CN115733839B - Bandwidth-adaptive data link intelligent distribution strategy optimization method - Google Patents
Bandwidth-adaptive data link intelligent distribution strategy optimization method Download PDFInfo
- Publication number
- CN115733839B CN115733839B CN202211421295.0A CN202211421295A CN115733839B CN 115733839 B CN115733839 B CN 115733839B CN 202211421295 A CN202211421295 A CN 202211421295A CN 115733839 B CN115733839 B CN 115733839B
- Authority
- CN
- China
- Prior art keywords
- strategy
- distribution
- current
- gene vector
- distribution strategy
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- 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
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention belongs to the technical field of intelligent distribution of data chains, and discloses a bandwidth self-adaptive intelligent distribution strategy optimization method of the data chains, which aims to maximize performances such as data transmission richness and completeness and minimize communication blocking rate under different bandwidth conditions. Firstly, setting an initial distribution strategy as a current distribution strategy and distributing according to the current strategy, then designing quality evaluation indexes to evaluate the quality of a distribution process, obtaining various index evaluation values and calculating self-adaptive optimization tendency weights. And setting a distribution quality threshold value to judge the rationality of the current distribution strategy and the current communication environment. When unreasonable occurs, a distribution strategy self-adaptive optimization method is called, a strategy gene vector and a self-adaptive optimization trend weight after vectorization of the current distribution strategy are taken as input, a new distribution strategy is obtained through an intelligent optimization method, the current distribution strategy is replaced, and self-adaptive optimization of the distribution strategy is completed.
Description
Technical Field
The invention belongs to the technical field of intelligent distribution of data chains, and particularly relates to a method for automatically adjusting an information distribution strategy between each message generation and consumption platform according to the quality of bandwidth.
Background
With the gradual development of various platforms such as unmanned aerial vehicles, unmanned boats, unmanned vehicles and the like, the acquired data types are gradually enriched. The traditional data link is mainly narrowband communication, is limited by narrower bandwidth and can only transmit formatted message code streams, and along with the gradual development of the broadband data link, the mode of data to be distributed gradually develops from a simple formatted message to a composite mode of message, picture, message, video and the like, and the corresponding distribution strategy is more abundant.
However, current data distribution service algorithms only perform distribution services for fixed modality data. When the communication quality of the data link between the platforms is poor and the bandwidth is narrowed, the distribution strategy cannot be adaptively adjusted to reduce the blocking of the channel. When the communication quality of the data link between the platforms is improved and the bandwidth is widened, the distribution strategy cannot be adaptively adjusted to increase the richness and completeness of information transmission.
Therefore, a bandwidth adaptive data link intelligent distribution strategy optimization method is needed to be researched, the quality of the current communication environment of the data link is evaluated, and the distribution strategy is adaptively optimized according to the evaluation result so as to adapt to the complex and changeable data link transmission environment.
Disclosure of Invention
The invention aims to solve the problem that the data distribution strategy is difficult to be adaptively adjusted under the condition of changeable communication environment so as to cause insufficient data link information transmission capability, and provides a bandwidth adaptive data link intelligent distribution strategy optimization method which can evaluate the quality of the data link transmission environment in real time and adaptively optimize the distribution strategy of data to be distributed in an intelligent optimizing mode so as to realize the aims of maximizing the performances such as data transmission richness and completeness and minimizing the communication blocking rate under different bandwidth conditions.
The invention adopts the technical scheme that:
a bandwidth self-adaptive data link intelligent distribution strategy optimization method comprises the following steps:
(1) Setting an initial distribution strategy as a current distribution strategy, wherein the initial distribution strategy comprises a data mode, a transmission frequency band and a retransmission requirement; wherein the data modalities include one or a combination of modalities of formatting messages, pictures, videos, and waveforms;
(2) Distributing the current data to be distributed by adopting a current distribution strategy, after the distribution is completed, evaluating the timeliness, completeness and richness of the whole distribution process according to a data link network transmission log and by using a set quality evaluation index to obtain an timeliness evaluation value, a completeness evaluation value and a richness evaluation value, and summing all the evaluation values to obtain a final quality evaluation result value of the distribution process;
(3) Obtaining self-adaptive optimized trend weights including an timeliness trend weight, a completeness trend weight and a richness trend weight through calculating reciprocal according to the timeliness evaluation value, the completeness evaluation value and the richness evaluation value which are obtained through evaluation;
(4) Setting a distribution quality threshold, if the final quality evaluation result value of the current distribution process is higher than the distribution quality threshold, indicating that the current distribution strategy is reasonable, otherwise, indicating that the current distribution strategy is unreasonable, and executing the step (5);
(5) And (3) automatically generating a new distribution strategy according to the self-adaptive optimization trend weight by utilizing a genetic algorithm, replacing the current distribution strategy, and returning to the step (2).
Wherein, the step (5) comprises the following steps:
(501) Abstracting the distribution strategy into a strategy gene vector, wherein each digit in the strategy gene vector represents one strategy content in the distribution strategy;
(502) Taking the differential weighting of the self-adaptive optimization tendency weight and the strategy gene vector as an adaptability function of a genetic algorithm, and adopting a random function to generate a plurality of strategy gene vectors to form a first generation strategy gene vector set which is used as a current strategy gene vector set;
(503) Calculating the score of the fitness function of each strategy gene vector, and selecting the maximum value as the fitness score of the current strategy gene vector set;
(504) Performing iterative transformation on the current strategy gene vector set by adopting a cross mutation method, taking the strategy gene vector set after iterative transformation as the current strategy gene vector set, and returning to the step (503) until the fitness score of the strategy gene vector set is stable and unchanged;
(504) And (3) taking the strategy gene vector with the maximum fitness score in the strategy gene vector set when the fitness score is stable and unchanged as a new distribution strategy to replace the current distribution strategy, and returning to the step (2).
Compared with the background technology, the invention has the following advantages:
1. the invention provides a brand-new bandwidth self-adaptive multi-mode message intelligent distribution method, which solves the problem that the existing algorithm cannot carry out self-adaptive adjustment on a distribution strategy according to a multi-variable communication bandwidth environment, and avoids the phenomena of communication blockage, poor effectiveness, poor richness and poor completeness in the data chain distribution process.
2. The invention can better adjust various distribution strategies and support high-degree-of-freedom expansibility of the self-adaptive optimization distribution strategy.
Drawings
FIG. 1 is a block flow frame design of the present invention.
Detailed Description
The following description of the embodiments of the invention is presented in conjunction with the accompanying drawings to provide a better understanding of the invention to those skilled in the art. It is to be expressly noted that in the description below, detailed descriptions of known functions and designs are omitted here as perhaps obscuring the present invention.
Fig. 1 is a schematic flow diagram of an implementation of the bandwidth adaptive data link intelligent distribution policy optimization method of the present invention.
In this embodiment, the bandwidth adaptive data link intelligent distribution policy optimization method as shown in fig. 1 includes the following steps:
(1) Setting an initial distribution strategy as a current distribution strategy, wherein the initial distribution strategy comprises a data mode, a transmission frequency band and a retransmission requirement; wherein the data modalities include one or a combination of modalities of formatting messages, pictures, videos, and waveforms;
(2) Distributing the current data to be distributed by adopting a current distribution strategy, after the distribution is completed, evaluating the timeliness, completeness and richness of the whole distribution process according to a data link network transmission log and by using a set quality evaluation index to obtain an timeliness evaluation value, a completeness evaluation value and a richness evaluation value, and summing all the evaluation values to obtain a final quality evaluation result value of the distribution process;
(3) Obtaining self-adaptive optimized trend weights including an timeliness trend weight, a completeness trend weight and a richness trend weight through calculating reciprocal according to the timeliness evaluation value, the completeness evaluation value and the richness evaluation value which are obtained through evaluation;
(4) Setting a distribution quality threshold, if the final quality evaluation result value of the current distribution process is higher than the distribution quality threshold, indicating that the current distribution strategy is reasonable, otherwise, indicating that the current distribution strategy is unreasonable, and executing the step (5);
(5) And (3) automatically generating a new distribution strategy according to the self-adaptive optimization trend weight by utilizing a genetic algorithm, replacing the current distribution strategy, and returning to the step (2).
Wherein, the step (5) comprises the following steps:
(501) The current distribution strategy is abstracted into a strategy gene vector, each digit in the strategy gene vector represents one strategy content in the distribution strategy, for example, the first digit in the strategy gene vector represents a data mode, the digit 1 represents the data mode is a formatted message, and the digit 2 represents the data mode is a picture.
(502) Taking the differential weighting of the self-adaptive optimization tendency weight and the strategy gene vector as an adaptability function of a genetic algorithm, and adopting a random function to generate a plurality of strategy gene vectors to form a first generation strategy gene vector set which is used as a current strategy gene vector set;
(503) Calculating the score of the fitness function of each strategy gene vector, and selecting the maximum value as the fitness score of the current strategy gene vector set;
(504) Performing iterative transformation on the current strategy gene vector set by adopting a cross mutation method, taking the strategy gene vector set after iterative transformation as the current strategy gene vector set, and returning to the step (503) until the fitness score of the strategy gene vector set is stable and unchanged;
(504) And (3) taking the strategy gene vector with the maximum fitness score in the strategy gene vector set when the fitness score is stable and unchanged as a new distribution strategy to replace the current distribution strategy, and returning to the step (2).
While the foregoing describes illustrative embodiments of the present invention to facilitate an understanding of the present invention by those skilled in the art, it should be understood that the present invention is not limited to the scope of the embodiments, but is to be construed as protected by the accompanying claims insofar as various changes are within the spirit and scope of the present invention as defined and defined by the appended claims.
Claims (1)
1. A bandwidth self-adaptive data link intelligent distribution strategy optimization method is characterized by comprising the following steps:
(1) Setting an initial distribution strategy as a current distribution strategy, wherein the initial distribution strategy comprises a data mode, a transmission frequency band and a retransmission requirement; wherein the data modalities include one or a combination of modalities of formatting messages, pictures, videos, and waveforms;
(2) Distributing the current data to be distributed by adopting a current distribution strategy, after the distribution is completed, evaluating the timeliness, completeness and richness of the whole distribution process according to a data link network transmission log and by using a set quality evaluation index to obtain an timeliness evaluation value, a completeness evaluation value and a richness evaluation value, and summing all the evaluation values to obtain a final quality evaluation result value of the distribution process;
(3) Obtaining self-adaptive optimized trend weights including an timeliness trend weight, a completeness trend weight and a richness trend weight through calculating reciprocal according to the timeliness evaluation value, the completeness evaluation value and the richness evaluation value which are obtained through evaluation;
(4) Setting a distribution quality threshold, if the final quality evaluation result value of the current distribution process is higher than the distribution quality threshold, indicating that the current distribution strategy is reasonable, otherwise, indicating that the current distribution strategy is unreasonable, and executing the step (5);
(5) Automatically generating a new distribution strategy according to the self-adaptive optimization trend weight by utilizing a genetic algorithm to replace the current distribution strategy, and returning to the step (2);
wherein, the step (5) comprises the following steps:
(501) Abstracting the distribution strategy into a strategy gene vector, wherein each digit in the strategy gene vector represents one strategy content in the distribution strategy;
(502) Taking the differential weighting of the self-adaptive optimization tendency weight and the strategy gene vector as an adaptability function of a genetic algorithm, and adopting a random function to generate a plurality of strategy gene vectors to form a first generation strategy gene vector set which is used as a current strategy gene vector set;
(503) Calculating the score of the fitness function of each strategy gene vector, and selecting the maximum value as the fitness score of the current strategy gene vector set;
(504) Performing iterative transformation on the current strategy gene vector set by adopting a cross mutation method, taking the strategy gene vector set after iterative transformation as the current strategy gene vector set, and returning to the step (503) until the fitness score of the strategy gene vector set is stable and unchanged;
(504) And (3) taking the strategy gene vector with the maximum fitness score in the strategy gene vector set when the fitness score is stable and unchanged as a new distribution strategy to replace the current distribution strategy, and returning to the step (2).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211421295.0A CN115733839B (en) | 2022-11-14 | 2022-11-14 | Bandwidth-adaptive data link intelligent distribution strategy optimization method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211421295.0A CN115733839B (en) | 2022-11-14 | 2022-11-14 | Bandwidth-adaptive data link intelligent distribution strategy optimization method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115733839A CN115733839A (en) | 2023-03-03 |
| CN115733839B true CN115733839B (en) | 2023-09-12 |
Family
ID=85295608
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211421295.0A Active CN115733839B (en) | 2022-11-14 | 2022-11-14 | Bandwidth-adaptive data link intelligent distribution strategy optimization method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115733839B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2413302A1 (en) * | 2010-07-29 | 2012-02-01 | Andreas Kuhn | Method for traffic management of a street |
| CN103873479A (en) * | 2014-03-28 | 2014-06-18 | 北京邮电大学 | Parallel data transmission algorithm based on cross-layer estimation |
| CN103957267A (en) * | 2014-05-08 | 2014-07-30 | 中国人民解放军总参谋部气象水文空间天气总站 | Multi-network multi-task multi-node data distribution method |
| WO2016165392A1 (en) * | 2015-04-17 | 2016-10-20 | 华南理工大学 | Genetic algorithm-based cloud computing resource scheduling method |
| CN115079929A (en) * | 2021-03-12 | 2022-09-20 | 天翼云科技有限公司 | Path scheduling method and device, storage medium and electronic equipment |
-
2022
- 2022-11-14 CN CN202211421295.0A patent/CN115733839B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2413302A1 (en) * | 2010-07-29 | 2012-02-01 | Andreas Kuhn | Method for traffic management of a street |
| CN103873479A (en) * | 2014-03-28 | 2014-06-18 | 北京邮电大学 | Parallel data transmission algorithm based on cross-layer estimation |
| CN103957267A (en) * | 2014-05-08 | 2014-07-30 | 中国人民解放军总参谋部气象水文空间天气总站 | Multi-network multi-task multi-node data distribution method |
| WO2016165392A1 (en) * | 2015-04-17 | 2016-10-20 | 华南理工大学 | Genetic algorithm-based cloud computing resource scheduling method |
| CN115079929A (en) * | 2021-03-12 | 2022-09-20 | 天翼云科技有限公司 | Path scheduling method and device, storage medium and electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| ADS-B多数据链路融合方案探索;邱伟杰;;苏州科技学院学报(工程技术版)(02);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115733839A (en) | 2023-03-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110267338B (en) | Joint resource allocation and power control method in D2D communication | |
| CN109729528B (en) | D2D resource allocation method based on multi-agent deep reinforcement learning | |
| Sun et al. | Adaptive federated learning with gradient compression in uplink NOMA | |
| Wang et al. | Learn to compress CSI and allocate resources in vehicular networks | |
| CN108134843B (en) | Service function chain deployment method under 5G-C-RAN scene | |
| CN109587519B (en) | Heterogeneous network multipath video transmission control system and method based on Q learning | |
| CN110213776A (en) | A kind of WiFi discharging method based on Q study and multiple attribute decision making (MADM) | |
| CN102711125B (en) | Method for improving transmission capability of wireless mesh network | |
| CN111787543A (en) | 5G communication system resource allocation method based on improved wolf optimization algorithm | |
| CN115189910B (en) | Intentional attack survivability evaluation method based on network digital twin | |
| CN102208934A (en) | Antenna selection method based on full cross weight genetic algorithm | |
| CN107911857A (en) | A kind of multi-access method based on upstream and downstream decoupling in super-intensive heterogeneous network | |
| CN115733839B (en) | Bandwidth-adaptive data link intelligent distribution strategy optimization method | |
| CN110113803B (en) | Network access selection method based on user experience in heterogeneous network | |
| CN110677176A (en) | Combined compromise optimization method based on energy efficiency and spectrum efficiency | |
| Liu et al. | Power allocation in ultra-dense networks through deep deterministic policy gradient | |
| CN103188785B (en) | Optimization method of power distribution in accessing strategy of wireless relays of internet of things | |
| CN114257988B (en) | Imperfect CSI-oriented resource allocation method and system in ultra-reliable Internet of vehicles | |
| CN108494632B (en) | Mobile data traffic unloading method based on reinforcement learning | |
| CN110445566B (en) | Resource allocation method for reliable data transmission of industrial Internet of things | |
| CN110519664B (en) | Configuration method and device of transceiver in software defined optical network | |
| CN109327848B (en) | Wireless cache resource optimization method adopting zero-forcing beamforming | |
| CN107105451B (en) | A kind of link scheduling method based on minimum co-channel interference | |
| CN111919220A (en) | Adaptive pre-coding model training method, adaptive pre-coding method and base station | |
| CN111031606A (en) | Wireless network resource allocation method, system and storage medium |
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 |