CN113919974A - Knowledge graph-based large-scale power grid flow convergence artificial intelligence adjustment method and system - Google Patents

Knowledge graph-based large-scale power grid flow convergence artificial intelligence adjustment method and system Download PDF

Info

Publication number
CN113919974A
CN113919974A CN202111254305.1A CN202111254305A CN113919974A CN 113919974 A CN113919974 A CN 113919974A CN 202111254305 A CN202111254305 A CN 202111254305A CN 113919974 A CN113919974 A CN 113919974A
Authority
CN
China
Prior art keywords
state
knowledge
power grid
flow
scale power
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.)
Pending
Application number
CN202111254305.1A
Other languages
Chinese (zh)
Inventor
文晶
陈兴雷
汤涌
郭强
黄彦浩
李文臣
王甜婧
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Electric Power Research Institute Co Ltd CEPRI
Original Assignee
China Electric Power Research Institute Co Ltd CEPRI
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China Electric Power Research Institute Co Ltd CEPRI filed Critical China Electric Power Research Institute Co Ltd CEPRI
Priority to CN202111254305.1A priority Critical patent/CN113919974A/en
Publication of CN113919974A publication Critical patent/CN113919974A/en
Pending legal-status Critical Current

Links

Images

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
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/02—Knowledge representation; Symbolic representation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/04—Inference or reasoning models
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
    • H02J2203/10—Power transmission or distribution systems management focussing at grid-level, e.g. load flow analysis, node profile computation, meshed network optimisation, active network management or spinning reserve management
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
    • H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
    • 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

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • Economics (AREA)
  • Public Health (AREA)
  • General Business, Economics & Management (AREA)
  • Water Supply & Treatment (AREA)
  • Tourism & Hospitality (AREA)
  • Strategic Management (AREA)
  • Primary Health Care (AREA)
  • General Health & Medical Sciences (AREA)
  • Marketing (AREA)
  • Human Resources & Organizations (AREA)
  • Power Engineering (AREA)
  • Supply And Distribution Of Alternating Current (AREA)

Abstract

The invention discloses a large-scale power grid flow convergence artificial intelligence adjusting method and system based on a knowledge graph, wherein the method comprises the following steps: determining a knowledge representation of large-scale power grid flow adjustment, wherein the knowledge representation comprises nodes of large-scale power grid flow and relations among the nodes; constructing a knowledge graph based on the relation of the knowledge representation; and sequentially adjusting the large-scale power grid flow under different nodes based on the relation and the adjusting means of each node in the knowledge graph until the large-scale power grid flow is converged. The invention discloses an artificial intelligent adjustment method for large-scale power grid flow convergence, which is characterized in that rules in a knowledge graph are used as a basis for adjusting the direction, and adjusting means in the knowledge graph are packaged into independent operation, so that the power grid state is judged and corresponding adjusting decisions are given, and finally the artificial intelligent adjustment for large-scale power grid flow convergence is realized.

Description

Knowledge graph-based large-scale power grid flow convergence artificial intelligence adjustment method and system
Technical Field
The invention relates to the technical field of power system simulation, in particular to a knowledge graph-based artificial intelligence adjustment method and system for power flow convergence of a large-scale power grid.
Background
The power flow calculation is the most basic and important calculation for researching the power system and is the basis for planning and operating the power grid. However, as the size of the power grid is continuously enlarged, the variables of the power flow equation are also increased sharply. For an actual ten-thousand-level node power grid, the load flow equation variables of the data calculated in the mode reach tens of thousands, various constraint conditions such as voltage and power need to be met, and the load flow calculation is often in the case of non-convergence. At this time, the operation mode needs to be adjusted by means of changing the output of the generator, switching the capacitance reactor and the like, so that the power flow returns to a reasonable feasible solution, and the convergence and the reasonable distribution of the power flow are ensured. The large-scale power grid refers to a power grid with bus nodes more than 10000.
At present, in the prior art, the unconverged power flow can be adjusted only by manual work on the basis of the existing power flow calculation program, a trial-and-error method is mainly adopted in the adjustment process, manual experience is seriously relied on, the adjustment precision is not guaranteed, the error and leakage phenomenon is easily caused, and the efficiency is very low. A large amount of manpower and time are required to be arranged every year for completing large-scale power grid load flow calculation and operation mode adjustment of a power grid enterprise, and a large amount of manpower resources are consumed. The defects of the traditional power flow calculation working mode are difficult to meet the increasingly complex large-scale power grid simulation analysis requirements, and an artificial intelligent method for automatically adjusting power flow convergence is urgently needed, so that the working is more efficient and accurate, and the manpower is liberated.
The prior art improves the PSASP load flow calculation module of the existing power system simulation software. In the original PSASP load flow calculation module, two adjusting means of presetting a balance point and reading a last load flow result to make an initial value are provided for improving load flow convergence. The preset balance point means that the load flow calculation is divided into two stages: initial value calculation and normal iteration calculation. In the initial value calculation stage, the 'preset balance point' is used as a balance point to participate in iteration, a load flow initial value with certain precision can be obtained quickly, then the 'preset balance point' is restored to the original node type, and normal iterative calculation is started by the load flow initial value obtained in the initial value calculation stage. Through the calculation of the two stages, the convergence of the conventional power flow calculation method can be improved. Reading the last power flow result to make an initial value means that the bus voltage phase angle of the power flow result which has converged at the last time is used as an iteration initial value of the calculation. Because the change between two times of load flow calculation is smaller, especially for large-scale data, the influence of the change of an individual grid frame or power generation load data on the whole voltage distribution of the whole network is smaller, and the bus voltage value of the last time of load flow result is close to the true value of the current time of load flow calculation, the calculation convergence can be improved.
However, in the prior art, in the original PSASP power flow calculation module, the initial value of the calculation iteration is changed only by presetting the balance point and reading the previous power flow result to make the initial value, so that the performance of the power flow calculation algorithm is improved to a certain extent. However, the two adjusting means do not modify the power flow calculation data, such as the output of the generator and the capacity of the parallel capacitor reactor, so that the power flow distribution condition cannot be fundamentally improved, and the power flow which is unreasonably distributed per se cannot be effectively acted.
In addition, in the original PSASP load flow calculation module, the two adjusting means are provided for the user as auxiliary tools, so that the user can select whether to adopt the method. The user cannot judge whether the adjustment means is needed or not according to the current state of the power grid, and cannot judge which adjustment means is more effective in the current state of the power grid, and the adjustment can only be carried out in a mode of repeated trial and error. The adjustment process is neither flexible nor intelligent.
Therefore, a technology is needed to realize the large-scale power grid flow convergence artificial intelligence adjustment technology based on the knowledge graph.
Disclosure of Invention
The technical scheme of the invention provides a knowledge graph-based large-scale power grid power flow convergence artificial intelligence adjusting method and system, and aims to solve the problem of how to adjust the large-scale power grid power flow convergence based on the knowledge graph.
In order to solve the above problems, the present invention provides a large-scale power grid flow convergence artificial intelligence adjustment method based on a knowledge graph, wherein the method comprises:
determining a knowledge representation of large-scale power grid flow adjustment, wherein the knowledge representation comprises nodes of large-scale power grid flow and relations among the nodes;
constructing a knowledge graph based on the relation of the knowledge representation;
and sequentially adjusting the large-scale power grid flow under different nodes based on the relation and the adjusting means of each node in the knowledge graph until the large-scale power grid flow is converged.
Preferably, the adjusting the large-scale power grid flow under different nodes in sequence based on the relation and the adjusting means of each node in the knowledge graph includes:
judging the current state of the large-scale power grid based on the nodes represented by the knowledge;
acquiring a plurality of load flow adjusting means of the current state of the large-scale power grid and an execution sequence executed by the plurality of load flow adjusting means based on the relation expressed by the knowledge;
and sequentially adopting a power flow adjusting means according to the determined execution sequence to adjust the power flow of the large-scale power grid.
Preferably, before adjusting the large-scale power grid flow at different nodes, the method further includes:
and setting execution weights for the plurality of power flow adjusting means respectively, and determining the execution sequence of the plurality of power flow adjusting means according to the execution weights.
Preferably, the triple data structure is in the form of < node, relation, node >, and different nodes and relations are defined based on different knowledge representations.
Preferably, the states in the node include: the state of unconvergence, the state of data inspection, the state of calculation setting modification, the state of regional active imbalance and the state of reactive imbalance.
Preferably, the knowledge of the unconverged state is expressed as: < unconverged state, characterized by a flow convergence flag =1>, < unconverged state, operation, flow calculation >.
Preferably, the subsequent state of the unconverged state points to the data check state, and the knowledge of the data check state is expressed as: < non-convergence state, follow-up state, data check state >, < data check state, operation, check transformer transformation ratio >, < data check state, operation, check parallel transformer parameter >, < data check state, operation, check parallel capacitor reactor >, < data check state, operation, check generator voltage parameter >.
Preferably, the subsequent state of the data check state points to the computation settings modification state, the knowledge of which is expressed as: < data check state, follow-up state, calculation setting modification state >, < calculation setting modification state, operation, modification load flow calculation setting >.
Preferably, the subsequent state of the calculation setting modification state points to the zone active imbalance state, and the knowledge of the zone active imbalance state is represented as: the method comprises the steps of < calculating setting modification state, subsequent state, regional active unbalanced state >, < regional active unbalanced state, operation, checking active unbalanced region >, < regional active unbalanced state, operation, finding a generator to be put in >, < regional active unbalanced state, operation, finding a generator to be quitted >, < regional active unbalanced state, operation, finding a generator to be added with work >, < regional active unbalanced state, operation, finding a generator to be reduced with work >, < regional active unbalanced state, operation and modification of generator parameters >.
Preferably, the subsequent state of the zone active imbalance state points to the reactive imbalance state, and the knowledge of the reactive imbalance state is expressed as: the method comprises the steps of (1) finding a maximum error bus >, < a reactive unbalance state, operating, finding a heavy load bus >, < a reactive unbalance state, operating, finding a load bus with low power factor >, < a reactive unbalance state, operating and adding a PV node > < an area active unbalance state, a follow-up state, a reactive unbalance state >, < a reactive unbalance state, operating, finding a load bus with low power factor >, < a reactive unbalance state.
Preferably, the method further comprises the following steps: updating the knowledge graph by inference:
and if the tail node of the first triple represented by the knowledge is the same as the head node of the second triple, a new triple can be obtained through inference of the first triple and the second triple.
Preferably, the method further comprises the following steps: cleaning the knowledge-graph is achieved by removing duplicate triples in the knowledge representation.
Based on another embodiment of the present invention, the present invention provides a system for large-scale power grid power flow convergence artificial intelligence adjustment based on a knowledge graph, the system comprising:
an initial unit for determining a knowledge representation of the large scale grid flow adjustment, the knowledge representation comprising nodes of the large scale grid flow and relations between the nodes;
the construction unit is used for constructing a knowledge graph based on the relation of the knowledge representation;
and the execution unit is used for sequentially adjusting the large-scale power grid flow under different nodes based on the relation and the adjustment means of each node in the knowledge graph until the large-scale power grid flow is converged.
Preferably, the execution unit is further configured to:
judging the current state of the large-scale power grid based on the nodes represented by the knowledge;
acquiring a plurality of load flow adjusting means of the current state of the large-scale power grid and an execution sequence executed by the plurality of load flow adjusting means based on the relation expressed by the knowledge;
and sequentially adopting a power flow adjusting means according to the determined execution sequence to adjust the power flow of the large-scale power grid.
Preferably, the execution unit is further configured to:
and setting execution weights for the plurality of power flow adjusting means respectively, and determining the execution sequence of the plurality of power flow adjusting means according to the execution weights.
The technical scheme of the invention provides a large-scale power grid flow convergence artificial intelligence adjusting method and system based on a knowledge graph, wherein the method comprises the following steps: determining a knowledge representation of the large-scale power grid flow adjustment, wherein the knowledge representation comprises nodes of the large-scale power grid flow and relations among the nodes; constructing a knowledge graph based on the relation of knowledge representation; and sequentially adjusting the large-scale power grid flow under different nodes based on the relation and the adjusting means of each node in the knowledge graph until the large-scale power grid flow is converged. The technical scheme of the invention provides a large-scale power grid flow convergence artificial intelligence adjusting method based on a knowledge graph, which abstracts knowledge experience accumulated in flow adjustment, rule specifications required to be followed in an adjusting process and effective adjusting means into knowledge to form a power grid flow adjusting knowledge graph. The technical scheme of the invention takes the rules in the knowledge graph as the basis for adjusting the direction, and encapsulates the adjusting means in the knowledge graph into independent operation, thereby judging the state of the power grid and giving out corresponding adjusting decisions, and finally realizing the artificial intelligent adjustment of the large-scale power grid load flow convergence.
A more complete understanding of exemplary embodiments of the present invention may be had by reference to the following drawings in which:
FIG. 1 is a flow chart of a method for adjusting the power flow convergence artificial intelligence of a large-scale power grid based on a knowledge graph according to a preferred embodiment of the invention;
FIG. 2 is a flow chart of a large-scale power grid power flow convergence artificial intelligence adjustment method according to a preferred embodiment of the invention;
FIG. 3 is a diagram of a large-scale grid power flow adjustment knowledge graph according to a preferred embodiment of the present invention; and
fig. 4 is a structural diagram of a large-scale power grid flow convergence artificial intelligence adjustment system based on a knowledge graph according to a preferred embodiment of the invention.
Detailed Description
The exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, however, the present invention may be embodied in many different forms and is not limited to the embodiments described herein, which are provided for complete and complete disclosure of the present invention and to fully convey the scope of the present invention to those skilled in the art. The terminology used in the exemplary embodiments illustrated in the accompanying drawings is not intended to be limiting of the invention. In the drawings, the same units/elements are denoted by the same reference numerals.
Unless otherwise defined, terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Further, it will be understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense.
Fig. 1 is a flowchart of a large-scale power grid flow convergence artificial intelligence adjustment method based on a knowledge graph according to a preferred embodiment of the invention. The invention provides a large-scale power grid flow convergence artificial intelligence adjusting method based on a knowledge graph, which comprises the steps of knowledge representation of large-scale power grid flow adjustment, construction of the large-scale power grid flow adjustment knowledge graph and the large-scale power grid flow convergence artificial intelligence adjusting method. The knowledge representation of the large-scale power grid flow adjustment is the core content of the knowledge map, the construction of the knowledge map is the basis for realizing the large-scale power grid flow convergence artificial intelligence adjustment method, and the large-scale power grid flow convergence artificial intelligence adjustment method is an integral adjustment process and finally provides an adjustment strategy.
As shown in fig. 1, the invention provides a large-scale power grid flow convergence artificial intelligence adjustment method based on a knowledge graph, which comprises the following steps:
step 101: determining knowledge representation of large-scale power grid flow adjustment, wherein the knowledge representation comprises nodes of large-scale power grid flow and relations among the nodes; preferably, the triple data structure is in the form of < node, relationship, node >, with different nodes and relationships defined based on different knowledge representations.
The knowledge representation of the large-scale power grid load flow adjustment is a data structure which is convenient for a computer to store and utilize by representing the state of a power grid, rule specifications to be followed and an effective adjustment means in the load flow adjustment process in a form of a triple group.
The triple of the invention is composed of < nodes, relations and nodes >, and different node types and relations can be defined according to different knowledge.
The node of the present invention is described in a string called the name of the node. The node representing the large-scale power grid flow adjustment knowledge comprises: the system comprises state nodes, characteristic nodes, operation nodes, power grid element nodes, power grid parameter nodes, position nodes, function nodes, weight nodes and node type description nodes. For example, the state node is a node for describing the state of the power grid, such as "unconverged state", "power flow out-of-limit state", and the like. The state nodes must have the relationship of "featured", "operated" and their corresponding subsequent nodes to form a triple.
The relation of the invention is that two nodes are connected in a knowledge base and represent the name of the direct logical relation of the two nodes. Can be seen as a directional arrow, through the relationship one node can find another node. The relationship representing the large-scale power grid flow adjustment knowledge comprises: there are features, operations, yes, call, there is an attribute, there is a location, weight. For example, with the characteristics, which indicate what characteristics a state has, the head node is a state node, the tail node is a characteristic node, and the knowledge base determines what state the grid is currently in by checking whether the grid data conforms to the characteristics. And the operation indicates which operations need to be executed in one state, the head node of the operation is a state node, the tail node of the operation is an operation node, one state can have a plurality of operations, and after the state is checked by the knowledge base, the operations corresponding to the state can be sequentially executed according to the weight.
Step 102: and constructing a knowledge graph based on the relation of the knowledge representation.
As shown in fig. 3, the construction of the large-scale power flow adjustment knowledge graph of the present invention refers to that knowledge is constructed into a knowledge base which is related to each other and conforms to large-scale power flow adjustment logic and flow according to a certain organization mode.
The invention relates to an organization mode of a large-scale power grid power flow adjustment knowledge graph, which is a process that a power flow adjustment process is regarded as being composed of a plurality of different states, each state represents the characteristics of the current power grid, and whether the current power grid enters the next state is judged by knowledge < state 1, the subsequent state and state 2 >. Each state corresponds to a plurality of operations related to the state, namely, the sequence of execution of each operation is determined by the weight for the adjustment means adopted for changing the state.
Preferably, the states in the three nodes include: the state of unconvergence, the state of data inspection, the state of calculation setting modification, the state of regional active imbalance and the state of reactive imbalance.
The invention discloses a plurality of states in a power flow adjusting process, which comprise the following steps: the state of unconvergence, the state of data inspection, the state of calculation setting modification, the state of regional active imbalance and the state of reactive imbalance.
Preferably, the knowledge of the unconverged state is expressed as: < unconverged state, characterized by a flow convergence flag =1>, < unconverged state, operation, flow calculation >.
The unconverged state of the present invention is characterized by a power flow convergence flag =1, and corresponds to an operation of performing power flow calculation. The state is expressed as < unconverged state in the knowledge graph, and is characterized by a power flow convergence flag =1>, < unconverged state, operation, and power flow calculation >.
Preferably, the subsequent state of the unconverged state points to a data check state, the knowledge of which is expressed as: < non-convergence state, follow-up state, data check state >, < data check state, operation, check transformer transformation ratio >, < data check state, operation, check parallel transformer parameter >, < data check state, operation, check parallel capacitor reactor >, < data check state, operation, check generator voltage parameter >.
The data checking state of the invention is a subsequent state of a non-convergence state, and the operation corresponding to the state comprises the following steps: checking transformer transformation ratio, checking parallel transformer parameters, checking parallel capacitor reactors and checking generator voltage parameters. This state is expressed in the knowledge graph as < non-convergence state, follow-up state, data check state >, < data check state, operation, check transformer transformation ratio >, < data check state, operation, check parallel capacitor reactor >, < data check state, operation, check generator voltage parameter >.
The checking of the transformer transformation ratio operation of the invention refers to checking whether the transformation ratio exceeds given upper and lower limits. If the upper limit and the lower limit are exceeded, the default value is modified.
The operation of checking the parameters of the parallel transformers refers to checking whether the parameters of the parallel running transformers are different greatly. If the difference exceeds the threshold, the two are modified to be consistent.
The operation of the parallel capacitor reactor is checked to see whether the impedance value of the parallel capacitor reactor is too small. If the threshold value is less than the preset threshold value, the data is set as invalid.
The operation of the voltage parameter of the generator is checked to see whether the given voltage amplitude of the generator is in a reasonable range. If the range is exceeded, the default value is modified.
Preferably, the subsequent state of the data check state points to a computation settings modification state, the knowledge of which is expressed as: < data check state, follow-up state, calculation setting modification state >, < calculation setting modification state, operation, modification load flow calculation setting >.
The calculation of the invention sets a modification state, and checks the subsequent state of the state for the data, and the operation corresponding to the state comprises the following steps: and modifying the load flow calculation setting. This state is expressed in the knowledge graph as < data inspection state, subsequent state, calculation setting modification state >, < calculation setting modification state, operation, modification load flow calculation setting >.
The operation of modifying the load flow calculation setting refers to modifying the calculation precision, the iteration times and the calculation method. And if the node scale exceeds 10000, setting a preset balance point.
Preferably, the subsequent state of the calculation setting modification state points to a regional active imbalance state, and the knowledge of the regional active imbalance state is expressed as: the method comprises the steps of < calculating setting modification state, subsequent state, regional active unbalanced state >, < regional active unbalanced state, operation, checking active unbalanced region >, < regional active unbalanced state, operation, finding a generator to be put in >, < regional active unbalanced state, operation, finding a generator to be quitted >, < regional active unbalanced state, operation, finding a generator to be added with work >, < regional active unbalanced state, operation, finding a generator to be reduced with work >, < regional active unbalanced state, operation and modification of generator parameters >.
The zone active power imbalance state of the invention is a subsequent state of a modified state for calculation setting, and the operation corresponding to the state comprises the following steps: checking an active unbalance area, searching a generator to be put in, searching a generator to be quitted, searching a generator to be added with work, searching a generator to be reduced with work, and modifying generator parameters. The state is expressed as < calculation setting modification state, subsequent state, region active unbalance state >, < region active unbalance state, operation, checking active unbalance region >, < region active unbalance state, operation, finding the generator to be put in >, < region active unbalance state, operation, finding the generator to be quitted >, < region active unbalance state, operation, finding the generator to be added with work >, < region active unbalance state, operation, finding the generator to be reduced with work >, < region active unbalance state, operation, modification generator parameter >.
The operation of checking the active imbalance region of the invention refers to checking the active balance condition according to the region. And if the area is in active imbalance, carrying out next adjustment on the area.
The method for searching the generator operation to be put into is used for searching the generator which can be put into in the region with active load > active power generation. And (3) searching principle: the active unbalance is minimized after the input.
The method for searching for the generator operation to be exited refers to the step of searching for the generator which can be exited in the area with the active load < active power generation. And (3) searching principle: the active imbalance is minimized after exit.
The method and the device for searching the active power imbalance of the generator are used for searching the generator with increased power, and if the generator can not be put into the generator or the active power imbalance after the generator is put into the generator does not meet the requirement, the generator with increased power is searched. And (3) searching principle: the active power output of the generator is less than the upper limit of the output, and the active power imbalance is minimized after the output is increased.
The invention searches for the generator with reduced power operation, and if the generator can not be quitted or the active unbalance amount after quitting the generator does not meet the requirement, the generator with reduced power output is searched for. And (3) searching principle: the active power output of the generator is greater than the lower limit of the output, and the active power imbalance is minimized after the output is reduced.
The operation of modifying the parameters of the generator means that the active power is adjusted by modifying the parameters of the effective mark, the active output and the like of the generator.
Preferably, the subsequent states of the zone active imbalance state point to reactive imbalance states, the knowledge of which is expressed as: the method comprises the steps of (1) finding a maximum error bus >, < a reactive unbalance state, operating, finding a heavy load bus >, < a reactive unbalance state, operating, finding a load bus with low power factor >, < a reactive unbalance state, operating and adding a PV node > < an area active unbalance state, a follow-up state, a reactive unbalance state >, < a reactive unbalance state, operating, finding a load bus with low power factor >, < a reactive unbalance state.
The reactive unbalance state is a subsequent state of a regional active unbalance state, and the operation corresponding to the state comprises the following steps: searching a maximum error bus, searching a heavy load bus, searching a load bus with low power factor, and adding a PV node. The state is expressed as < regional active unbalanced state, subsequent state, reactive unbalanced state >, < reactive unbalanced state, operation, finding maximum error bus >, < reactive unbalanced state, operation, finding load bus with low power factor >, < reactive unbalanced state, operation, adding PV node > in the knowledge graph.
The operation of searching the maximum error bus refers to searching the maximum error bus in the iterative process of load flow calculation.
The operation of searching for the heavy load bus is to search for the heavy load bus in each area.
The operation of searching the load bus with low power factor refers to searching the load bus with the power factor lower than 0.8.
The additional PV node of the invention is that a load node is added on the found reactive unbalance node, and the node type is set as PV, thereby supporting the reactive power at the node.
Preferably, the method further comprises the following steps: and (3) updating the knowledge graph through reasoning:
and if the tail node of the first triple represented by the knowledge is the same as the head node of the second triple, a new triple can be obtained through inference of the first triple and the second triple.
Preferably, the method further comprises the following steps: and searching repeated triples in the knowledge representation, and deleting one of the repeated triples to clean the knowledge graph.
Step 103: and sequentially adjusting the large-scale power grid flow under different nodes based on the relation and the adjusting means of each node in the knowledge graph until the large-scale power grid flow is converged.
Preferably, based on the relationship and the adjustment means of each node in the knowledge graph, the method sequentially adjusts the large-scale power grid flow under different nodes, and further comprises:
judging the current state of the large-scale power grid based on the nodes represented by the knowledge;
acquiring a plurality of load flow adjusting means of the current state of the large-scale power grid and an execution sequence executed by the plurality of load flow adjusting means based on the relation expressed by the knowledge;
and sequentially adopting a power flow adjusting means according to the determined execution sequence to adjust the power flow of the large-scale power grid.
Preferably, before adjusting the large-scale power grid flow at different nodes, the method further includes:
and setting execution weights for the plurality of power flow adjusting means respectively, and determining the execution sequence of the plurality of power flow adjusting means according to the execution weights.
The invention discloses an artificial intelligent adjustment method for large-scale power grid load flow convergence, which is characterized in that rules in a knowledge graph are used as a basis for adjusting the direction, adjusting means in the knowledge graph are packaged into independent operation, logic and possibility reasoning and deduction are carried out on knowledge in the knowledge graph, so that the power grid state is judged, a corresponding adjustment decision is given, and finally the artificial intelligent adjustment of large-scale power grid load flow convergence is realized.
The knowledge reasoning mechanism of the invention utilizes knowledge in the knowledge base to carry out reasoning according to a certain reasoning method and control strategy according to the current known fact, and obtains the answer of the problem or proves the correctness of a certain hypothesis. The inference method adopted by the invention is deductive inference and adopts a positive and negative mixed inference strategy.
The reasoning of the invention is to deduce new conclusions according to the fact that the actual problem is newly added, the conclusions are kept to be inconsistent with the existing knowledge and conclusions, and the reasoning is to deduce the fact that the known fact is included in a problem according to an axiomatic system as the conclusion.
The invention relates to a positive and negative mixed reasoning control strategy, which comprises the following specific steps: firstly, a batch of targets are generated according to part of problem information provided by a user, then, further information is obtained for each generated target, and the targets are tested one by one. The core of this is the early elimination of solutions that are inconsistent with current problem data constraints.
The large-scale power grid flow convergence artificial intelligence adjusting process is that firstly, the current state of a power grid is judged according to power grid data by knowledge < state, characteristic and description >; then, according to the regulation rule, the regulation means to be adopted by the state is selected by the knowledge < state, rule and operation >, and the execution sequence of each regulation means is determined by the knowledge < operation, weight and given value >; finally, an adjustment strategy is given, and large-scale power grid power flow convergence artificial intelligence adjustment is achieved.
In summary, the knowledge and experience accumulated in the power flow adjustment are expressed in a triple mode, the knowledge map is constructed on the basis, then the rule of the knowledge map is used as the rule of the power flow intelligent adjustment, logical and possible reasoning and deduction are carried out on the adjustment direction and the adjustment means, judgment and decision are made, and finally the artificial intelligent adjustment of the large-scale power grid power flow convergence is achieved.
In an embodiment of the invention, a CREPI36 node system example is adopted for verification, the method is applied to the example, the power flow is adjusted by an artificial intelligence adjusting method based on a knowledge graph, and a sample which is not converged is enabled to calculate convergence by adjusting an operation mode. The test results prove the effectiveness of the invention.
In order to test the effectiveness of knowledge in a knowledge base and the adaptability to power grids with different characteristics, based on the initial convergence trend of the system, a generator and a load are randomly changed between 0 and 4 times, and the switching condition of a capacitance reactor is changed at the same time to generate 7470 groups of data. Through load flow calculation, in 7470 groups of data, 3365 group of data converges and 4105 group of data does not converge.
The invention is described by taking 1 group of data as an example, and the initial trend of the data is not converged. Step 1, judging the initial state of the power grid according to data, and carrying out load flow calculation on the data according to knowledge < initial state, operation and load flow calculation > to obtain a load flow convergence mark =1, which indicates that the load flow calculation is not converged. The initial state of the data is judged to be the unconverged state according to knowledge < unconverged state, characterized by a convergence flag =1 >. And step 2, according to the knowledge < unconverged state, subsequent state and checking parameter state >, the data enters a parameter checking state, and the adjustment operation corresponding to the state is executed. According to the knowledge < checking parameter state, operation, checking transformer transformation ratio > and the knowledge < checking parameter state, operation, checking generator voltage parameter > whether the transformer transformation ratio in the data and the given voltage amplitude of the generator are in a reasonable range is checked, the transformation ratio of the three-winding transformer BUS10 is found to exceed the range, and the voltage phase angles of the generator BUS3 and BUS7 are found to exceed the range, so that the three-winding transformer BUS10 and the generator BUS7 are modified. And step 3, calculating and setting a modification state according to the knowledge < checking parameter state and subsequent state, wherein the modification calculation precision is 0.001, and the upper limit of the number of modification iterations is 100. And 4, according to the knowledge < calculation setting modification state, subsequent state and regional active unbalance state >, performing regional active balance check on the data, finding that the active load of the region 1 and the region 3 is smaller than the active power generation and the active load of the region 2 is larger than the active power generation, and performing active balance adjustment on the 3 regions: regions 1 and 3 increase generator output, and region 2 decreases generator output. And 5, according to knowledge < the regional active imbalance state, the subsequent state and the reactive imbalance state >, according to the operation in the state, searching a reactive weak BUS node as BUS23, and additionally arranging a PV node at the position to meet the reactive compensation requirement. After the adjustment, the load flow is recalculated, and the data is converged.
The invention adopts the artificial intelligence adjustment method provided by the invention to adjust 4105 groups of unconverged data, and finally, 3595 groups of converged data have the adjustment success rate of 87.6 percent, thereby verifying the effectiveness and the correctness of the method.
As another embodiment of the invention, the invention adopts a northeast power grid data sample set for verification. The sample set had 10470 sets of data. Wherein, 1990 group data initial power flow convergence, and 8480 group data power flow non-convergence.
The method of the invention is adopted to adjust the data of the non-convergence of the power flow, and the adjustment result is counted, as shown in the table 1.
Attached table 1 northeast data calculation example adjustment result statistical table
Figure 906033DEST_PATH_IMAGE002
As can be seen from the above table, after adjustment, the total data of the power flow convergence is 8043 groups, and the adjustment success rate is 94.8%, which meets the requirements of engineering and practice. The required adjustment time of all data is 335 minutes, the average adjustment time of one group of data is 0.032 minute, compared with a manual adjustment method, the adjustment speed and efficiency are greatly improved, the labor is saved, and the workload is reduced.
Fig. 4 is a structural diagram of a large-scale power grid flow convergence artificial intelligence adjustment system based on a knowledge graph according to a preferred embodiment of the invention. As shown in fig. 4, the present invention provides a large-scale power grid flow convergence artificial intelligence adjustment system based on a knowledge graph, which includes:
an initial unit 401, configured to determine a knowledge representation of large-scale grid power flow adjustment, where the knowledge representation includes nodes of large-scale grid power flow and relationships between the nodes; preferably, the triple data structure is in the form of < node, relationship, node >, with different nodes and relationships defined based on different knowledge representations.
A construction unit 402, configured to construct a knowledge graph based on the relation of the knowledge representation.
Preferably, the states in the nodes include: the state of unconvergence, the state of data inspection, the state of calculation setting modification, the state of regional active imbalance and the state of reactive imbalance.
Preferably, the knowledge of the unconverged state is expressed as: < unconverged state, characterized by a flow convergence flag =1>, < unconverged state, operation, flow calculation >.
Preferably, the subsequent state of the unconverged state points to a data check state, the knowledge of which is expressed as: < non-convergence state, follow-up state, data check state >, < data check state, operation, check transformer transformation ratio >, < data check state, operation, check parallel transformer parameter >, < data check state, operation, check parallel capacitor reactor >, < data check state, operation, check generator voltage parameter >.
Preferably, the subsequent state of the data check state points to a computation settings modification state, the knowledge of which is expressed as: < data check state, follow-up state, calculation setting modification state >, < calculation setting modification state, operation, modification load flow calculation setting >.
Preferably, the subsequent state of the calculation setting modification state points to a regional active imbalance state, and the knowledge of the regional active imbalance state is expressed as: the method comprises the steps of < calculating setting modification state, subsequent state, regional active unbalanced state >, < regional active unbalanced state, operation, checking active unbalanced region >, < regional active unbalanced state, operation, finding a generator to be put in >, < regional active unbalanced state, operation, finding a generator to be quitted >, < regional active unbalanced state, operation, finding a generator to be added with work >, < regional active unbalanced state, operation, finding a generator to be reduced with work >, < regional active unbalanced state, operation and modification of generator parameters >.
Preferably, the subsequent states of the zone active imbalance state point to reactive imbalance states, the knowledge of which is expressed as: the method comprises the steps of (1) finding a maximum error bus >, < a reactive unbalance state, operating, finding a heavy load bus >, < a reactive unbalance state, operating, finding a load bus with low power factor >, < a reactive unbalance state, operating and adding a PV node > < an area active unbalance state, a follow-up state, a reactive unbalance state >, < a reactive unbalance state, operating, finding a load bus with low power factor >, < a reactive unbalance state.
Preferably, the method further comprises the following steps: and (3) updating the knowledge graph through reasoning:
and if the tail node of the first triple represented by the knowledge is the same as the head node of the second triple, a new triple can be obtained through inference of the first triple and the second triple.
Preferably, the method further comprises the following steps: cleaning the knowledge graph is achieved by removing repeated triples in the knowledge representation.
And the execution unit 403 is configured to sequentially adjust the large-scale power grid flow at different nodes based on the relationship and the adjustment means of each node in the knowledge graph until the large-scale power grid flow converges.
Preferably, based on the relationship and the adjustment means of each node in the knowledge graph, the method sequentially adjusts the large-scale power grid flow under different nodes, and further comprises:
judging the current state of the large-scale power grid based on the nodes represented by the knowledge;
acquiring a plurality of load flow adjusting means of the current state of the large-scale power grid and an execution sequence executed by the plurality of load flow adjusting means based on the relation expressed by the knowledge;
and sequentially adopting a power flow adjusting means according to the determined execution sequence to adjust the power flow of the large-scale power grid.
Preferably, before adjusting the large-scale power grid flow at different nodes, the method further includes:
and setting execution weights for the plurality of power flow adjusting means respectively, and determining the execution sequence of the plurality of power flow adjusting means according to the execution weights.
The system 400 for adjusting large-scale power grid flow convergence artificial intelligence based on a knowledge graph according to the preferred embodiment of the present invention corresponds to the method 100 for adjusting large-scale power grid flow convergence artificial intelligence based on a knowledge graph according to the preferred embodiment of the present invention, and will not be described herein again.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting the protection scope thereof, and although the present invention has been described in detail with reference to the above-mentioned embodiments, those skilled in the art should understand that after reading the present invention, they can make various changes, modifications or equivalents to the specific embodiments of the present invention, but these changes, modifications or equivalents are within the protection scope of the appended claims.
The invention has been described with reference to a few embodiments. However, other embodiments of the invention than the one disclosed above are equally possible within the scope of the invention, as would be apparent to a person skilled in the art from the appended patent claims.
Generally, all terms used in the claims are to be interpreted according to their ordinary meaning in the technical field, unless explicitly defined otherwise herein. All references to "a/an/the [ device, component, etc ]" are to be interpreted openly as referring to at least one instance of said device, component, etc., unless explicitly stated otherwise. The steps of any method disclosed herein do not have to be performed in the exact order disclosed, unless explicitly stated.

Claims (15)

1. A large-scale power grid flow convergence artificial intelligence adjusting method based on a knowledge graph comprises the following steps:
determining a knowledge representation of large-scale power grid flow adjustment, wherein the knowledge representation comprises nodes of large-scale power grid flow and relations among the nodes;
constructing a knowledge graph based on the relation of the knowledge representation;
and sequentially adjusting the large-scale power grid flow under different nodes based on the relation and the adjusting means of each node in the knowledge graph until the large-scale power grid flow is converged.
2. The method according to claim 1, wherein the adjusting the large-scale power grid flow under different nodes in sequence based on the relation and the adjusting means of each node in the knowledge graph comprises:
judging the current state of the large-scale power grid based on the nodes represented by the knowledge;
acquiring a plurality of load flow adjusting means of the current state of the large-scale power grid and an execution sequence executed by the plurality of load flow adjusting means based on the relation expressed by the knowledge;
and sequentially adopting a power flow adjusting means according to the determined execution sequence to adjust the power flow of the large-scale power grid.
3. The method of claim 2, further comprising, before adjusting the large-scale grid power flow at different nodes:
and setting execution weights for the plurality of power flow adjusting means respectively, and determining the execution sequence of the plurality of power flow adjusting means according to the execution weights.
4. The method of claim 1, the triple data structure being in the form of < node, relationship, node >, different nodes and relationships being defined based on different knowledge representations.
5. The method of claim 4, the state in the node comprising: the state of unconvergence, the state of data inspection, the state of calculation setting modification, the state of regional active imbalance and the state of reactive imbalance.
6. The method of claim 5, the knowledge of the unconverged state is represented as: < unconverged state, characterized by a flow convergence flag =1>, < unconverged state, operation, flow calculation >.
7. The method of claim 5, the subsequent state of the unconverged state pointing to the data check state, knowledge of the data check state represented as: < non-convergence state, follow-up state, data check state >, < data check state, operation, check transformer transformation ratio >, < data check state, operation, check parallel transformer parameter >, < data check state, operation, check parallel capacitor reactor >, < data check state, operation, check generator voltage parameter >.
8. The method of claim 5, the subsequent state of the data check state pointing to the computation settings modification state, the knowledge of the computation settings modification state represented as: < data check state, follow-up state, calculation setting modification state >, < calculation setting modification state, operation, modification load flow calculation setting >.
9. The method of claim 5, the subsequent state of the calculation setting modification state pointing to the zone active imbalance state, the knowledge of the zone active imbalance state being represented as: the method comprises the steps of < calculating setting modification state, subsequent state, regional active unbalanced state >, < regional active unbalanced state, operation, checking active unbalanced region >, < regional active unbalanced state, operation, finding a generator to be put in >, < regional active unbalanced state, operation, finding a generator to be quitted >, < regional active unbalanced state, operation, finding a generator to be added with work >, < regional active unbalanced state, operation, finding a generator to be reduced with work >, < regional active unbalanced state, operation and modification of generator parameters >.
10. The method of claim 5, the subsequent states of the regional active imbalance state pointing to the reactive imbalance state, the knowledge of the reactive imbalance state being represented as: the method comprises the steps of (1) finding a maximum error bus >, < a reactive unbalance state, operating, finding a heavy load bus >, < a reactive unbalance state, operating, finding a load bus with low power factor >, < a reactive unbalance state, operating and adding a PV node > < an area active unbalance state, a follow-up state, a reactive unbalance state >, < a reactive unbalance state, operating, finding a load bus with low power factor >, < a reactive unbalance state.
11. The method of claim 4, further comprising: updating the knowledge graph by inference:
and if the tail node of the first triple represented by the knowledge is the same as the head node of the second triple, a new triple can be obtained through inference of the first triple and the second triple.
12. The method of claim 4, further comprising: cleaning the knowledge-graph is achieved by removing duplicate triples in the knowledge representation.
13. A knowledge-graph-based large-scale power grid flow convergence artificial intelligence adjustment system, comprising:
an initial unit for determining a knowledge representation of the large scale grid flow adjustment, the knowledge representation comprising nodes of the large scale grid flow and relations between the nodes;
the construction unit is used for constructing a knowledge graph based on the relation of the knowledge representation;
and the execution unit is used for sequentially adjusting the large-scale power grid flow under different nodes based on the relation and the adjustment means of each node in the knowledge graph until the large-scale power grid flow is converged.
14. The system of claim 13, the execution unit to further:
judging the current state of the large-scale power grid based on the nodes represented by the knowledge;
acquiring a plurality of load flow adjusting means of the current state of the large-scale power grid and an execution sequence executed by the plurality of load flow adjusting means based on the relation expressed by the knowledge;
and sequentially adopting a power flow adjusting means according to the determined execution sequence to adjust the power flow of the large-scale power grid.
15. The system of claim 14, the execution unit to further:
and setting execution weights for the plurality of power flow adjusting means respectively, and determining the execution sequence of the plurality of power flow adjusting means according to the execution weights.
CN202111254305.1A 2021-10-27 2021-10-27 Knowledge graph-based large-scale power grid flow convergence artificial intelligence adjustment method and system Pending CN113919974A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111254305.1A CN113919974A (en) 2021-10-27 2021-10-27 Knowledge graph-based large-scale power grid flow convergence artificial intelligence adjustment method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111254305.1A CN113919974A (en) 2021-10-27 2021-10-27 Knowledge graph-based large-scale power grid flow convergence artificial intelligence adjustment method and system

Publications (1)

Publication Number Publication Date
CN113919974A true CN113919974A (en) 2022-01-11

Family

ID=79243220

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111254305.1A Pending CN113919974A (en) 2021-10-27 2021-10-27 Knowledge graph-based large-scale power grid flow convergence artificial intelligence adjustment method and system

Country Status (1)

Country Link
CN (1) CN113919974A (en)

Similar Documents

Publication Publication Date Title
Ye et al. Multi-objective optimal power flow considering transient stability based on parallel NSGA-II
CN112803404A (en) Self-healing reconstruction planning method and device for power distribution network and terminal
CN109066710A (en) A kind of multi-objective reactive optimization method, apparatus, computer equipment and storage medium
CN111224404B (en) Power flow rapid control method for electric power system with controllable phase shifter
CN110350510A (en) A kind of power distribution network service restoration method considering failure disturbance degree
CN109066728B (en) Online damping coordination control method for multiple interval oscillation modes of extra-high voltage power grid
CN115085202A (en) Power grid multi-region intelligent power collaborative optimization method, device, equipment and medium
CN111030089B (en) Method and system for optimizing PSS (Power System stabilizer) parameters based on moth fire suppression optimization algorithm
CN114094592A (en) Method, system, equipment and storage medium for controlling emergency load of power grid
CN109873406B (en) A kind of electric system weakness route discrimination method
CN115021249A (en) Distribution network transient characteristic equivalence method and system considering distributed photovoltaic
CN103280817B (en) Reactive balance area determining method based on tabu search
CN110994621B (en) Power grid active power flow adjusting method and device based on improved direct current power flow algorithm
Wang et al. Pareto optimization of power system reconstruction using NSGA-II algorithm
CN113328467A (en) Probability voltage stability evaluation method, system, terminal device and medium
CN105896547B (en) A kind of bulk power grid hierarchical voltage control method under wind power integration
CN113919974A (en) Knowledge graph-based large-scale power grid flow convergence artificial intelligence adjustment method and system
CN112103950A (en) Power grid partitioning method based on improved GN splitting algorithm
CN114977191B (en) Static voltage stability analysis method and device and computer storage medium
CN113300367B (en) Online rapid identification method for key section of power grid and power transmission limit making method and device
CN107769245A (en) A kind of pilot bus system of selection for considering wind power fluctuation probability nature
CN114204613A (en) Reactive compensation method and system for offshore wind farm access power system
CN116599067B (en) Micro-grid power quality global optimization method
CN115276055B (en) Energy storage configuration method and system based on power grid frequency spatial distribution characteristics
Zhang et al. Mining transient stability database for rule-based preventive control of power systems

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