CN116565859A - Power grid optimal scheduling system and method based on artificial intelligence - Google Patents

Power grid optimal scheduling system and method based on artificial intelligence Download PDF

Info

Publication number
CN116565859A
CN116565859A CN202310833287.5A CN202310833287A CN116565859A CN 116565859 A CN116565859 A CN 116565859A CN 202310833287 A CN202310833287 A CN 202310833287A CN 116565859 A CN116565859 A CN 116565859A
Authority
CN
China
Prior art keywords
scheduling
network source
power grid
network
time
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202310833287.5A
Other languages
Chinese (zh)
Other versions
CN116565859B (en
Inventor
郑宇�
张轶珠
陈述
曹源
刘屹
李生洋
高子涵
郭蕊
李金灿
都兴宇
邹坤成
秦美琪
陈欣琼
许柳
刘镇宁
潘国栋
陈儒
赵鑫
王彦博
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.)
Liaoyuan Power Supply Co Of State Grid Jilinsheng Electric Power Supply Co
Original Assignee
Liaoyuan Power Supply Co Of State Grid Jilinsheng Electric Power Supply Co
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 Liaoyuan Power Supply Co Of State Grid Jilinsheng Electric Power Supply Co filed Critical Liaoyuan Power Supply Co Of State Grid Jilinsheng Electric Power Supply Co
Priority to CN202310833287.5A priority Critical patent/CN116565859B/en
Publication of CN116565859A publication Critical patent/CN116565859A/en
Application granted granted Critical
Publication of CN116565859B publication Critical patent/CN116565859B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
    • 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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06313—Resource planning in a project environment
    • 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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06315—Needs-based resource requirements planning or analysis
    • 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
    • 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
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/24—Arrangements for preventing or reducing oscillations of power in 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
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
    • H02J3/381—Dispersed generators
    • 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
    • H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
    • H02J3/46—Controlling of the sharing of output between the generators, converters, or transformers
    • H02J3/466—Scheduling the operation of the generators, e.g. connecting or disconnecting generators to meet a given demand
    • 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]
    • 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
    • H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
    • H02J2300/20—The dispersed energy generation being of renewable origin
    • 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)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • Power Engineering (AREA)
  • Marketing (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Quality & Reliability (AREA)
  • Development Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Educational Administration (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biodiversity & Conservation Biology (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 an artificial intelligence-based power grid optimization scheduling system and method, and belongs to the technical field of power grid scheduling. Constructing a power grid framework cloud platform, analyzing regulation and control relations among network sources, forming a power grid framework connection tree model, and sensing the variation condition of the network sources in real time; receiving a scheduling demand instruction through a power grid framework cloud platform, generating a data tag and a scheduling list, randomly optimizing a group of scheduling time sets, and dividing time intervals; performing corresponding mapping of time intervals on the demand time, verifying that the random optimization meets the conditions, and generating a random optimization sample scheduling list set; analyzing random optimization fluctuation conditions of a scheduling list; and the power grid data system can be expanded in real time and flexibly reduced so as to cope with randomness brought by new energy grid connection, and the random demand variation can be positioned to different time intervals to carry out dimension reduction and microminiaturization processing, so that the overall volatility of the power grid system is determined, and the scheduling risk condition of each network source of the new energy market is dealt with.

Description

Power grid optimal scheduling system and method based on artificial intelligence
Technical Field
The invention relates to the technical field of power grid dispatching, in particular to a power grid optimization dispatching system and method based on artificial intelligence.
Background
The power grid dispatching is a core link of safe and stable operation of the power system, and the traditional power grid dispatching mode is comprehensively considered by a dispatching mechanism according to a national directive plan, a local government frame agreement, a annual and monthly electricity purchasing plan and other medium-long-term plans, and by combining the conditions of the system operation condition, the load prediction level and the like on the second day and according to the principles of unified dispatching and hierarchical management;
at present, with the large-scale grid connection of new energy sources with strong randomness and volatility and the large-scale access of interactive equipment such as electric automobiles, distributed power supplies and the like, the scheduling automation requirement is higher; when new energy is developed into main energy, the scheduling mode is more rigid facing to the conventional power supply, the new energy needs to be considered to play a larger role in ensuring the safety of the system and the power supply, and further, as the new energy duty ratio is improved year by year, the safety foundation of the power grid is changed, the mechanism of the power grid operation is synchronously changed, and the scheduling mode is also optimized.
Disclosure of Invention
The invention aims to provide an artificial intelligence-based power grid optimization scheduling system and method, which are used for solving the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme:
an artificial intelligence-based power grid optimization scheduling system comprises: the system comprises a power grid framework cloud platform module, a random optimization module, a mapping verification module and a random optimization fluctuation analysis module;
the power grid framework cloud platform module is used for constructing a power grid framework cloud platform, comprehensively planning all network sources in a power grid system, analyzing regulation and control relations among the network sources, locking to form a transmission network source layer, forming a power grid framework connection tree model according to the regulation and control relations, sensing the variation condition of the network sources in the power grid system in real time, and updating the power grid framework connection tree model in real time;
the random optimization module is used for receiving the dispatching demand instruction of each network source through the power grid framework cloud platform in each dispatching period, generating a data tag and a dispatching list according to the dispatching demand instruction, wherein the data tag comprises the number of the network sources, the demand time and the dispatching demand value contained in a transmission network source layer, randomly optimizing a group of dispatching time sets, and dividing time intervals according to the dispatching time sets;
the mapping verification module is used for carrying out corresponding mapping of time intervals on the demand time according to the scheduling time set, generating a section network source set, verifying that the random optimization meets the conditions according to the section network source set, extracting all scheduling time sets for verifying that the random optimization meets the conditions, and generating a random optimization sample scheduling list set;
the random optimization fluctuation analysis module analyzes random optimization fluctuation conditions of any one scheduling list according to the random optimization sample list set and outputs a scheduling time set corresponding to the minimum random optimization fluctuation value.
Further, the power grid framework cloud platform module further comprises a regulation and control relation analysis unit and a power grid framework connection tree model unit;
the regulation and control relation analysis unit is used for constructing a power grid framework cloud platform, integrally planning all network sources in a power grid system, uniformly coding all the network sources, identifying a line connection mode among the network sources in the power grid system, locking the regulation and control relation among the network sources according to the line connection mode, and when the network source A is the network source i To network source A j When the regulation and control are carried out, N net removing sources A are adopted in the middle i And network source A j When other network sources except the network source are transmitted, if N is more than or equal to 1, marking all other network sources participating in transmission in the middle as a transmission network source layer, and marking the network source A as a transmission network source layer i With network sourceA j The regulation and control relation between the two components is as follows: network source A i Indirectly through the transmission network source layer to the network source A j Regulating and controlling, and is marked as A i Conveying network source layer → A j The method comprises the steps of carrying out a first treatment on the surface of the If N is equal to 0, network source A i With network source A j The regulation and control relation between the two components is as follows: network source A i Directly to network source A j Regulating and controlling, and is marked as A i →A j The method comprises the steps of carrying out a first treatment on the surface of the Wherein N is a natural number, i and j both represent network source codes, and i is not equal to j;
the power grid framework connection tree model unit forms a power grid framework connection tree model according to the regulation and control relation, expands the power grid framework connection tree model when a new network source is connected in the power grid system, reduces the power grid framework connection tree model when the original network source is deleted in the power grid system, and refreshes the power grid framework connection tree model when the regulation and control relation in the power grid system is changed.
Further, the random optimization module further comprises a data tag unit and a randomization unit;
the data tag unit is configured to send a scheduling demand command to a grid framework cloud platform by each network source in a kth scheduling period, where one network source correspondingly sends a scheduling demand, the grid framework cloud platform coordinates all received scheduling demands, and generates a scheduling list of the kth scheduling period, where the scheduling list is attached with a data tag of each scheduling request, and the data tag of any one scheduling request is denoted as L (a i )；[N(A i )，t(A i )，SV(A i )]Wherein N (A i ) Representing network source A i Conveying the number, t (A), of network sources contained in a network source layer in a corresponding regulation and control relation i ) Representing network source A i Corresponding to the time of demand, SV (A) i ) Representing network source A i Corresponding to the scheduling requirement value, marking the scheduling list of the kth scheduling period as SL k Sequencing the data labels in the scheduling list according to the time required;
the randomizing unit is used for randomly optimizing a group of scheduling time sets and is marked as ST m ={T 0 ，T 1 ，T 2 ，...，T w }, wherein T is 1 ，T 2 ，...，T w Randomly optimized 1,2,..w scheduling times, T 0 Is a fixed value and T 0 =0; according to the set of scheduling times ST m Generating w time intervals, wherein the a-th time interval is recorded as R a ：T a-1 ～T a Wherein T is a-1 、T a ∈ST m And a is more than or equal to 1 and less than or equal to w, and m represents the mth random optimization.
Further, the mapping verification module further comprises a mapping unit and a verification unit;
the mapping unit is used for mapping the scheduling list SL k Each demand time of (1) is set according to the scheduling time m Corresponding mapping is carried out on the corresponding generated time interval, and the time interval R is counted a The network source corresponding to the mapped demand time is generated and an interval network source set is generated and is recorded as SV (R) a )；
The verification unit verifies that the random optimization meets the conditions according to the interval network source set, and a specific verification formula is as follows:
∑ Ai∈SVa SV(A i )≤Max(SV)
∑ 1≤a≤w NUM[SV(R a )]=NUM(SL k )
wherein ai=a i ，SVa=SV(R a )，NUM[SV(R a )]Representing a time interval R b Section network source set SV (R a ) The number of network sources contained in the network, max (SV) represents the maximum demand value which can be scheduled by a node at a single scheduling time, NUM (SL) k ) Representing a schedule list SL k The number of network sources contained in the network;
if the random optimization is verified to meet the condition, the random optimization can be performed, otherwise, the random optimization is performed again; and extracting all scheduling time sets which verify that the random optimization meets the conditions, and generating a random optimization sample scheduling list set.
Further, the random optimization fluctuation analysis module further comprises a random optimization fluctuation value calculation unit and an artificial intelligent screening unit;
the random optimization fluctuation value calculation unit calculates the random optimization fluctuation value of any scheduling list according to the random optimization sample list set, and the specific calculation formula is as follows:
RS(ST m )=∑ 1≤a、b≤w {[∑ Ai∈SVa SV(A i )-∑ Aj∈SVb SV(A j )]/[∑ Ai∈SVa N(A i )-∑ Aj∈SVb N(A j )]}
wherein RS (ST) m ) Representing a set of scheduling times ST m Randomly optimized fluctuation value of (1), SV (A) j ) Representing network source A j N (A) corresponding to the scheduling requirement value j ) Representing network source A j The corresponding regulation and control relation conveys the network source quantity contained in the network source layer, and aj=a j ，SVb=SV(R b )，SV(R b ) Representing a time interval R b A is not equal to b;
the artificial intelligence screening unit is used for selecting a scheduling time set corresponding to the random optimization fluctuation value with the minimum value from the random optimization sample list set, and sending the scheduling time set to staff through the power grid architecture cloud platform.
An artificial intelligence-based power grid optimization scheduling method comprises the following steps:
step S100: constructing a power grid framework cloud platform, comprehensively planning all network sources in a power grid system, analyzing regulation and control relations among all the network sources, locking to form a transmission network source layer, forming a power grid framework connection tree model according to the regulation and control relations, sensing the variation condition of the network sources in the power grid system in real time, and updating the power grid framework connection tree model in real time;
step S200: in each scheduling period, receiving scheduling demand instructions of all network sources through a power grid framework cloud platform, generating a data tag and a scheduling list according to the scheduling demand instructions, wherein the data tag comprises the number of the network sources, the demand time and the scheduling demand value contained in a transmission network source layer, randomly optimizing a group of scheduling time sets, and dividing time intervals according to the scheduling time sets;
step S300: according to the scheduling time set, carrying out corresponding mapping of time intervals on the demand time to generate a section network source set, verifying that the random optimization meets the conditions according to the section network source set, extracting all scheduling time sets verifying that the random optimization meets the conditions, and generating a random optimization sample scheduling list set;
step S400: according to the random optimization sample list set, analyzing random optimization fluctuation conditions of any one scheduling list, and outputting a scheduling time set corresponding to the minimum random optimization fluctuation value.
Further, the specific implementation process of the step S100 includes:
step S101: constructing a power grid framework cloud platform, comprehensively planning all network sources in a power grid system, uniformly coding all the network sources, identifying a line connection mode among the network sources in the power grid system, locking regulation and control relations among the network sources according to the line connection mode, and when the network source A is the network source i To network source A j When the regulation and control are carried out, N net removing sources A are adopted in the middle i And network source A j When other network sources except the network source are transmitted, if N is more than or equal to 1, marking all other network sources participating in transmission in the middle as a transmission network source layer, and marking the network source A as a transmission network source layer i With network source A j The regulation and control relation between the two components is as follows: network source A i Indirectly through the transmission network source layer to the network source A j Regulating and controlling, and is marked as A i Conveying network source layer → A j The method comprises the steps of carrying out a first treatment on the surface of the If N is equal to 0, network source A i With network source A j The regulation and control relation between the two components is as follows: network source A i Directly to network source A j Regulating and controlling, and is marked as A i →A j The method comprises the steps of carrying out a first treatment on the surface of the Wherein N is a natural number, i and j both represent network source codes, and i is not equal to j;
step S102: forming a power grid framework connection tree model according to the regulation and control relation, expanding the power grid framework connection tree model when a new network source is connected in the power grid system, reducing the power grid framework connection tree model when the original network source is deleted in the power grid system, and refreshing the power grid framework connection tree model when the regulation and control relation in the power grid system is changed;
according to the method, due to the fact that new energy sources with strong randomness and volatility are connected in a large scale, a traditional regulation and control operation system is not suitable for flexible market environments, a power grid framework cloud platform is further built, a power grid framework connection tree model is formed, and therefore a power grid data system can be expanded and reduced flexibly in real time, and scheduling data can be obtained in real time.
Further, the specific implementation process of the step S200 includes:
step S201: in the kth scheduling period, each network source sends a scheduling demand instruction to a network architecture cloud platform, wherein one network source correspondingly sends scheduling demands once, the network architecture cloud platform performs overall planning on all received scheduling demands, and generates a scheduling list of the kth scheduling period, wherein the scheduling list is attached with a data tag of each scheduling request, and the data tag of any scheduling request is marked as L (A i )；[N(A i )，t(A i )，SV(A i )]Wherein N (A i ) Representing network source A i Conveying the number, t (A), of network sources contained in a network source layer in a corresponding regulation and control relation i ) Representing network source A i Corresponding to the time of demand, SV (A) i ) Representing network source A i Corresponding to the scheduling requirement value, marking the scheduling list of the kth scheduling period as SL k Sequencing the data labels in the scheduling list according to the time required;
step S202: randomly optimizing a set of scheduling time sets, denoted ST m ={T 0 ，T 1 ，T 2 ，...，T w }, wherein T is 1 ，T 2 ，...，T w Randomly optimized 1,2,..w scheduling times, T 0 Is a fixed value and T 0 =0; according to the set of scheduling times ST m Generating w time intervals, wherein the a-th time interval is recorded as R a ：T a-1 ～T a Wherein T is a-1 、T a ∈ST m And a is more than or equal to 1 and less than or equal to w, and m represents the mth random optimization.
Further, the implementation process of the step S300 includes:
step S301: will beScheduling list SL k Each demand time of (1) is set according to the scheduling time m Corresponding mapping is carried out on the corresponding generated time interval, and the time interval R is counted a The network source corresponding to the mapped demand time is generated and an interval network source set is generated and is recorded as SV (R) a )；
Step S302: according to the interval network source set, the random optimization is verified to meet the condition, and a specific verification formula is as follows:
∑ Ai∈SVa SV(A i )≤Max(SV)
∑ 1≤a≤w NUM[SV(R a )]=NUM(SL k )
wherein ai=a i ，SVa=SV(R a )，NUM[SV(R a )]Representing a time interval R b Section network source set SV (R a ) The number of network sources contained in the network, max (SV) represents the maximum demand value which can be scheduled by a node at a single scheduling time, NUM (SL) k ) Representing a schedule list SL k The number of network sources contained in the network;
if the random optimization is verified to meet the condition, the random optimization can be performed, otherwise, the random optimization is performed again; extracting all scheduling time sets which verify that the random optimization meets the conditions, and generating a random optimization sample scheduling list set;
according to the method, due to the market randomness brought by the new energy grid connection, the market randomness refers to the market increase and decrease change condition of electric vehicle charging and the flexible condition of electric vehicle charging amount demand, so that the traditional scheduling mode is difficult to meet the market randomness, and the purpose of randomly optimizing a group of scheduling time is to position the randomized demand change to different time intervals to meet the dimension reduction and micro quantization, and then the random optimization needs to meet two conditions simultaneously, wherein the formula is Ai∈SVa SV(A i ) Max (SV) represents the first condition that randomization needs to satisfy, i.e., the total scheduling demand Sigma satisfied in the corresponding time interval at each scheduling time node Ai∈SVa SV(A i ) Maximum demand value Max (SV) schedulable by a node at a single scheduling time cannot be exceededThe maximum demand value which can be scheduled by the inter-node is a single maximum electricity value which can be scheduled in an overall way according to the power generation condition of the power grid system; meanwhile, the formula sigma 1≤a≤w NUM[SV(R a )]=NUM(SL k ) It is necessary to cover all the scheduling demands under a random optimization group of scheduling time sets, and any scheduling demands cannot be omitted.
Further, the specific implementation process of the step S400 includes:
step S401: according to the random optimization sample list set, calculating random optimization fluctuation values of any scheduling list, wherein the specific calculation formula is as follows:
RS(ST m )=∑ 1≤a、b≤w {[∑ Ai∈SVa SV(A i )-∑ Aj∈SVb SV(A j )]/[∑ Ai∈SVa N(A i )-∑ Aj∈SVb N(A j )]}
wherein RS (ST) m ) Representing a set of scheduling times ST m Randomly optimized fluctuation value of (1), SV (A) j ) Representing network source A j N (A) corresponding to the scheduling requirement value j ) Representing network source A j The corresponding regulation and control relation conveys the network source quantity contained in the network source layer, and aj=a j ，SVb=SV(R b )，SV(R b ) Representing a time interval R b A is not equal to b;
step S402: selecting a scheduling time set corresponding to the minimum random optimization fluctuation value from the random optimization sample list set, and sending the scheduling time set to staff through a power grid architecture cloud platform;
according to the method, when the number of the network sources contained in the network source layer is excessive, the method means that more line loss waste or excessive reactive load is generated in the electric energy conveying process, the overall stability of the power grid system is reduced, and the formula is shown as sigma Ai∈SVa SV(A i )-∑ Aj∈SVb SV(A j ) Representing the change in the scheduling requirement value when transitioning from one time interval to another, equation Σ Ai∈SVa N(A i )-∑ Aj∈SVb N(A j ) Representing transfer from one time interval to anotherAnd when the time interval is counted, the hidden loss condition of the power grid system is analyzed by the ratio of the change condition of the dispatching requirement value to the hidden loss condition, so that the fluctuation of the power grid system when one time interval is transferred to the other time interval is determined, and then the overall fluctuation value of the power grid system under the dispatching time set is calculated through the overall accumulation analysis under the full dispatching time set domain, wherein the larger the fluctuation value is, the optimization under the dispatching time set is represented, the larger the overall instability of the power grid system is, and the larger the dispatching risk of each network source aiming at the new energy market is.
Compared with the prior art, the invention has the following beneficial effects: according to the power grid optimization scheduling system and method based on the artificial intelligence, the regulation and control relationship between network sources is analyzed by constructing a power grid framework cloud platform to form a power grid framework connection tree model, and the change condition of the network sources is perceived in real time; receiving a scheduling demand instruction through a power grid framework cloud platform, generating a data tag and a scheduling list, randomly optimizing a group of scheduling time sets, and dividing time intervals; performing corresponding mapping of time intervals on the demand time, verifying that the random optimization meets the conditions, and generating a random optimization sample scheduling list set; analyzing random optimization fluctuation conditions of a scheduling list; and the power grid data system can be expanded in real time and flexibly reduced so as to cope with randomness brought by new energy grid connection, and the random demand variation can be positioned to different time intervals to carry out dimension reduction and microminiaturization processing, so that the overall volatility of the power grid system is determined, and the scheduling risk condition of each network source of the new energy market is dealt with.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic diagram of an artificial intelligence based power grid optimization scheduling system;
fig. 2 is a schematic diagram of steps of an artificial intelligence-based power grid optimization scheduling method.
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.
Referring to fig. 1-2, the present invention provides the following technical solutions:
referring to fig. 1, in a first embodiment: provided is an artificial intelligence-based power grid optimization scheduling system, which comprises: the system comprises a power grid framework cloud platform module, a random optimization module, a mapping verification module and a random optimization fluctuation analysis module;
the power grid framework cloud platform module is used for constructing a power grid framework cloud platform, comprehensively planning all network sources in a power grid system, analyzing regulation and control relations among the network sources, locking to form a transmission network source layer, forming a power grid framework connection tree model according to the regulation and control relations, sensing the variation condition of the network sources in the power grid system in real time, and updating the power grid framework connection tree model in real time;
the power grid framework cloud platform module further comprises a regulation and control relation analysis unit and a power grid framework connection tree model unit;
the regulation and control relation analysis unit is used for constructing a power grid framework cloud platform, integrally planning all network sources in a power grid system, uniformly coding all the network sources, identifying a line connection mode among the network sources in the power grid system, locking the regulation and control relation among the network sources according to the line connection mode, and judging the regulation and control relation as a network source A i To network source A j When the regulation and control are carried out, N net removing sources A are adopted in the middle i And network source A j When other network sources except the network source are transmitted, if N is more than or equal to 1, marking all other network sources participating in transmission in the middle as a transmission network source layer, and marking the network source A as a transmission network source layer i With network source A j The regulation and control relation between the two components is as follows: network source A i Indirectly through the transmission network source layer to the network source A j Regulating and controlling, and is marked as A i Conveying network source layer → A j The method comprises the steps of carrying out a first treatment on the surface of the If N is equal to 0, network source A i With network source A j The regulation and control relation between the two components is as follows: network source A i Directly to network source A j Regulating and controlling, and is marked as A i →A j The method comprises the steps of carrying out a first treatment on the surface of the Wherein N is a natural number, i and j both represent network source codes, and i is not equal to j;
the power grid framework connection tree model unit forms a power grid framework connection tree model according to the regulation and control relation, expands the power grid framework connection tree model when a new network source is connected in the power grid system, reduces the power grid framework connection tree model when the original network source is deleted in the power grid system, and refreshes the power grid framework connection tree model when the regulation and control relation in the power grid system is changed;
the random optimization module is used for receiving the dispatching demand instruction of each network source through the power grid framework cloud platform in each dispatching period, generating a data tag and a dispatching list according to the dispatching demand instruction, wherein the data tag comprises the number of the network sources, the demand time and the dispatching demand value contained in a transmission network source layer, randomly optimizing a group of dispatching time sets, and dividing time intervals according to the dispatching time sets;
the random optimization module further comprises a data tag unit and a randomization unit;
the data tag unit is used for sending a scheduling demand instruction to the grid framework cloud platform by each network source in the kth scheduling period, wherein one network source correspondingly sends one scheduling demand, the grid framework cloud platform performs overall arrangement on all received scheduling demands, a scheduling list of the kth scheduling period is generated, the scheduling list is attached with a data tag of each scheduling request, and the data tag of any one scheduling request is marked as L (A i )；[N(A i )，t(A i )，SV(A i )]Wherein N (A i ) Representing network source A i Conveying the number, t (A), of network sources contained in a network source layer in a corresponding regulation and control relation i ) Representing network source A i Corresponding to the time of demand, SV (A) i ) Representing network source A i Corresponding to the scheduling requirement value, the scheduling list of the kth scheduling period is recorded as SL k Will be scheduledThe data labels in the list are sequenced in time sequence according to the required time;
randomizing unit for randomly optimizing a set of scheduling time sets, denoted as ST m ={T 0 ，T 1 ，T 2 ，...，T w }, wherein T is 1 ，T 2 ，...，T w Randomly optimized 1,2,..w scheduling times, T 0 Is a fixed value and T 0 =0; according to the set of scheduling times ST m Generating w time intervals, wherein the a-th time interval is recorded as R a ：T a-1 ～T a Wherein T is a-1 、T a ∈ST m And a is more than or equal to 1 and less than or equal to w, m represents the mth random optimization;
the mapping verification module is used for carrying out corresponding mapping of time intervals on the demand time according to the scheduling time set, generating an interval network source set, verifying that the random optimization meets the conditions according to the interval network source set, extracting all scheduling time sets for verifying that the random optimization meets the conditions, and generating a random optimization sample scheduling list set;
the mapping verification module further comprises a mapping unit and a verification unit;
mapping unit for mapping the scheduling list SL k Each demand time of (1) is set according to the scheduling time m Corresponding mapping is carried out on the corresponding generated time interval, and the time interval R is counted a The network source corresponding to the mapped demand time is generated and an interval network source set is generated and is recorded as SV (R) a )；
The verification unit verifies that the random optimization meets the conditions according to the interval network source set, and the specific verification formula is as follows:
∑ Ai∈SVa SV(A i )≤Max(SV)
∑ 1≤a≤w NUM[SV(R a )]=NUM(SL k )
wherein ai=a i ，SVa=SV(R a )，NUM[SV(R a )]Representing a time interval R b Section network source set SV (R a ) The number of network sources contained in the network, max (SV) represents a single scheduling time nodeMaximum demand value that can be scheduled, NUM (SL k ) Representing a schedule list SL k The number of network sources contained in the network;
if the random optimization is verified to meet the condition, the random optimization can be performed, otherwise, the random optimization is performed again; extracting all scheduling time sets which verify that the random optimization meets the conditions, and generating a random optimization sample scheduling list set;
for example, a set of scheduling times {6 months 10 days, 7 months 15 days, 8 months 12 days }, the cloud platform receives a scheduling requirement with { net source 1:5,6 months, 4 days, 100; network source 2:0,6 months, 6 days, 100; network source 3:2,6 months, 8 days, 80}, then Σ Ai∈SVa SV(A i ) =100+100+80=280, num [ sv (0-6 months 10 days)]=3; { network source 4:3,7 months, 4 days, 100; network source 5:1,7 months, 6 days, 80; network source 6:1,7 months, 8 days, 80}, then Σ Ai∈SVa SV(A i ) =100+80+80=260, num [ sv (6 month 10 day-7 month 15 day)]=3；
The random optimization fluctuation analysis module analyzes random optimization fluctuation conditions of any one scheduling list according to the random optimization sample list set and outputs a scheduling time set corresponding to the minimum random optimization fluctuation value;
the random optimization fluctuation analysis module further comprises a random optimization fluctuation value calculation unit and an artificial intelligent screening unit;
the random optimization fluctuation value calculation unit calculates random optimization fluctuation values of any one scheduling list according to a random optimization sample list set, and the specific calculation formula is as follows:
RS(ST m )=∑ 1≤a、b≤w {[∑ Ai∈SVa SV(A i )-∑ Aj∈SVb SV(A j )]/[∑ Ai∈SVa N(A i )-∑ Aj∈SVb N(A j )]}
wherein RS (ST) m ) Representing a set of scheduling times ST m Randomly optimized fluctuation value of (1), SV (A) j ) Representing network source A j N (A) corresponding to the scheduling requirement value j ) Representing network source A j The corresponding regulation and control relation conveys the network source quantity contained in the network source layer, and aj=a j ，SVb=SV(R b )，SV(R b ) Representing a time interval R b A is not equal to b;
for example, the time interval shifts from 0-6 months 10 days to 6 months 10 days-7 months 15 days, [ Σ) Ai∈SVa SV(A i )-∑ Aj∈ SVb SV(A j )]/[∑ Ai∈SVa N(A i )-∑ Aj∈SVb N(A j )]=（280-260）/[5+0+2-（3+1+1）]=10；
The artificial intelligent screening unit is used for selecting a scheduling time set corresponding to the random optimization fluctuation value with the minimum value from the random optimization sample list set, and sending the scheduling time set to staff through the power grid architecture cloud platform.
Referring to fig. 2, in the second embodiment: the utility model provides an artificial intelligence-based power grid optimization scheduling method, which comprises the following steps:
constructing a power grid framework cloud platform, comprehensively planning all network sources in a power grid system, analyzing regulation and control relations among all the network sources, locking to form a transmission network source layer, forming a power grid framework connection tree model according to the regulation and control relations, sensing the variation condition of the network sources in the power grid system in real time, and updating the power grid framework connection tree model in real time;
constructing a power grid framework cloud platform, comprehensively planning all network sources in a power grid system, uniformly coding all the network sources, identifying a line connection mode among the network sources in the power grid system, locking regulation and control relations among the network sources according to the line connection mode, and when the network source A is the network source i To network source A j When the regulation and control are carried out, N net removing sources A are adopted in the middle i And network source A j When other network sources except the network source are transmitted, if N is more than or equal to 1, marking all other network sources participating in transmission in the middle as a transmission network source layer, and marking the network source A as a transmission network source layer i With network source A j The regulation and control relation between the two components is as follows: network source A i Indirectly through the transmission network source layer to the network source A j Regulating and controlling, and is marked as A i Conveying network source layer → A j The method comprises the steps of carrying out a first treatment on the surface of the If N is equal to 0, network source A i With network source A j The regulation and control relation between the two components is as follows: network source A i Directly to network source A j Regulating and controlling, and is marked as A i →A j The method comprises the steps of carrying out a first treatment on the surface of the Wherein N is a natural number, i and j both represent network source codes, and i is not equal to j;
forming a power grid framework connection tree model according to the regulation and control relation, expanding the power grid framework connection tree model when a new network source is connected in the power grid system, reducing the power grid framework connection tree model when the original network source is deleted in the power grid system, and refreshing the power grid framework connection tree model when the regulation and control relation in the power grid system is changed;
in each scheduling period, receiving scheduling demand instructions of all network sources through a power grid framework cloud platform, generating a data tag and a scheduling list according to the scheduling demand instructions, wherein the data tag comprises the number of the network sources, the demand time and the scheduling demand value contained in a transmission network source layer, randomly optimizing a group of scheduling time sets, and dividing time intervals according to the scheduling time sets;
in the kth scheduling period, each network source sends a scheduling demand instruction to a power grid framework cloud platform, wherein one network source correspondingly sends scheduling demands once, the power grid framework cloud platform performs overall planning on all received scheduling demands, a scheduling list of the kth scheduling period is generated, a data tag of each scheduling request is attached to the scheduling list, and the data tag of any scheduling request is marked as L (A i )；[N(A i )，t(A i )，SV(A i )]Wherein N (A i ) Representing network source A i Conveying the number, t (A), of network sources contained in a network source layer in a corresponding regulation and control relation i ) Representing network source A i Corresponding to the time of demand, SV (A) i ) Representing network source A i Corresponding to the scheduling requirement value, the scheduling list of the kth scheduling period is recorded as SL k Sequencing the data labels in the scheduling list according to the time required;
randomly optimizing a set of scheduling time sets, denoted ST m ={T 0 ，T 1 ，T 2 ，...，T w }, wherein T is 1 ，T 2 ，...，T w Randomly optimized 1,2,..w scheduling times, T 0 Is a fixed value and T 0 =0; according to the set of scheduling times ST m Generating w time intervals, wherein the a-th time interval is recorded as R a ：T a-1 ～T a Wherein T is a-1 、T a ∈ST m And a is more than or equal to 1 and less than or equal to w, m represents the mth random optimization;
according to the scheduling time set, carrying out corresponding mapping of time intervals on the demand time to generate a section network source set, verifying that the random optimization meets the conditions according to the section network source set, extracting all scheduling time sets verifying that the random optimization meets the conditions, and generating a random optimization sample scheduling list set;
will schedule list SL k Each demand time of (1) is set according to the scheduling time m Corresponding mapping is carried out on the corresponding generated time interval, and the time interval R is counted a The network source corresponding to the mapped demand time is generated and an interval network source set is generated and is recorded as SV (R) a )；
According to the interval network source set, the random optimization is verified to meet the condition, and a specific verification formula is as follows:
∑ Ai∈SVa SV(A i )≤Max(SV)
∑ 1≤a≤w NUM[SV(R a )]=NUM(SL k )
wherein ai=a i ，SVa=SV(R a )，NUM[SV(R a )]Representing a time interval R b Section network source set SV (R a ) The number of network sources contained in the network, max (SV) represents the maximum demand value which can be scheduled by a node at a single scheduling time, NUM (SL) k ) Representing a schedule list SL k The number of network sources contained in the network;
if the random optimization is verified to meet the condition, the random optimization can be performed, otherwise, the random optimization is performed again; extracting all scheduling time sets which verify that the random optimization meets the conditions, and generating a random optimization sample scheduling list set;
according to the random optimization sample list set, analyzing random optimization fluctuation conditions of any scheduling list, and outputting a scheduling time set corresponding to the minimum random optimization fluctuation value;
according to the random optimization sample list set, calculating random optimization fluctuation values of any scheduling list, wherein the specific calculation formula is as follows:
RS(ST m )=∑ 1≤a、b≤w {[∑ Ai∈SVa SV(A i )-∑ Aj∈SVb SV(A j )]/[∑ Ai∈SVa N(A i )-∑ Aj∈SVb N(A j )]}
wherein RS (ST) m ) Representing a set of scheduling times ST m Randomly optimized fluctuation value of (1), SV (A) j ) Representing network source A j N (A) corresponding to the scheduling requirement value j ) Representing network source A j The corresponding regulation and control relation conveys the network source quantity contained in the network source layer, and aj=a j ，SVb=SV(R b )，SV(R b ) Representing a time interval R b A is not equal to b;
and selecting a corresponding scheduling time set with the minimum random optimization fluctuation value from the random optimization sample list set, and sending the scheduling time set to staff through the power grid architecture cloud platform.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention and is not intended to limit the present invention, but although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the technical solutions described in the foregoing embodiments, or equivalents may be substituted for some of the technical features thereof. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. An artificial intelligence-based power grid optimization scheduling method is characterized by comprising the following steps of:
step S100: constructing a power grid framework cloud platform, comprehensively planning all network sources in a power grid system, analyzing regulation and control relations among all the network sources, locking to form a transmission network source layer, forming a power grid framework connection tree model according to the regulation and control relations, sensing the variation condition of the network sources in the power grid system in real time, and updating the power grid framework connection tree model in real time;
step S200: in each scheduling period, receiving scheduling demand instructions of all network sources through a power grid framework cloud platform, generating a data tag and a scheduling list according to the scheduling demand instructions, wherein the data tag comprises the number of the network sources, the demand time and the scheduling demand value contained in a transmission network source layer, randomly optimizing a group of scheduling time sets, and dividing time intervals according to the scheduling time sets;
step S300: according to the scheduling time set, carrying out corresponding mapping of time intervals on the demand time to generate a section network source set, verifying that the random optimization meets the conditions according to the section network source set, extracting all scheduling time sets verifying that the random optimization meets the conditions, and generating a random optimization sample scheduling list set;
step S400: according to the random optimization sample list set, analyzing random optimization fluctuation conditions of any one scheduling list, and outputting a scheduling time set corresponding to the minimum random optimization fluctuation value.
2. The power grid optimization scheduling method based on artificial intelligence according to claim 1, wherein the specific implementation process of step S100 includes:
step S101: constructing a power grid framework cloud platform, comprehensively planning all network sources in a power grid system, and carrying out power grid framework cloud platform on all network sourcesThe network sources perform unified coding, the line connection mode among all the network sources in the power grid system is identified, the regulation and control relationship among all the network sources is locked according to the line connection mode, and when the network source A i To network source A j When the regulation and control are carried out, N net removing sources A are adopted in the middle i And network source A j When other network sources except the network source are transmitted, if N is more than or equal to 1, marking all other network sources participating in transmission in the middle as a transmission network source layer, and marking the network source A as a transmission network source layer i With network source A j The regulation and control relation between the two components is as follows: network source A i Indirectly through the transmission network source layer to the network source A j Regulating and controlling, and is marked as A i Conveying network source layer → A j The method comprises the steps of carrying out a first treatment on the surface of the If N is equal to 0, network source A i With network source A j The regulation and control relation between the two components is as follows: network source A i Directly to network source A j Regulating and controlling, and is marked as A i →A j The method comprises the steps of carrying out a first treatment on the surface of the Wherein N is a natural number, i and j both represent network source codes, and i is not equal to j;
step S102: according to the regulation and control relation, a power grid framework connection tree model is formed, when a new network source is connected in the power grid system, the power grid framework connection tree model is expanded, when the original network source is deleted in the power grid system, the power grid framework connection tree model is reduced, and when the regulation and control relation in the power grid system is changed, the power grid framework connection tree model is refreshed.
3. The power grid optimization scheduling method based on artificial intelligence according to claim 2, wherein the specific implementation process of step S200 includes:
step S201: in the kth scheduling period, each network source sends a scheduling demand instruction to a network architecture cloud platform, wherein one network source correspondingly sends scheduling demands once, the network architecture cloud platform performs overall planning on all received scheduling demands, and generates a scheduling list of the kth scheduling period, wherein the scheduling list is attached with a data tag of each scheduling request, and the data tag of any scheduling request is marked as L (A i )；[N(A i )，t(A i )，SV(A i )]Wherein N (A i ) Representing network source A i Conveying the number, t (A), of network sources contained in a network source layer in a corresponding regulation and control relation i ) Representing network source A i Corresponding to the time of demand, SV (A) i ) Representing network source A i Corresponding to the scheduling requirement value, marking the scheduling list of the kth scheduling period as SL k Sequencing the data labels in the scheduling list according to the time required;
step S202: randomly optimizing a set of scheduling time sets, denoted ST m ={T 0 ，T 1 ，T 2 ，...，T w }, wherein T is 1 ，T 2 ，...，T w Randomly optimized 1,2,..w scheduling times, T 0 Is a fixed value and T 0 =0; according to the set of scheduling times ST m Generating w time intervals, wherein the a-th time interval is recorded as R a ：T a-1 ～T a Wherein T is a-1 、T a ∈ST m And a is more than or equal to 1 and less than or equal to w, and m represents the mth random optimization.
4. The power grid optimization scheduling method based on artificial intelligence according to claim 3, wherein the specific implementation process of the step S300 includes:
step S301: will schedule list SL k Each demand time of (1) is set according to the scheduling time m Corresponding mapping is carried out on the corresponding generated time interval, and the time interval R is counted a The network source corresponding to the mapped demand time is generated and an interval network source set is generated and is recorded as SV (R) a )；
Step S302: according to the interval network source set, the random optimization is verified to meet the condition, and a specific verification formula is as follows:
∑ Ai∈SVa SV(A i )≤Max(SV)
∑ 1≤a≤w NUM[SV(R a )]=NUM(SL k )
wherein ai=a i ，SVa=SV(R a )，NUM[SV(R a )]Representing a time interval R b Section network source set SV (R a ) The number of network sources contained in the network, max (SV) represents the maximum demand value that a node can schedule at a single scheduling time, NUM (SL) k ) Representing a schedule list SL k The number of network sources contained in the network;
if the random optimization is verified to meet the condition, the random optimization can be performed, otherwise, the random optimization is performed again; and extracting all scheduling time sets which verify that the random optimization meets the conditions, and generating a random optimization sample scheduling list set.
5. The method for optimizing and scheduling the power grid based on the artificial intelligence according to claim 4, wherein the specific implementation process of the step S400 includes:
step S401: according to the random optimization sample list set, calculating random optimization fluctuation values of any scheduling list, wherein the specific calculation formula is as follows:
RS(ST m )=∑ 1≤a、b≤w {[∑ Ai∈SVa SV(A i )-∑ Aj∈SVb SV(A j )]/[∑ Ai∈SVa N(A i )-∑ Aj∈SVb N(A j )]}
wherein RS (ST) m ) Representing a set of scheduling times ST m Randomly optimized fluctuation value of (1), SV (A) j ) Representing network source A j N (A) corresponding to the scheduling requirement value j ) Representing network source A j The corresponding regulation and control relation conveys the network source quantity contained in the network source layer, and aj=a j ，SVb=SV(R b )，SV(R b ) Representing a time interval R b A is not equal to b;
step S402: and selecting a corresponding scheduling time set with the minimum random optimization fluctuation value from the random optimization sample list set, and sending the scheduling time set to staff through the power grid architecture cloud platform.
6. An artificial intelligence-based grid optimization scheduling system, the system comprising: the system comprises a power grid framework cloud platform module, a random optimization module, a mapping verification module and a random optimization fluctuation analysis module;
the power grid framework cloud platform module is used for constructing a power grid framework cloud platform, comprehensively planning all network sources in a power grid system, analyzing regulation and control relations among the network sources, locking to form a transmission network source layer, forming a power grid framework connection tree model according to the regulation and control relations, sensing the variation condition of the network sources in the power grid system in real time, and updating the power grid framework connection tree model in real time;
the random optimization module is used for receiving the dispatching demand instruction of each network source through the power grid framework cloud platform in each dispatching period, generating a data tag and a dispatching list according to the dispatching demand instruction, wherein the data tag comprises the number of the network sources, the demand time and the dispatching demand value contained in a transmission network source layer, randomly optimizing a group of dispatching time sets, and dividing time intervals according to the dispatching time sets;
the mapping verification module is used for carrying out corresponding mapping of time intervals on the demand time according to the scheduling time set, generating a section network source set, verifying that the random optimization meets the conditions according to the section network source set, extracting all scheduling time sets for verifying that the random optimization meets the conditions, and generating a random optimization sample scheduling list set;
the random optimization fluctuation analysis module analyzes random optimization fluctuation conditions of any one scheduling list according to the random optimization sample list set and outputs a scheduling time set corresponding to the minimum random optimization fluctuation value.
7. The artificial intelligence based grid optimization scheduling system of claim 6, wherein: the power grid framework cloud platform module further comprises a regulation and control relation analysis unit and a power grid framework connection tree model unit;
the regulation and control relation analysis unit is used for constructing a power grid framework cloud platform, integrally planning all network sources in a power grid system, uniformly coding all the network sources, identifying a line connection mode among the network sources in the power grid system, locking the regulation and control relation among the network sources according to the line connection mode, and when the network source A is the network source i To network source A j When the regulation and control are carried out, N net removing sources A are adopted in the middle i And network source A j When other network sources except the network source are transmitted, if N is more than or equal to 1, marking all other network sources participating in transmission in the middle as a transmission network source layer, and marking the network source A as a transmission network source layer i With network source A j The regulation and control relation between the two components is as follows: network source A i Indirectly through the transmission network source layer to the network source A j Regulating and controlling, and is marked as A i Conveying network source layer → A j The method comprises the steps of carrying out a first treatment on the surface of the If N is equal to 0, network source A i With network source A j The regulation and control relation between the two components is as follows: network source A i Directly to network source A j Regulating and controlling, and is marked as A i →A j The method comprises the steps of carrying out a first treatment on the surface of the Wherein N is a natural number, i and j both represent network source codes, and i is not equal to j;
the power grid framework connection tree model unit forms a power grid framework connection tree model according to the regulation and control relation, expands the power grid framework connection tree model when a new network source is connected in the power grid system, reduces the power grid framework connection tree model when the original network source is deleted in the power grid system, and refreshes the power grid framework connection tree model when the regulation and control relation in the power grid system is changed.
8. The artificial intelligence based grid optimization scheduling system of claim 7, wherein: the random optimization module further comprises a data tag unit and a randomization unit;
the data tag unit is configured to send a scheduling demand command to a grid framework cloud platform by each network source in a kth scheduling period, where one network source correspondingly sends a scheduling demand, the grid framework cloud platform coordinates all received scheduling demands, and generates a scheduling list of the kth scheduling period, where the scheduling list is attached with a data tag of each scheduling request, and the data tag of any one scheduling request is denoted as L (a i )；[N(A i )，t(A i )，SV(A i )]Wherein N (A i ) Representing network source A i Conveying the number, t (A), of network sources contained in a network source layer in a corresponding regulation and control relation i ) Representing network source A i Corresponding to the time of demand, SV (A) i ) Representing network source A i Corresponding schedulingThe scheduling list of the kth scheduling period is recorded as SL according to the requirement value k Sequencing the data labels in the scheduling list according to the time required;
the randomizing unit is used for randomly optimizing a group of scheduling time sets and is marked as ST m ={T 0 ，T 1 ，T 2 ，...，T w }, wherein T is 1 ，T 2 ，...，T w Randomly optimized 1,2,..w scheduling times, T 0 Is a fixed value and T 0 =0; according to the set of scheduling times ST m Generating w time intervals, wherein the a-th time interval is recorded as R a ：T a-1 ～T a Wherein T is a-1 、T a ∈ST m And a is more than or equal to 1 and less than or equal to w, and m represents the mth random optimization.
9. The artificial intelligence based grid optimization scheduling system of claim 8, wherein: the mapping verification module further comprises a mapping unit and a verification unit;
the mapping unit is used for mapping the scheduling list SL k Each demand time of (1) is set according to the scheduling time m Corresponding mapping is carried out on the corresponding generated time interval, and the time interval R is counted a The network source corresponding to the mapped demand time is generated and an interval network source set is generated and is recorded as SV (R) a )；
The verification unit verifies that the random optimization meets the conditions according to the interval network source set, and a specific verification formula is as follows:
∑ Ai∈SVa SV(A i )≤Max(SV)
∑ 1≤a≤w NUM[SV(R a )]=NUM(SL k )
wherein ai=a i ，SVa=SV(R a )，NUM[SV(R a )]Representing a time interval R b Section network source set SV (R a ) The number of network sources contained in the network, max (SV) represents the maximum demand value which can be scheduled by a node at a single scheduling time, NUM (SL) k ) Representing a schedule list SL k Comprising a netNumber of sources;
if the random optimization is verified to meet the condition, the random optimization can be performed, otherwise, the random optimization is performed again; and extracting all scheduling time sets which verify that the random optimization meets the conditions, and generating a random optimization sample scheduling list set.
10. An artificial intelligence based grid optimization scheduling system in accordance with claim 9, wherein: the random optimization fluctuation analysis module further comprises a random optimization fluctuation value calculation unit and an artificial intelligent screening unit;
the random optimization fluctuation value calculation unit calculates the random optimization fluctuation value of any scheduling list according to the random optimization sample list set, and the specific calculation formula is as follows:
RS(ST m )=∑ 1≤a、b≤w {[∑ Ai∈SVa SV(A i )-∑ Aj∈SVb SV(A j )]/[∑ Ai∈SVa N(A i )-∑ Aj∈SVb N(A j )]}
wherein RS (ST) m ) Representing a set of scheduling times ST m Randomly optimized fluctuation value of (1), SV (A) j ) Representing network source A j N (A) corresponding to the scheduling requirement value j ) Representing network source A j The corresponding regulation and control relation conveys the network source quantity contained in the network source layer, and aj=a j ，SVb=SV(R b )，SV(R b ) Representing a time interval R b A is not equal to b;
the artificial intelligence screening unit is used for selecting a scheduling time set corresponding to the random optimization fluctuation value with the minimum value from the random optimization sample list set, and sending the scheduling time set to staff through the power grid architecture cloud platform.
CN202310833287.5A 2023-07-10 2023-07-10 Power grid optimal scheduling system and method based on artificial intelligence Active CN116565859B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310833287.5A CN116565859B (en) 2023-07-10 2023-07-10 Power grid optimal scheduling system and method based on artificial intelligence

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310833287.5A CN116565859B (en) 2023-07-10 2023-07-10 Power grid optimal scheduling system and method based on artificial intelligence

Publications (2)

Publication Number Publication Date
CN116565859A true CN116565859A (en) 2023-08-08
CN116565859B CN116565859B (en) 2023-09-19

Family

ID=87488292

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310833287.5A Active CN116565859B (en) 2023-07-10 2023-07-10 Power grid optimal scheduling system and method based on artificial intelligence

Country Status (1)

Country Link
CN (1) CN116565859B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116823188A (en) * 2023-08-24 2023-09-29 江苏博纳汇数字智能科技有限公司 Production management system and method based on big data analysis
CN117709634A (en) * 2023-12-05 2024-03-15 江苏智融能源科技有限公司 Charging pile power resource management system and method based on big data

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110957758A (en) * 2019-11-20 2020-04-03 国网河北省电力有限公司电力科学研究院 Comprehensive energy efficiency evaluation and control performance optimization method based on wide-area situation awareness
CN112163671A (en) * 2020-12-02 2021-01-01 中国电力科学研究院有限公司 New energy scene generation method and system

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110957758A (en) * 2019-11-20 2020-04-03 国网河北省电力有限公司电力科学研究院 Comprehensive energy efficiency evaluation and control performance optimization method based on wide-area situation awareness
CN112163671A (en) * 2020-12-02 2021-01-01 中国电力科学研究院有限公司 New energy scene generation method and system

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
MOHAMMAD MEHDI HOSSEINI 等: "Artificial intelligence for resilience enhancement of power distribution systems", THE ELECTRICITY JOURNAL, vol. 34, no. 1, pages 1 - 6, XP086454804, DOI: 10.1016/j.tej.2020.106880 *
冯旭阳 等: "面向泛在电力物联网的网源协调关键技术分析", 河北电力技术, vol. 38, no. 06, pages 37 - 39 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116823188A (en) * 2023-08-24 2023-09-29 江苏博纳汇数字智能科技有限公司 Production management system and method based on big data analysis
CN116823188B (en) * 2023-08-24 2023-11-17 江苏博纳汇数字智能科技有限公司 Production management system and method based on big data analysis
CN117709634A (en) * 2023-12-05 2024-03-15 江苏智融能源科技有限公司 Charging pile power resource management system and method based on big data

Also Published As

Publication number Publication date
CN116565859B (en) 2023-09-19

Similar Documents

Publication Publication Date Title
CN116565859B (en) Power grid optimal scheduling system and method based on artificial intelligence
Wu et al. GENCO's risk-based maintenance outage scheduling
Rudnick et al. Economically adapted transmission systems in open access schemes-application of genetic algorithms
Ikeda et al. A novel optimization method combining metaheuristics and machine learning for daily optimal operations in building energy and storage systems
US7489989B2 (en) System for dispatching and controlling of generation in large-scale electric power systems
Lohmann et al. Tailored benders decomposition for a long-term power expansion model with short-term demand response
Zhang et al. Cost-oriented load forecasting
Kampouropoulos et al. Multiobjective optimization of multi-carrier energy system using a combination of ANFIS and genetic algorithms
Li et al. Optimal sizing of distributed generation in gas/electricity/heat supply networks
CN111260108B (en) Energy hub robust optimization method based on interval prediction
Jin et al. Dispatching strategies for coordinating environmental awareness and risk perception in wind power integrated system
CN111062514A (en) Power system planning method and system
Narimani et al. A practical approach for reliability-oriented multi-objective unit commitment problem
CN117040027B (en) Coordination optimization method and device for rural virtual power plant
CN115498624A (en) Low-carbon economic dispatching method for power distribution network containing flexible interactive resources based on two-stage robust optimization
CN113690885B (en) Power supply control method and power supply platform
Sani et al. Affine decision rule approximation to address demand response uncertainty in smart grids’ capacity planning
Kumar et al. Stochastic profit‐based unit commitment problem considering renewable energy sources with battery storage systems and plug‐in hybrid electric vehicles
CN112510690B (en) Optimal scheduling method and system considering wind-fire-storage combination and demand response reward and punishment
CN110021932A (en) The peak regulation ancillary service capacity of bilateral participation chooses and economic model construction method
AHMAD et al. A review of recent advances in generator maintenance scheduling
CN111047071B (en) Power system real-time supply and demand interaction method based on deep migration learning and Stackelberg game
Rau et al. A model for economy energy exchanges in interconnected power systems
CN115189409A (en) Power system production simulation method and device, computer equipment and storage medium
Li et al. A model-free optimal operation strategy of diversified demands-park integrated energy system considering energy cascade utilization

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