the nodes needing to be overhauled in the overhauling plan;
The equation construction module is used for constructing a Newton-Laportson method power flow calculation equation of the power grid topological model, solving partial derivatives of the power flow calculation equation, constructing a Jacobian matrix and constructing an unbalance amount; meanwhile, defining a correction equation, setting a convergence condition, converging the Newton-Laporton method power flow calculation equation, outputting the voltage of each node when the convergence condition is reached, and re-entering an equation construction module when the convergence condition is not reached;
The node selection module is used for evaluating the influence of the electric equipment maintenance on the full-power-grid ground state power flow according to the change condition of the voltage of each node before and after the connection of the maintenance equipment, the change of the node load rate after the maintenance and the change of the node load rate before and after the maintenance acquired in the power-grid topology model, setting an influence threshold value, and when the influence exceeds the influence threshold value, bringing the node into a power failure node;
And the power outage area determining module is used for setting a power outage event identifier according to the power outage node and the power grid topology model and further determining the power outage area.
3. The distribution network outage planning management system according to claim 2, wherein the outage area determination module specifically comprises:
the data acquisition module acquires the power grid topological model and sends the power grid topological model to the range determination module;
The identification module is used for acquiring the power failure node, setting a power failure event identification, and sending the power failure event identification of the power failure node to the range determination module;
The range determining module is used for receiving the power outage event identification of the power outage node sent by the data acquisition module and the power outage node sent by the identification module, and adding the power outage event identification of the power outage node in the given range of the maintenance plan to the node corresponding to the power outage node in the power grid topology model; based on a preset blackout event rule, determining an influence node range which is influenced by the blackout event corresponding to the blackout event, starting from the current node of the power grid topology model to the end node, and executing the following processes for each node added with the blackout event identifier: determining adjacent nodes of the nodes within the range of the affected node based on the power grid topology model, and adding a blackout event identifier if the adjacent nodes are blackout nodes; and determining each ending node added with the power outage event identifier as an influence range of the power outage event identifier corresponding to the power outage event, wherein the influence range is the power outage area.
4. The distribution network power outage plan management method is characterized by comprising the following steps of:
s1: monitoring current real-time data of the power grid in real time and sending the current real-time data to a terminal data platform for storage;
s2: the terminal data platform stores the real-time data, the historical transfer data and the section data, and simultaneously receives and displays the published maintenance plan and the published power failure plan in real time;
S3: establishing a power grid topology model according to a maintenance plan issued by the terminal data platform and stored data, and identifying a power outage area by detecting power outage nodes;
s4: generating an optimal transfer strategy according to transfer nodes of the power outage area corresponding to the power outage node, and transmitting the optimal transfer strategy to the terminal data platform for display, wherein the optimal transfer strategy is a power outage plan;
The generating the optimal transfer strategy specifically comprises the following steps:
In the power dispatching knowledge graph, the power failure items in the transfer items are marked with parts of speech for the power failure items, then named entity identification is carried out, and a data set is automatically marked to generate a corpus; in the corpus, word2vector is input by taking sentences as big units and words as small units to obtain word embedded vectors, the word embedded vectors are input into Bi-LSTM network, and word vectors are output;
Acquiring corresponding power failure nodes and power transfer nodes in the power failure area, inputting the word2vector by taking the power failure nodes as large units and the power transfer nodes as small units to obtain word embedding vectors to be processed, inputting the word embedding vectors into a Bi-LSTM network, and outputting to obtain word vectors to be processed;
calculating attention a similarity matrix according to the word vector and the word vector to be processed, then respectively carrying out threshold attention alignment, and splicing results;
And respectively calculating the average value of the spliced results, respectively mapping the average value into a vector with a fixed length through a feedforward neural network, respectively mapping the vector with the fixed dimension into a vector with a fixed dimension through an MLP (multi-layer logic) layer, mapping the vector with the fixed dimension into a predicted value through the MLP layer, presetting a matching threshold value, and selecting a transfer power supply node with the maximum predicted value and exceeding the matching threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311729084.8A CN117575537B (en) | 2023-12-15 | 2023-12-15 | Distribution network power failure plan management system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311729084.8A CN117575537B (en) | 2023-12-15 | 2023-12-15 | Distribution network power failure plan management system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117575537A CN117575537A (en) | 2024-02-20 |
| CN117575537B true CN117575537B (en) | 2024-05-31 |
Family
ID=89864281
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311729084.8A Active CN117575537B (en) | 2023-12-15 | 2023-12-15 | Distribution network power failure plan management system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117575537B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117783797B (en) * | 2024-02-28 | 2024-05-10 | 国网山东省电力公司莒县供电公司 | Power distribution automatic switch partial discharge detection early warning system |
| CN117875948B (en) * | 2024-03-12 | 2024-05-14 | 江苏秉信科技有限公司 | Equipment-based power grid overhaul event determination method, device, equipment and medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110601188A (en) * | 2019-09-20 | 2019-12-20 | 国网天津市电力公司 | Rapid processing method for large-area power failure of power distribution network based on optimal regional load transfer strategy |
| CN110889587A (en) * | 2019-10-18 | 2020-03-17 | 国家电网有限公司 | Power distribution network line risk assessment method |
| CN112561248A (en) * | 2020-11-27 | 2021-03-26 | 国电南瑞南京控制系统有限公司 | Intelligent analysis and control method and system for power failure plan of main and distribution network dispatching |
| CN113344280A (en) * | 2021-06-21 | 2021-09-03 | 广西电网有限责任公司南宁供电局 | Power failure plan optimization model constraint construction method and device considering load transfer |
| CN113627766A (en) * | 2021-08-02 | 2021-11-09 | 广西电网有限责任公司 | Risk identification method for topology identification power failure maintenance plan |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140379435A1 (en) * | 2013-05-07 | 2014-12-25 | Isam Yahia AL-FILALI | Reyada system and method for performance management, communication, strategic planning, and strategy execution |
-
2023
- 2023-12-15 CN CN202311729084.8A patent/CN117575537B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110601188A (en) * | 2019-09-20 | 2019-12-20 | 国网天津市电力公司 | Rapid processing method for large-area power failure of power distribution network based on optimal regional load transfer strategy |
| CN110889587A (en) * | 2019-10-18 | 2020-03-17 | 国家电网有限公司 | Power distribution network line risk assessment method |
| CN112561248A (en) * | 2020-11-27 | 2021-03-26 | 国电南瑞南京控制系统有限公司 | Intelligent analysis and control method and system for power failure plan of main and distribution network dispatching |
| CN113344280A (en) * | 2021-06-21 | 2021-09-03 | 广西电网有限责任公司南宁供电局 | Power failure plan optimization model constraint construction method and device considering load transfer |
| CN113627766A (en) * | 2021-08-02 | 2021-11-09 | 广西电网有限责任公司 | Risk identification method for topology identification power failure maintenance plan |
Non-Patent Citations (1)
| Title |
|---|
| "基于自然语言解析和事理图谱的自校核智能停复电系统构建";佟佳弘;《万方》;20230715;第1-91页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117575537A (en) | 2024-02-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117575537B (en) | Distribution network power failure plan management system and method | |
| Zhuo et al. | Incorporating massive scenarios in transmission expansion planning with high renewable energy penetration | |
| Miranda et al. | Fuzzy modelling of power system optimal load flow | |
| Cheng et al. | A two-stage robust approach for the reliable logistics network design problem | |
| Zhou et al. | Multi-energy net load forecasting for integrated local energy systems with heterogeneous prosumers | |
| Gbadamosi et al. | A comparative analysis of generation and transmission expansion planning models for power loss minimization | |
| CN106022614A (en) | Data mining method of neural network based on nearest neighbor clustering | |
| Mahvi et al. | Optimal bidding strategy in a competitive electricity market based on agent-based approach and numerical sensitivity analysis | |
| De Oliveira et al. | Efficient hybrid algorithm for transmission expansion planning | |
| Alaee et al. | Stochastic transmission expansion planning incorporating reliability solved using SFLA meta-heuristic optimization technique | |
| Yin et al. | Equilibrium stability of asymmetric evolutionary games of multi-agent systems with multiple groups in open electricity market | |
| CN106557876A (en) | The constructing system and its method of evaluation index and assessment scale based on power information | |
| Agrawal et al. | A multi-objective thermal exchange optimization model for solving optimal power flow problems in hybrid power systems | |
| CN110210679A (en) | A kind of load prediction system applied to County Level Distribution Network planning | |
| Chen et al. | Deep-quantile-regression-based surrogate model for joint chance-constrained optimal power flow with renewable generation | |
| Shaghaghi et al. | Proposing a new optimized forecasting model for the failure rate of power distribution network thermal equipment for educational centers | |
| Serraji et al. | Multi swarm optimization based adaptive fuzzy multi agent system for microgrid multi-objective energy management | |
| Javadi et al. | Intelligent particle swarm optimization augmented with chaotic searching technique to integrate distant energy resources | |
| Lu et al. | Voltage limit violation risk evaluation method considering communication failures in distributed voltage regulation system | |
| Nik et al. | A multi-objective optimization and fuzzy prioritization approach for project risk responses selection | |
| Kim et al. | Projection-aware deep neural network for dc optimal power flow without constraint violations | |
| CN115051360A (en) | Online computing method and device for operation risk of electric power system based on integrated knowledge migration | |
| CN115577999A (en) | Power grid operation safety checking platform based on big data processing | |
| Zhang et al. | An Efficient Learning-Based Solver for Two-Stage DC Optimal Power Flow with Feasibility Guarantees | |
| CN114204554A (en) | Method for evaluating regulation and control operation safety for intelligent power grid system |
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 |