CN112528416B - Online real-time distribution algorithm - Google Patents

Online real-time distribution algorithm Download PDF

Info

Publication number
CN112528416B
CN112528416B CN202011504772.0A CN202011504772A CN112528416B CN 112528416 B CN112528416 B CN 112528416B CN 202011504772 A CN202011504772 A CN 202011504772A CN 112528416 B CN112528416 B CN 112528416B
Authority
CN
China
Prior art keywords
task
aircraft
mission
uav
algorithm
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202011504772.0A
Other languages
Chinese (zh)
Other versions
CN112528416A (en
Inventor
张俊杰
徐骋
李振
梁文宝
张云
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.)
Beijing Electromechanical Engineering Research Institute
Original Assignee
Beijing Electromechanical Engineering Research Institute
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 Beijing Electromechanical Engineering Research Institute filed Critical Beijing Electromechanical Engineering Research Institute
Priority to CN202011504772.0A priority Critical patent/CN112528416B/en
Publication of CN112528416A publication Critical patent/CN112528416A/en
Application granted granted Critical
Publication of CN112528416B publication Critical patent/CN112528416B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/15—Vehicle, aircraft or watercraft design
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/04—Constraint-based 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
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Geometry (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Automation & Control Theory (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses an online real-time allocation algorithm, which has the advantages of low computational complexity and high operation efficiency compared with other task allocation algorithms. The method is suitable for a multi-aircraft online real-time multi-task distribution scene, and can well meet task distribution requirements.

Description

Online real-time distribution algorithm
Technical Field
The invention relates to the problem of online real-time multi-task distribution of multiple aircrafts, in particular to an online distribution algorithm based on a market mechanism, and belongs to the field of task distribution.
Background
The problem of aircraft mission allocation is an important issue in aircraft applications. In aircraft allocation problems, the task types may differ. Therefore, how to allocate an aircraft to perform a related mission while considering the performance of the aircraft and the constraint of the mission type, such that the total system benefit is the greatest is a problem to be solved by the aircraft cluster system.
Distributed and centralized are the two main algorithms that are now studying the problem of multi-aircraft mission allocation. Compared with a centralized algorithm, the distributed algorithm has small dependence on a communication center, has better expandability and robustness, and is more and more widely focused on the problem of task allocation of the aircraft based on the distributed algorithm under the communication limitation.
Disclosure of Invention
The invention provides an online real-time allocation algorithm which can quickly realize the online task allocation process of multiple aircrafts in the problem of real-time multi-task allocation of the multiple aircrafts.
An online real-time allocation algorithm comprising the steps of:
step 1, establishing an online multitasking algorithm mathematical model: establishing a corresponding mathematical model through the requirements of on-line real-time task allocation of the multiple aircrafts, and setting corresponding constraint conditions according to the allocation requirements;
Step 2, designing a bidding algorithm: estimating the task income value of the situation that the aircraft completes each task based on situation awareness results of the aircraft on the environment, the cluster state, the task state and the like; according to the task income estimation result, selecting an intentional task based on a task selection strategy; contacting the aircraft connected with the network, and sending out bidding price for the task;
Step 3, designing a synchronization algorithm: receiving task bids, comparing the received task bid valuations with the task value estimates of the task bids, and determining transaction results; responding to all the aircrafts connected with the aircrafts in the operation period, publishing the decided transaction results, completing the synchronization of the task allocation results among the aircrafts, and ensuring the consistency of the global allocation results.
The invention provides an online real-time allocation algorithm, which has weak dependence on a communication center, strong robustness and good stability compared with the traditional centralized task allocation algorithm; compared with other distributed task allocation algorithms, the online real-time allocation algorithm has the advantages of low computational complexity and high operation efficiency. The method is suitable for a multi-aircraft online real-time multi-task distribution scene, and can well meet task distribution requirements.
Drawings
The accompanying drawings, which are included to provide a further understanding of embodiments of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention. It is evident that the drawings in the following description are only some embodiments of the present invention and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art.
FIG. 1 is a schematic flow chart of a bidding algorithm;
FIG. 2 is a schematic diagram of a synchronization algorithm flow;
FIG. 3 is a schematic diagram of the distribution results in the initial state;
FIG. 4 is a schematic diagram of the distribution result after the target position is changed;
FIG. 5 is a graph showing the distribution result after the target is increased;
FIG. 6 is a schematic illustration of the assignment after a change in position of the aircraft;
FIG. 7 is a graph of time spent planning a cycle versus a target number for different algorithms.
Detailed Description
The invention is described in further detail below with reference to the accompanying drawings.
An online real-time distribution algorithm is adopted to solve the problem of online real-time multi-task distribution of a multi-man machine, and the algorithm comprises the following steps:
Step 1, establishing an online algorithm mathematical model: through the demand of on-line real-time task allocation of the multiple aircrafts, a corresponding mathematical model is established, the mathematical model is expressed through a mathematical formula, and corresponding constraint conditions are set according to the allocation demand.
Step 2, designing a bidding algorithm: the bidding algorithm is used for estimating the task income value of the situation that the aircraft completes each task based on situation awareness results of the aircraft on the environment, the cluster state, the task state and the like; according to the task income estimation result, selecting an intentional task based on a task selection strategy; an aircraft connected to its own network is contacted and a bid is sent for the mission.
Step 3, designing a synchronization algorithm: the function of the synchronous algorithm is to receive task bids, compare the received task bid valuations with the value estimation of the task by the synchronous algorithm, and determine the transaction result; responding to all the aircrafts connected with the aircrafts in the operation period, publishing the decided transaction results, completing the synchronization of the task allocation results among the aircrafts, and ensuring the consistency of the global allocation results.
Step 4, building feasibility of a corresponding simulation environment verification algorithm: in order to research the practical application effect of the algorithm, a specific case is designed to simulate and verify the performance index. And judging the feasibility of the algorithm through the simulation result.
Further, the step 1 specifically includes:
Based on a task allocation principle and an aircraft cluster task model, the following mathematical optimization model is established:
S.t.
In the above formula: the benefit of the aircraft performing the mission represented by Y, N is the number of missions, M is the number of aircrafts, R (S UAV(j),Stask (i)) is the benefit calculation function of the aircraft j performing the mission i, S UAV (j) is the status function of the jth aircraft, S task (i) is the status function of the ith mission, Z i is the number of aircrafts required for the ith mission, Z a is the number of aircrafts performing the mission, and the status function is expressed as follows:
SUAV(j)＝{PUAV(j),V,Cj} (4)
Stask(i)＝{ptask(i),Ii,Ti,Zi} (5)
The task profit calculation function R (S UAV(j),Stask (i)) is proportional to-D ij、Ii, -C j、-Ti, the benefit function is established as follows:
In the above formula; p UAV (j) is the position coordinate of the jth aircraft, V is the speed of the aircraft, C j is the loss degree of the jth aircraft, P task (I) is the position coordinate of the ith task, I i is the importance degree of the ith task, T i is the threat degree of the ith task, D ij is the distance from the jth aircraft to the ith task, R A,RB is the variation gain and the basic gain of the task, and ρ and epsilon 1、ε2、ε3、ε4、ε5 are weight coefficients.
Further, the step 2 specifically includes:
the operation of each cycle of the bidding algorithm is based on the judgment of the situation change, namely, the bidding algorithm is operated when the situation changes; the aircraft always calculates potential benefits R(SUAV(j),Stask(1))、R(SUAV(j),Stask(2))、R(SUAN(j),Stask(3))…、R(SUAV(j),Stask(M)) of each mission in the whole mission process, in the benefits calculation formula, S UAV (j) represents a state function of the jth aircraft, and S task (i) represents a state function of the ith mission; then judging whether the situation of all the current aircrafts changes or not, and judging whether the acquired benefits meet the following conditions:
The meaning of equation (1) is that the current revenue for the jth aircraft is lower than the maximum revenue for the current mission and the aircraft is not assigned to a mission;
The judgment condition is to find a mission that is more profitable than the existing mission of the aircraft, and if such a mission does not exist, return to the beginning of the algorithm.
Further, the step 3 specifically includes:
The operation of each cycle of the synchronization algorithm is based on a periodic synchronization point, i.e. synchronization is performed once at intervals;
In the whole communication process, the structure of the system must be a complete network, namely, the topology structure of the network can cover all aircrafts;
before each round of iteration starts, the task price is updated through the aircraft connected with the price, the maximum price of the previous round is taken as the updated price of the next round before each round of price updating, and the price updating formula is as follows:
wherein, Representing the price of the jth mission stored by the ith aircraft before the start of the τ round of iterations.
Further, if the entire network can be connected, the highest bid that can be eventually obtained by constantly communicating with neighboring nodes.
For a further understanding of the present invention, an online real-time allocation algorithm of the present invention is described in detail below with reference to the accompanying drawings.
As shown in fig. 1, a flow chart of the bidding algorithm is shown. The operation of each cycle of the bidding algorithm is based on the determination of the change in situation, i.e., the bidding algorithm is operated when the situation changes, and the aircraft always calculates the potential revenue R(SUAV(j),Stask(1))、R(SUAV(j),Stask(2))、R(SUAN(j),Stask(3))…、R(SUAV(j),Stask(M)) for each mission throughout the mission, where S UAV (j) represents the status function of the jth aircraft and S task (i) represents the status function of the ith mission. Then judging whether the situation of all the current aircrafts changes or not, and judging whether the acquired benefits meet the following conditions:
The meaning of equation (1) is that the current gain of the jth aircraft is lower than the maximum gain of the current mission and the aircraft is not assigned to the mission.
The judgment condition is to find a mission that is more profitable than the existing mission of the aircraft, and if such a mission does not exist, return to the beginning of the algorithm.
Preferably, before designing the bidding algorithm flow chart, the following steps should be included:
Based on the principle of market mechanism and the task model of the aircraft cluster, the following mathematical optimization model is established:
S.t.
In the above formula: the benefit of the aircraft performing the mission is represented by Y, N is the number of missions, M is the number of aircrafts, R (S UAV(j),Stask (i)) is the benefit calculation function of the aircraft j performing the mission i, S UAV (j) is the status function of the j-th aircraft, S task (i) is the status function of the i-th mission, Z i is the number of aircrafts required for the i-th mission, and Z a is the number of aircrafts performing the mission. The state function may be expressed as follows:
SUAV(j)＝{PUAV(j),V,Cj} (4)
Stask(i)＝{ptask(i),Ii,Ti,Zi} (5)
The task profit calculation function R (S UAV(j),Stask (i)) is proportional to-D ij、Ii, -C j、-Ti. The benefit function is established as follows:
In the above formula; p UAV (j) is the position coordinate of the jth aircraft, V is the speed of the aircraft, C j is the loss degree of the jth aircraft, P task (I) is the position coordinate of the ith task, I i is the importance degree of the ith task, T i is the threat degree of the ith task, D ij is the distance from the jth aircraft to the ith task, R A,RB is the variation gain and the basic gain of the task, and ρ and epsilon 1、ε2、ε3、ε4、ε5 are weight coefficients.
As shown in fig. 2, a flowchart of the synchronization algorithm is shown. The operation of each cycle of the synchronization algorithm is based on a periodic synchronization point, i.e. synchronization is performed once at intervals.
As shown in fig. 3, is a diagram of inter-cluster network communications for an aircraft. Throughout the communication, the structure must be a complete network, i.e. the topology of the network is capable of covering all aircraft. In an optimal environment, the communication network can realize point-to-point communication between any two aircrafts in a short time.
In the fully distributed algorithm of the present invention, since no unique wing aircraft is designated to collect and broadcast the price information for all the missions, the aircraft does not know the global maximum price for the mission, and it can only update the mission price by the aircraft to which it is connected before the iteration of each round begins. The price update formula is as follows:
The meaning of the formula is that before each round of price update, the updated price of the next round takes the maximum price of the previous round.
Wherein,Representing the price of the jth mission stored by the ith aircraft before the start of the τ round of iteration, it is apparent that the highest bid that can be eventually achieved by constantly communicating with neighboring nodes if the entire network can be connected.
In order to research the practical application effect of the algorithm, the following cases are designed to simulate the performance index. And the aircraft command center receives the upper-level instruction and sends out the aircraft cluster to execute the task. The set area range is 200 x 200, the speed of the aircraft is 200m/s, and specific parameters of other aircraft and targets are not described in detail herein. According to the practical application environment, the algorithm is simulated and verified, and the specific simulation result is shown in the following figure.
As shown in fig. 3, the distribution results in the initial state at the time of simulation are shown. The corresponding application scene is designed according to the algorithm, 3 task targets and 10 aircrafts are in an initial state, and the optimal distribution effect can be obtained by running the algorithm.
As shown in fig. 4, the allocation result after the target position is changed. When the position of the task object is changed, the allocation result is changed relative to the initial situation.
As shown in fig. 5, the distribution result after the target increase is shown. When one task object is added, the corresponding distribution results of 4 task objects and 10 aircrafts are changed.
As shown in fig. 6, the position of the aircraft is changed to be allocated. When the position of the aircraft changes, the distribution results change.
As shown in fig. 7, which is a graph of the relationship between the time spent in planning a cycle and the number of targets in different algorithms, i can see that when the number of target tasks is less than 5, the time spent in the algorithm of the present invention is not particularly significant compared with the time spent in the conventional centralized allocation algorithm, but when the number of target tasks is greater than 5, the time spent in the specified cycle of the algorithm of the present invention is significantly superior to that of the conventional algorithm.
Compared with the traditional centralized task allocation algorithm, the algorithm has weak dependence on a communication center, strong robustness and good stability; compared with other distributed task allocation algorithms, the online real-time allocation algorithm has the advantages of low computational complexity and high operation efficiency. The method is suitable for a multi-aircraft online real-time multi-task distribution scene, and can well meet task distribution requirements.

Claims (4)

1. An online real-time distribution method is characterized by comprising the following steps:
Step 1, establishing an online multitasking algorithm mathematical model: establishing a corresponding mathematical model through the requirements of on-line real-time task allocation of the multiple aircrafts, and setting corresponding constraint conditions according to the allocation requirements;
Step 2, designing a bidding algorithm: estimating the task income value of the situation that the aircraft completes each task based on situation awareness results of the aircraft on the environment, the cluster state, the task state and the like; according to the task income estimation result, selecting an intentional task based on a task selection strategy; contacting the aircraft connected with the network, and sending out bidding price for the task;
The step 1 specifically comprises the following steps:
Based on the principle of market mechanism and the task model of the aircraft cluster, the following mathematical optimization model is established:
S.t.
In the above formula: the benefit of the aircraft performing the mission represented by Y, N is the number of missions, M is the number of aircrafts, R (S UAV(j),Stask (i)) is the benefit calculation function of the aircraft j performing the mission i, S UAV (j) is the status function of the jth aircraft, S task (i) is the status function of the ith mission, Z i is the number of aircrafts required for the ith mission, Z a is the number of aircrafts performing the mission, and the status function is expressed as follows:
SUAV(j)＝{PUAV(j),V,Cj} (4)
Stask(i)＝{ptask(i),Ii,Ti,Zi} (5)
The profit calculation function R (S UAV(j),Stask (i)) is proportional to-D ij、Ii, -C j、-Ti, the revenue calculation function is established as follows:
In the above formula; p UAV (j) is the position coordinate of the jth aircraft, V is the speed of the aircraft, C j is the loss degree of the jth aircraft, P task (I) is the position coordinate of the ith task, I i is the importance degree of the ith task, T i is the threat degree of the ith task, D ij is the distance from the jth aircraft to the ith task, R A,RB is the variation gain and the basic gain of the task, and ρ, ε 1 and ε 2、ε3、ε4、ε5 are weight coefficients.
2. The online real-time distribution method according to claim 1, further comprising step 3: designing a synchronization algorithm: receiving task bids, comparing the received task bid valuations with the task value estimates of the task bids, and determining transaction results; responding to all the aircrafts connected with the aircrafts in the operation period, publishing the decided transaction results, completing the synchronization of the task allocation results among the aircrafts, and ensuring the consistency of the global allocation results.
3. The online real-time distribution method according to claim 2, wherein step 2 specifically comprises:
the operation of each cycle of the bidding algorithm is based on the judgment of the situation change, namely, the bidding algorithm is operated when the situation changes; the aircraft always calculates potential benefits R(SUAV(j),Stask(1))、R(SUAV(j),Stask(2))、R(SUAN(j),Stask(3))…、R(SUAV(j),Stask(M)) of each mission in the whole mission process, in the benefits calculation formula, S UAV (j) represents a state function of the jth aircraft, and S task (i) represents a state function of the ith mission; then judging whether the situation of all the current aircrafts changes or not, and judging whether the acquired benefits meet the following conditions:
The meaning of equation (1) is that the current revenue for the jth aircraft is lower than the maximum revenue for the current mission and the aircraft is not assigned to a mission;
The judgment condition is to find a mission that is more profitable than the existing mission of the aircraft, and if such a mission does not exist, return to the beginning of the algorithm.
4. The online real-time distribution method according to claim 2, wherein step 3 specifically comprises:
The operation of each cycle of the synchronization algorithm is based on a periodic synchronization point, i.e. synchronization is performed once at intervals;
In the whole communication process, the structure of the system must be a complete network, namely, the topology structure of the network can cover all aircrafts;
before each round of iteration starts, the task price is updated through the aircraft connected with the price, the maximum price of the previous round is taken as the updated price of the next round before each round of price updating, and the price updating formula is as follows:
wherein, Representing the price of the jth mission stored by the ith aircraft before the start of the τ round of iterations.
CN202011504772.0A 2020-12-18 2020-12-18 Online real-time distribution algorithm Active CN112528416B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011504772.0A CN112528416B (en) 2020-12-18 2020-12-18 Online real-time distribution algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011504772.0A CN112528416B (en) 2020-12-18 2020-12-18 Online real-time distribution algorithm

Publications (2)

Publication Number Publication Date
CN112528416A CN112528416A (en) 2021-03-19
CN112528416B true CN112528416B (en) 2024-07-09

Family

ID=75001416

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011504772.0A Active CN112528416B (en) 2020-12-18 2020-12-18 Online real-time distribution algorithm

Country Status (1)

Country Link
CN (1) CN112528416B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114610058B (en) * 2022-03-01 2024-10-18 北京机电工程研究所 Cluster aircraft multitasking distributed task allocation method

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8146090B2 (en) * 2005-09-29 2012-03-27 Rockstar Bidco, LP Time-value curves to provide dynamic QoS for time sensitive file transfer
WO2017139344A1 (en) * 2016-02-12 2017-08-17 Wal-Mart Stores, Inc. Systems and methods to allocate unmanned aircraft systems
CN110162043B (en) * 2019-05-17 2020-10-09 北京航空航天大学 Cluster task allocation and control method under constraint of simultaneous arrival of multiple target points
CN111199360B (en) * 2020-01-13 2023-05-05 西安电子科技大学 Unmanned aerial vehicle task allocation planning method

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
多无人机协同任务 规划技术;韩攀;中国优秀硕士学位论文全文 数据库;20140715(第07期);C031-131 *
多目标跟踪的飞行器集群协同实时任务分配策略;王厚鹏 等;导弹与航天运载技术;20200610(第03期);32-37 *

Also Published As

Publication number Publication date
CN112528416A (en) 2021-03-19

Similar Documents

Publication Publication Date Title
US9639642B2 (en) Time series forecasting ensemble
CN113128828B (en) Satellite observation distributed online planning method based on multi-agent reinforcement learning
CN107947845B (en) Communication relay-based unmanned aerial vehicle formation cooperative target allocation method
CN111064633B (en) Cloud-edge cooperative power information communication equipment automated testing resource allocation method
CN109189094B (en) Resource scheduling method for hybrid formation of multiple human-machines and multiple unmanned aerial vehicles
CN110739696B (en) Integrated scheduling method for demand side resources and renewable energy in intelligent distribution network environment
CN113671987B (en) Multi-machine distributed time sequence task allocation method based on non-deadlock contract net algorithm
CN110134146A (en) A kind of distributed multiple no-manned plane method for allocating tasks under uncertain environment
CN103218675A (en) Short-term load prediction method based on clustering and sliding window
CN114415735B (en) Dynamic environment-oriented multi-unmanned aerial vehicle distributed intelligent task allocation method
CN110456633A (en) Airborne multi-platform distributed task scheduling distribution method
Wang et al. A fuzzy adaptive comfort temperature model with grey predictor for multi-agent control system of smart building
CN112418495A (en) Building energy consumption prediction method based on longicorn stigma optimization algorithm and neural network
CN112528416B (en) Online real-time distribution algorithm
CN111798097B (en) Autonomous mobile robot task allocation processing method based on market mechanism
CN109102155A (en) A kind of ultra-short term deploying node probability forecasting method and system
CN114971819A (en) User bidding method and device based on multi-agent reinforcement learning algorithm under federal learning
CN114995989A (en) Multi-underwater robot task allocation method and system based on self-organizing neural network
Xu et al. Aoi-guaranteed incentive mechanism for mobile crowdsensing with freshness concerns
CN112070328B (en) Multi-water surface unmanned search and rescue boat task allocation method with partially known environmental information
CN105139069A (en) Method for improving contract net based on particle swarm algorithm
CN115689184A (en) Distributed task allocation method based on consensus binding algorithm
CN110942346A (en) Dynamic estimation method for construction engineering cost based on particle swarm algorithm
CN115630561A (en) Automatic optimization method and device for neural network thermal load prediction model
CN110504690B (en) Method for using cloud computing for power flow computing

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