CN111918403A - Industrial wireless network deterministic transmission scheduling method based on improved Monte Carlo search tree - Google Patents
Industrial wireless network deterministic transmission scheduling method based on improved Monte Carlo search tree Download PDFInfo
- Publication number
- CN111918403A CN111918403A CN202010767526.8A CN202010767526A CN111918403A CN 111918403 A CN111918403 A CN 111918403A CN 202010767526 A CN202010767526 A CN 202010767526A CN 111918403 A CN111918403 A CN 111918403A
- Authority
- CN
- China
- Prior art keywords
- node
- reliability
- wireless network
- industrial wireless
- scheduling
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000005540 biological transmission Effects 0.000 title claims abstract description 36
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000004891 communication Methods 0.000 claims abstract description 11
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000004088 simulation Methods 0.000 claims description 13
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 230000001902 propagating effect Effects 0.000 claims description 2
- 238000004422 calculation algorithm Methods 0.000 description 17
- 238000005070 sampling Methods 0.000 description 5
- 238000003672 processing method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W72/00—Local resource management
- H04W72/12—Wireless traffic scheduling
- H04W72/1263—Mapping of traffic onto schedule, e.g. scheduled allocation or multiplexing of flows
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W72/00—Local resource management
- H04W72/04—Wireless resource allocation
- H04W72/044—Wireless resource allocation based on the type of the allocated resource
- H04W72/0446—Resources in time domain, e.g. slots or frames
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
- Small-Scale Networks (AREA)
Abstract
The invention discloses an industrial wireless network deterministic transmission scheduling method based on an improved MCTS. Establishing a probabilistic determination transmission scheduling model, constructing a scheduling mode aiming at each node in the industrial wireless network, generating and verifying the scheduling mode by using a heuristic method based on a Monte Carlo search tree, iterating until the probability reliability corresponding to the time slot allocation scheme is more than or equal to the target reliability, outputting the time slot allocation scheme, and using each scheduling mode S in the time slot allocation scheme SiAnd controlling each corresponding node of the industrial wireless network to carry out communication transmission. The invention adopts a probabilistic deterministic transmission scheduling model to ensure the deterministic communication of the delivery deadline guarantee of the reliability package required by the industrial wireless network, reduces the computational complexity, obviously reduces the generation difficulty of the deterministic transmission scheduling scheme of the industrial wireless network, and has stable output result.
Description
Technical Field
The invention relates to a processing method for industrial wireless network communication transmission scheduling, in particular to a method for generating and verifying industrial wireless network probabilistic determination transmission scheduling based on an improved Monte Carlo search tree (MCTS).
Background
Industrial wireless networks are a cost-effective and scalable solution for connecting industrial field devices. It is flexible to deploy and easy to maintain compared to traditional wired networks. However, industrial wireless networks typically require deterministic communication with reliability and package delivery deadline guarantees. Achieving this goal in wireless networks is difficult due to the natural unreliability of wireless links. Since the optimal solution algorithm of the wireless network time slot allocation scheduling scheme is NP-hard, it is not feasible to directly find the optimal communication scheduling process of each node.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an industrial wireless network probabilistic determination transmission scheduling generation and detection method based on an improved Monte Carlo search tree.
The invention is realized by the following specific technical scheme, which comprises the following specific steps:
a1, establishing a probabilistic determination transmission scheduling model:
for each node N in an industrial wireless networkiA scheduling pattern S is constructediI represents the ordinal number of the node in the industrial wireless network, the scheduling mode SiIs represented by (N, T, W)iP), N represents the total number of nodes in the scheduling mode, T represents the total number of time slots to be transmitted, and node NiDeadline of packet transmission, WiRepresenting a time slot allocated to the ith node for sending, P representing target reliability, and N, T, P parameters forming a scheduling model parameter; and establishes a scheduling pattern SiReliability P':
wherein, XiIs the number of successful transmissions by the ith node.
The node refers to a communication node in the industrial wireless network. The scheduling model parameters are consistent and the same in each node.
Successful transmission means that a node in the industrial wireless network successfully sends a data packet to another node and then is received by another node.
A2, generating and verifying a scheduling mode by using a heuristic method based on a Monte Carlo search tree, iterating until the probability reliability corresponding to the time slot allocation scheme is more than or equal to the target reliability P, and outputting a time slot allocation scheme S;
a3, in each scheduling mode S in the time slot allocation scheme SiAnd controlling each corresponding node of the industrial wireless network to carry out communication transmission.
In specific implementation, the industrial wireless network refers to a network formed by sensors, actuators, gateways and the like in an industrial environment in a wireless network mode.
The A2 is specifically as follows:
a2-1, constructing a Monte Carlo search tree according to the scheduling model parameters in A1, and constructing a root node R of the Monte Carlo search tree, wherein the root node R is empty;
a2-2, starting from the root node R as the current node, performing the following processing:
a2-3, expansion: performing sub-node expansion by taking the current node as a father node to complete the next-layer expansion of the current node of the Monte Carlo search tree, wherein each sub-node obtained by the expansion comprises a scheduling mode set of all nodes of the industrial wireless network;
a2-4, simulation: according to the preset boundary condition, simulating the time slot distribution of the expanded sub-nodes of the next layer to obtain a scheduling mode set of each sub-node of the next layer as a time slot distribution scheme;
a2-5, reliability calculation:
converting the slot allocation scheme generated in A2-4 into a binary number, using logical bit operations to determine whether it is feasible: extracting a plurality of samples lambda from the space of each subnode, wherein one sample is a scheduling mode, and the scheduling mode S of each sampleiConversion to binary numbers alphaiAnd then further calculating the number of successful transmissions ζiAnd judging:
ηi＝αi&！(α1|α2|...|αi-1|αi+1|...|αn)
wherein eta isiRepresenting available spatial binary numbers;&represents a logical AND operation, | represents a logical OR operation, |! Represents a logical not operation;
then, the reliability of all samples is calculated as the probability reliability P' of the sub-node according to the following reliability formula:
therein, ζiIs the number of times the ith node corresponding to the sample successfully transmits, and λ represents the quantity of reliability tests extracted from all communication node transmission situations;
after the simulation is finished, the result after the simulation is evaluated, and the calculation amount can be reduced by adopting a random sampling mode for processing.
A2-6, counter-propagating:
reversely propagating, processing and updating the number of times of access of the parent node of the child node, namely the number of times of access of the current node according to the time slot allocation scheme obtained by the simulation of A2-4; the child nodes and their parents are accessed during the back propagation process.
A2-7, rollback mechanism:
after the slot allocation scheme obtained in the simulation of a2-4 is subjected to the reliability calculation of a2-5,
if at least one of the reliability of each child node exceeds the reliability of the parent node, carrying out the next step;
if the reliability of all the child nodes does not exceed that of the parent node, triggering a rollback mechanism, resetting the Monte Carlo search tree to a state before a fixed turn, and continuing to iterate again;
a2-8, calculating the confidence upper bound value (UCT) of each sub-node expanded by the current node in the Monte Carlo search tree, selecting the sub-node with the maximum confidence upper bound value, reserving and deleting other sub-nodes;
a2-9, comparing and judging the probability reliability P' of the reserved sub-nodes and the target reliability P: if the probability reliability P' is judged to be more than or equal to the target reliability P, stopping iteration and outputting a time slot distribution scheme corresponding to the currently reserved sub-node; otherwise, the reserved child node is taken as the current node, and the iterative processing returns to the step A2-3.
The calculation of the confidence upper bound value of the subnode in the Monte Carlo search tree is as follows:
wherein v isiIs the reliability of the ith sub-node, niIs the number of times the ith child node has been accessed in the back propagation, M is the total number of times the current node as the ith child node parent node has been accessed, C represents a weight coefficient, is a constant, and is usually taken
Because the problem of generating a transmission scheduling scheme determined probabilistically by an industrial wireless network is NP-Hard, the invention provides a heuristic algorithm based on a Monte Carlo search tree to generate a scheduling mode so as to reduce the whole search space, and simultaneously, random sampling and logic bit operation are adopted in the method to reduce the calculation complexity of the algorithm.
The invention has the beneficial effects that:
the invention adopts a probabilistic deterministic transmission scheduling model to ensure the deterministic communication of the delivery deadline guarantee of the reliability package required by the industrial wireless network, adopts the improved Monte Carlo search tree processing to obtain the approximate optimal scheduling result, and simultaneously adopts random sampling and logic bit operation in the algorithm to reduce the computational complexity of the algorithm. The invention obviously reduces the difficulty of generating the deterministic transmission scheduling result in the industrial wireless network, and the algorithm has stable output result which is superior to the result of random time slot allocation.
Drawings
FIG. 1 is an iterative flow chart of the method of the present invention.
FIG. 2 is a schematic diagram of a logic bit operation calculation method.
Fig. 3 is a graph comparing the mean, maximum and minimum values of the results of the method with the improved monte carlo search tree process and the random slot allocation algorithm of the present invention.
Fig. 4 is a graph of a comparison of standard deviation of the results of the method with the improved monte carlo search tree process of the present invention and the random slot allocation algorithm.
Detailed Description
The objects and effects of the present invention will become more apparent from the following description of the present invention with reference to the accompanying drawings and examples.
The specific embodiment and the implementation process of the invention are as follows:
a1, establishing a probabilistic deterministic transmission scheduling model, node NiScheduling pattern S ofiCan be represented as (N, T, W)iP), N denotes the total number of nodes in the scheduling mode, T denotes the total number of slots in the scheduling mode, and also denotes the deadline of the data packet transmission, WiIndicating the time slot allocated to the i-th node for transmission in the scheduling mode, and P indicating the probabilistic deterministic transmission requirement that the scheduling scheme needs to achieve. Scheduling mode SiDegree of reliability of
P' is not less than P, wherein XiIs the number of successful transmissions by the ith node;
a2, generating and verifying a scheduling mode by using a heuristic algorithm based on a Monte Carlo search tree according to the given requirements in A1;
a3, iterating the steps in A2 until the reliability of the scheme S is more than or equal to P required in A1, and outputting a scheduling scheme S;
the a2, as shown in fig. 1, specifically includes:
a2-1, constructing Monte Carlo search tree root node R according to the scheduling model parameters given in A1;
a2-2, selecting: if the node is not expanded, the expansion of the sub-node is carried out; otherwise, selecting a sub-node with the maximum UCT value according to the UCT value obtained by calculation; the used algorithm is UCT, and the calculation method of UCT is as follows:
wherein v isiIs the reliability of the node, niIs the number of times the node has been accessed, N is the total number of times its parent node has been accessed, C is a constant, takes
A2-3, expansion: after the node is selected, expanding the next layer of the node;
a2-4, simulation: according to the set strategy, carrying out next time slot allocation simulation on the expanded sub-nodes;
a2-5, reliability calculation: after the simulation is completed, the result after the simulation needs to be evaluated. A random sampling method is adopted to reduce the calculation space. The reliability calculation formula in A1 is rewritten as
Wherein ζiIs the number of successful transmissions by the ith node in the sample. The slot allocation scheme generated in a2-4 is converted into a binary number using a logical bit operation, and the bit operation is used to determine whether it is feasible. Namely node NiScheduling pattern S ofiCan be converted into binary numbers alphaiCalculating to obtain betaiAnd then ζ can be further calculatedi：
ηi＝αi&！(α1|α2|...|αi-1|αi+1|...|αn)
As shown in FIG. 2, N1Can be represented by binary number 0b11000, let it be alpha1，N2And N3Can be similarly represented as 0b10100, 0b10010, let it be alpha2And alpha3. To calculate ζ1Will exclude a1All other numbers are logically ORed to obtain omega1Then to ω1Performing a logical NOT operation to obtain beta1Finally, will be alpha1And beta1Performing logical AND operation to obtain η1. If eta1And > 0, indicates that node 1 can successfully transmit under this scheduling condition, ζ1Increasing by 1; otherwise, node 1 cannot successfully transmit, ζ1And is not changed.
A2-6, counter-propagating: updating the father node information according to the result of the A2-4 simulation;
a2-6, rollback mechanism: due to the random sampling, a systematic error exists in the reliability calculation result, and a threshold value tau is defined. When the reliability of all the simulation results in A2-4 is calculated in A2-5, the reliability of the obtained nodes does not exceed that of the parent node, a rollback mechanism is triggered, and the search tree is reset to a state before a plurality of rounds to iterate again; conversely, this result is also considered acceptable by the search tree; the number xi of a backspacing wheel is setiRepresenting the number of the rounds needing to be backed off when the ith round is backed off; ξ when the ith round of iteration triggers rollbackiWill self increment by 1 to eliminate cumulative improper allocations as much as possible;
to verify the performance of the present invention, the present invention was implemented and compared with a random slot allocation algorithm for algorithm performance. Let N be 10, T be 95, λ be 10000, τ be 0.05, and P be 99.0%, and 100 tests were performed for each of the two algorithms. The mean value, the maximum value, the minimum value and the standard deviation of the reliability of the scheme output by each round of algorithm are used as judgment standards, and the larger the mean value, the maximum value and the minimum value are, the smaller the standard deviation is, the better and more stable the algorithm result is.
The scheme reliability average, maximum and minimum results with the improved monte carlo search tree processing method and the random time slot allocation algorithm of the present invention are shown in fig. 3, and the variance results are shown in fig. 4. The two graphs can be used for obtaining that the invention is superior to a random time slot allocation algorithm in four indexes, and the invention can be used for more accurately and more stably calculating the scheduling scheme which meets the requirement of the probabilistic determination of the transmission scheduling of the industrial wireless network.
Claims (3)
1. An industrial wireless network deterministic transmission scheduling method based on improved MCTS is characterized in that: the method comprises the following steps:
a1, establishing a probabilistic determination transmission scheduling model:
for each node N in an industrial wireless networkiA scheduling pattern S is constructediI represents the ordinal number of the node in the industrial wireless network, the scheduling mode SiIs represented by (N, T, W)iP), N represents the total number of nodes in the scheduling mode, T represents the total number of time slots to be transmitted, and node NiDeadline of packet transmission, WiRepresenting a time slot allocated to the ith node for sending, P representing target reliability, and N, T, P parameters forming a scheduling model parameter;
a2, generating and verifying a scheduling mode by using a heuristic method based on a Monte Carlo search tree, iterating until the probability reliability corresponding to the time slot allocation scheme is more than or equal to the target reliability P, and outputting a time slot allocation scheme S;
a3, in each scheduling mode S in the time slot allocation scheme SiAnd controlling each corresponding node of the industrial wireless network to carry out communication transmission.
2. The deterministic transmission scheduling method for industrial wireless networks based on improved MCTS as claimed in claim 1, characterized by: the A2 is specifically as follows:
a2-1, constructing a root node R of the Monte Carlo search tree, wherein the root node R is empty;
a2-2, starting from the root node R as the current node, performing the following processing:
a2-3, expansion: performing sub-node expansion by taking the current node as a father node to complete the next-layer expansion of the current node of the Monte Carlo search tree, wherein each sub-node obtained by the expansion comprises a scheduling mode set of all nodes of the industrial wireless network;
a2-4, simulation: according to the preset boundary condition, simulating the time slot distribution of the expanded sub-nodes of the next layer to obtain a scheduling mode set of each sub-node of the next layer as a time slot distribution scheme;
a2-5, reliability calculation:
converting the slot allocation scheme generated in A2-4 into a binary number, using logical bit operations to determine whether it is feasible: extracting samples lambda from each subnode, wherein one sample is a scheduling mode, and the scheduling mode S of each sampleiConversion to binary numbers alphaiAnd then further calculating the number of successful transmissions ζiAnd judging:
ηi＝αi&！(α1|α2|…|αi-1|αi+1|…|αn)
wherein eta isiRepresenting available spatial binary numbers;&represents a logical AND operation, | represents a logical OR operation, |! Represents a logical not operation;
then, the reliability of all samples is calculated as the probability reliability P' of the sub-node according to the following reliability formula:
therein, ζiIs the number of successful transmissions made by the ith node corresponding to the sample, and λ represents the transmission conditions from all communication nodesThe amount of the pattern extracted for reliability checking;
a2-6, counter-propagating:
reversely propagating and processing according to the time slot allocation scheme obtained by the simulation of A2-4 and updating the visited times of the parent node of the child node;
a2-7, rollback mechanism:
if at least one of the reliability of each child node exceeds the reliability of the parent node, carrying out the next step;
if the reliability of all the child nodes does not exceed that of the parent node, triggering a rollback mechanism, resetting the Monte Carlo search tree to a state before a fixed turn, and continuing to iterate again;
a2-8, calculating the confidence upper bound value (UCT) of each sub-node expanded by the current node in the Monte Carlo search tree, selecting the sub-node with the maximum confidence upper bound value, reserving and deleting other sub-nodes;
a2-9, comparing and judging the probability reliability P' of the reserved sub-nodes and the target reliability P: if the probability reliability P' is judged to be more than or equal to the target reliability P, stopping iteration and outputting a time slot distribution scheme corresponding to the currently reserved sub-node; otherwise, the reserved child node is taken as the current node, and the iterative processing returns to the step A2-3.
3. The deterministic transmission scheduling method for industrial wireless networks based on improved MCTS as claimed in claim 1, characterized by: the calculation of the confidence upper bound value of the subnode in the Monte Carlo search tree is as follows:
wherein v isiIs the reliability of the ith sub-node, niIs the number of times the ith child node has been accessed in the back propagation, M is the total number of times the current node, which is the ith child node parent node, has been accessed, and C represents a weight coefficient.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010767526.8A CN111918403B (en) | 2020-08-03 | 2020-08-03 | Industrial wireless network deterministic transmission scheduling method based on improved Monte Carlo search tree |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010767526.8A CN111918403B (en) | 2020-08-03 | 2020-08-03 | Industrial wireless network deterministic transmission scheduling method based on improved Monte Carlo search tree |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111918403A true CN111918403A (en) | 2020-11-10 |
| CN111918403B CN111918403B (en) | 2023-10-31 |
Family
ID=73287016
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010767526.8A Active CN111918403B (en) | 2020-08-03 | 2020-08-03 | Industrial wireless network deterministic transmission scheduling method based on improved Monte Carlo search tree |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111918403B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101321127A (en) * | 2008-07-21 | 2008-12-10 | 重庆邮电大学 | Determined communication scheduling method of industrial wireless network |
| CN106507492A (en) * | 2016-11-08 | 2017-03-15 | 重庆邮电大学 | Based on the industry wireless network definitiveness transmission dispatching method that priority is distributed |
| CN107257261A (en) * | 2017-05-18 | 2017-10-17 | 中国科学院计算技术研究所 | A kind of dynamic link dispatching method for 6TiSCH multi-hop wireless networks |
| CN108184244A (en) * | 2018-01-18 | 2018-06-19 | 重庆邮电大学 | A kind of industry wireless network deterministic schedule method that propagation delay time is supported to optimize |
| CN108960485A (en) * | 2018-06-11 | 2018-12-07 | 中国南方电网有限责任公司 | One provenance-lotus interacts the online dictionary learning probability optimal load flow method under electricity market |
| CN108985458A (en) * | 2018-07-23 | 2018-12-11 | 东北大学 | A kind of double tree monte carlo search algorithms of sequential synchronous game |
| CN109857532A (en) * | 2019-01-22 | 2019-06-07 | 杭州电子科技大学 | DAG method for scheduling task based on the search of Monte Carlo tree |
| CN111328109A (en) * | 2020-02-10 | 2020-06-23 | 浙江理工大学 | Distributed synchronization-free transmission scheduling method and system of multi-hop wireless network |
-
2020
- 2020-08-03 CN CN202010767526.8A patent/CN111918403B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101321127A (en) * | 2008-07-21 | 2008-12-10 | 重庆邮电大学 | Determined communication scheduling method of industrial wireless network |
| CN106507492A (en) * | 2016-11-08 | 2017-03-15 | 重庆邮电大学 | Based on the industry wireless network definitiveness transmission dispatching method that priority is distributed |
| CN107257261A (en) * | 2017-05-18 | 2017-10-17 | 中国科学院计算技术研究所 | A kind of dynamic link dispatching method for 6TiSCH multi-hop wireless networks |
| CN108184244A (en) * | 2018-01-18 | 2018-06-19 | 重庆邮电大学 | A kind of industry wireless network deterministic schedule method that propagation delay time is supported to optimize |
| CN108960485A (en) * | 2018-06-11 | 2018-12-07 | 中国南方电网有限责任公司 | One provenance-lotus interacts the online dictionary learning probability optimal load flow method under electricity market |
| CN108985458A (en) * | 2018-07-23 | 2018-12-11 | 东北大学 | A kind of double tree monte carlo search algorithms of sequential synchronous game |
| CN109857532A (en) * | 2019-01-22 | 2019-06-07 | 杭州电子科技大学 | DAG method for scheduling task based on the search of Monte Carlo tree |
| CN111328109A (en) * | 2020-02-10 | 2020-06-23 | 浙江理工大学 | Distributed synchronization-free transmission scheduling method and system of multi-hop wireless network |
Non-Patent Citations (3)
| Title |
|---|
| 张本宏;邱睿;黄琳琳;: "一种用于工业无线传感器网络的动态调度方法", 合肥工业大学学报(自然科学版), no. 03 * |
| 王仁超;张鹏程;徐跃明;: "基于蒙特卡洛树搜索的土石方动态调配算法及验证", 水利学报, no. 04 * |
| 王恒;朱元杰;杨杭;王平;: "基于优先级分类的工业无线网络确定性调度算法", 自动化学报, no. 02 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111918403B (en) | 2023-10-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Fronczak et al. | Average path length in random networks | |
| CN107037373B (en) | Battery remaining capacity prediction technique neural network based | |
| CN110910004A (en) | Reservoir dispatching rule extraction method and system with multiple uncertainties | |
| CN110446204B (en) | Trust value calculation method suitable for Internet of vehicles network vehicle node | |
| CN113507696A (en) | Indoor positioning method and system based on base station spatial layout optimization | |
| Osborne et al. | A comparison of two simulated annealing algorithms applied to the directed Steiner problem on networks | |
| CN111526208A (en) | High-concurrency cloud platform file transmission optimization method based on micro-service | |
| CN111918403A (en) | Industrial wireless network deterministic transmission scheduling method based on improved Monte Carlo search tree | |
| CN106649790A (en) | Multilayer link separated skiplist construction method and system | |
| CN116962438A (en) | Gradient data synchronization method, system, electronic equipment and readable storage medium | |
| Wynveen et al. | Nonequilibrium steady states in a model for prebiotic evolution | |
| Weber et al. | Multicomponent reaction-diffusion processes on complex networks | |
| CN116415655A (en) | Decentralizing asynchronous federation learning method based on directed acyclic graph | |
| US7966347B2 (en) | Generating a value associated with one of a plurality of leaf nodes by implicitly randomly climbing an implicit tree having the leaf nodes | |
| CN111967585B (en) | Network model processing method and device, electronic equipment and storage medium | |
| CN112395272B (en) | Communication algorithm database construction method, distributed machine device, and storage medium | |
| US10707896B2 (en) | Forward and backward smooth decoding method, device, and system | |
| Zhao et al. | Selective maintenance modeling for a multi-state system considering human reliability | |
| CN113673721A (en) | Cluster system preventive maintenance method based on deep reinforcement learning | |
| CN114884825B (en) | Network planning method and device and electronic equipment | |
| CN110798350A (en) | System reliability model construction and evaluation method based on incomplete state monitoring data learning | |
| Dodonov et al. | Modeling the Survivability of Network Structures. | |
| CN116090525B (en) | Embedded vector representation method and system based on hierarchical random walk sampling strategy | |
| Zjavka | Photovoltaic power intra‐and day‐ahead predictions with differential learning producing PDE‐modular models based on the node L‐transform derivatives | |
| Green et al. | A fast algorithm for incremental betweenness centrality |
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 |