CN114827152B - Low-delay cloud edge-side cooperative computing method and device for satellite-ground cooperative network - Google Patents
Low-delay cloud edge-side cooperative computing method and device for satellite-ground cooperative network Download PDFInfo
- Publication number
- CN114827152B CN114827152B CN202210763892.5A CN202210763892A CN114827152B CN 114827152 B CN114827152 B CN 114827152B CN 202210763892 A CN202210763892 A CN 202210763892A CN 114827152 B CN114827152 B CN 114827152B
- Authority
- CN
- China
- Prior art keywords
- base station
- delay
- computing
- task
- calculation
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B7/00—Radio transmission systems, i.e. using radiation field
- H04B7/14—Relay systems
- H04B7/15—Active relay systems
- H04B7/185—Space-based or airborne stations; Stations for satellite systems
- H04B7/1851—Systems using a satellite or space-based relay
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B7/00—Radio transmission systems, i.e. using radiation field
- H04B7/14—Relay systems
- H04B7/15—Active relay systems
- H04B7/185—Space-based or airborne stations; Stations for satellite systems
- H04B7/1851—Systems using a satellite or space-based relay
- H04B7/18513—Transmission in a satellite or space-based system
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Astronomy & Astrophysics (AREA)
- Aviation & Aerospace Engineering (AREA)
- General Physics & Mathematics (AREA)
- Mobile Radio Communication Systems (AREA)
- Radio Relay Systems (AREA)
Abstract
The invention discloses a satellite-ground cooperative network low-delay cloud edge-side cooperative computing method and device, which comprise the following steps: s1: collecting transmission power information, channel information, calculation task information and cloud end delay information required by the satellite-ground cooperative communication system to finish calculation and migration; s2: determining a system delay optimization problem based on a cloud edge cooperative computing mode; s3: solving the system delay optimization problem to obtain a calculation migration strategy of each user and each base station; s4: based on the obtained computing migration strategy, the user computing task is migrated to the base station and the cloud server to carry out cloud edge-side cooperative computing, and the result is returned to the user.
Description
Technical Field
The invention relates to the technical field of resource allocation in wireless communication, in particular to a satellite-ground cooperative network low-delay cloud edge-side cooperative computing method and device.
Background
The development of a single ground network is difficult to meet the future global communication requirement, and in the next generation mobile communication 6G white paper, the seamless connection between the ground network and the satellite network is provided for the future wireless network, and the satellite-ground cooperative network is a new trend for the development of the future communication network. When the satellite-ground cooperative network brings coverage advantages, a new challenge is also faced, and especially when a user accesses the internet through a satellite, a long transmission delay of a satellite-ground link brings extremely high communication delay, and the service quality of the user is difficult to guarantee.
Due to the advantages of computing and storage capabilities of cloud processing, services are provided in a communication network in a cloud processing-based mode. On the other hand, the edge server is arranged on the network edge side close to the user, and calculation and storage services are provided for the user on the network edge, so that the network delay can be greatly reduced, and the network response speed is improved. By combining the advantages of cloud computing and edge computing, cloud-side cooperative computing can effectively improve network computing capability, reduce network delay and improve system service efficiency.
Due to the fact that the computing capacity of the edge server is limited, a migration strategy needs to be determined according to the computing task requirements of the user, the data distribution proportion of local computing, edge computing and cloud computing of the user is optimized, and system delay is minimized. The current satellite-ground cooperative network cloud edge cooperative computing technology is still in a starting stage, and due to the long delay of a satellite-ground link, the traditional ground cloud edge cooperative computing method cannot be directly applied, the existing method is mainly independently researched aiming at a satellite-ground computing or base station computing scene, the advantages of a multi-stage network architecture in a satellite-ground system cannot be fully exploited, the satellite-ground cooperative network cloud edge cooperative computing architecture is not subjected to delay optimization, and the quality of user service in a future satellite-ground cooperative network is difficult to guarantee. In order to meet the diversified user requirements in the satellite-ground cooperative network in the future, an innovative low-delay computing migration method needs to be provided for a cloud edge-side cooperative computing architecture in the satellite-ground cooperative network.
Disclosure of Invention
The invention aims to provide a satellite-ground cooperative network low-delay cloud edge-side cooperative computing method and device to overcome the defects in the prior art.
In order to achieve the purpose, the invention provides the following technical scheme:
the invention discloses a satellite-ground cooperative network low-delay cloud edge-side cooperative computing method, which comprises the following steps of:
s1: collecting transmission power information, channel information, calculation task information and cloud end delay information required by the satellite-ground cooperative communication system to finish calculation and migration;
s2: determining a system delay optimization problem based on a cloud edge cooperative computing mode;
s3: solving the system delay optimization problem to obtain a calculation migration strategy of each user and each base station;
s4: and migrating the user computing task to the base station and the cloud server for cloud-side cooperative computing based on the obtained computing migration strategy, and returning the result to the user.
Preferably, in step S1, the satellite-ground cooperative communication system includes a space segment and a ground segment; the space segment comprises a plurality of satellites, and the ground segment comprises a user, a base station, a ground station and a cloud server; the satellite is connected with the ground station, the ground station is connected with the cloud server, and the cloud server provides cloud computing service; a plurality of base stations are covered under the satellite, the satellite is connected with the base stations within the coverage range of the satellite, and an edge server for computing service is arranged in each base station; the base station is covered with a plurality of users, the base station is connected with the users in the coverage range of the base station, and the users have the calculation capacity of performing local calculation; the user generates a computing task through computing, and the computing task is computed locally at the user or is migrated to a base station and a cloud server.
Preferably, in step S1, the transmission power information includes uplink transmission power information of each user and uplink transmission power information of each base station; the channel information comprises uplink average transmission channel information from each user to a base station and uplink average transmission channel information from each base station to a satellite; the calculation task information comprises the input data volume of each calculation task and the CPU calculation volume required by each bit of data of each calculation task; the cloud time delay information is two-way propagation time delay information from each base station to the cloud server, and the time delay is fixed link time delay generated by transmission distance and comprises fixed link time delay transmitted from the base station to the cloud server and fixed link time delay transmitted from the cloud server back to the base station.
Preferably, in step S2, the cloud-side collaborative computing means that the computing task of each user is collaboratively computed through user local computing, base station edge computing, and cloud server cloud computing.
Preferably, the system delay optimization problem represents minimizing a total delay from generation of a calculation task to acquisition of a calculation result by all users while satisfying system resource constraints.
Preferably, the step S2 includes the following sub-steps:
s21: calculating the average uplink transmission rate from each user to the base station, calculating uplink transmission delay based on the average uplink transmission rate, and calculating the calculation delay of the user task at the base station;
s22: calculating the average uplink transmission rate from each base station to the satellite, and calculating uplink transmission delay based on the average uplink transmission rate;
s23: calculating local calculation data delay of each user task, base station calculation data delay and cloud server calculation data delay; the user task total delay is the larger of task local computing data delay, base station computing data delay and cloud server computing data delay; the local computing data delay is the delay required by the task to complete the computation on partial data locally computed by the user; the base station computing data delay is the sum of the uplink transmission delay of the task transmitted from the user to the base station and the computing delay of the task in the base station; the cloud server computing data delay is the sum of uplink transmission delay of a task transmitted from a user to a base station, uplink transmission delay of the task transmitted from the base station to a satellite and bidirectional propagation delay of the base station to the cloud server;
s24: minimizing the total system delay under the system constraint to obtain the system delay optimization problem; the system constraints comprise a time frame length constraint of each base station, a time frame length constraint of a satellite, a calculation task decomposition constraint of each task and a total calculation capacity constraint of each base station; the total system delay is the sum of the total delays of all user tasks in the system.
Preferably, the step S3 includes the following sub-steps:
s31: initializing a base station time slot allocation strategy, a satellite time slot allocation strategy, a base station computing resource allocation strategy, a task decomposition strategy and an upper limit of iteration times;
s32: updating a base station time slot allocation strategy, a satellite time slot allocation strategy and a base station computing resource allocation strategy based on a resource updating strategy; the resource updating strategy is a resource updating strategy which enables the total delay of the system to be reduced;
s33: for each task, updating a task decomposition strategy based on the updated base station time slot allocation strategy, the satellite time slot allocation strategy and the base station computing resource allocation strategy to minimize the total time delay of the task;
s34: comparing the updated total system delay with the system total delay before updating, and setting a base station time slot allocation strategy, a satellite time slot allocation strategy, a base station computing resource allocation strategy and a task decomposition strategy which are stored in the iteration process into a delay smaller strategy;
s35: judging whether the iteration times reach the upper limit or not, if so, ending the iteration, and obtaining the calculation migration strategy of the user and the base station, namely the base station time slot allocation strategy, the satellite time slot allocation strategy, the base station calculation resource allocation strategy and the task decomposition strategy obtained in the step S34; if not, returning to step S32, and repeating the iteration process until the iteration is finished.
Preferably, the step S33 includes the following sub-steps:
s331: setting data migrated to the cloud server as zero for each task, calculating a task decomposition strategy when the local calculation data delay of the task and the calculation data delay of the base station are equal, and calculating the calculation delay of the task at the base station;
s332: judging the size relationship between the calculation delay of the base station and the bidirectional propagation delay from the base station to the cloud server of the task calculated in the step S331;
s333: if the calculation delay of the task at the base station, which is calculated in the step S331, is not greater than the bidirectional propagation delay from the base station to the cloud server, updating the task decomposition strategy to the strategy obtained in the step S331;
if the calculation delay of the task at the base station obtained by calculation in the step S331 is greater than the bidirectional propagation delay from the base station to the cloud server, the data migrated to the cloud server is set to be non-zero, and the task decomposition policy is calculated and updated to be the task decomposition policy when the task local calculation data delay, the base station calculation data delay, and the cloud server calculation data delay are equal.
Preferably, the step S4 includes the following sub-steps:
s41: each user locally calculates part of calculation tasks according to the calculated migration strategy obtained by solving;
s42: each user migrates part of the calculation tasks to the base station according to the calculation migration strategy obtained by solving, and the base station returns the calculation result to the user after completing the calculation;
s43: and the base station migrates part of the computing tasks to the cloud server according to the computing migration strategy obtained by solving, the cloud server returns the computing result to the base station after completing computing, and the base station further returns the result to the user.
The invention also discloses a satellite-ground cooperative network low-latency cloud edge cooperative computing device which comprises a memory and one or more processors, wherein executable codes are stored in the memory, and when the one or more processors execute the executable codes, the one or more processors are used for realizing the satellite-ground cooperative network low-latency cloud edge cooperative computing method.
The invention has the beneficial effects that: compared with the prior art, the low-delay cloud edge-end collaborative computing method and device for the satellite-ground collaborative network provided by the invention have the advantages that firstly, transmission power information, channel information, computing task information and cloud end delay information required by a satellite-ground collaborative communication system to complete computing migration are collected; then, determining a system delay optimization problem based on a cloud edge cooperative computing mode; then, solving the system delay optimization problem to obtain a calculation migration strategy of each user and each base station; finally, based on the obtained computing migration strategy, migrating the user computing task to the base station and the cloud server for cloud-side cooperative computing, and returning the result to the user; the method can fully utilize the multi-level network architecture in the satellite-ground cooperative communication system, obviously reduce the system delay through the cloud edge-end cooperative computing, and ensure the transmission of the user delay sensitive service.
Drawings
Fig. 1 is a flowchart of a low-latency cloud edge-side collaborative computing method of a satellite-ground collaborative network according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a satellite-ground cooperative communication system according to an embodiment of the present invention;
fig. 3 is a flowchart for collecting transmission power information, channel information, computation task information, and cloud delay information required by the satellite-ground cooperative communication system to complete computation migration according to the embodiment of the present invention;
fig. 4 is a flowchart of determining a system delay optimization problem based on a cloud-edge-side collaborative computing manner according to an embodiment of the present invention;
fig. 5 is a flowchart for solving a system delay optimization problem to obtain a migration calculation strategy for each user and base station according to the embodiment of the present invention;
fig. 6 is a flowchart for minimizing the total delay of the task based on the updated base station time slot allocation policy, the satellite time slot allocation policy, and the base station computing resource allocation policy, for each task according to the embodiment of the present invention;
fig. 7 is a schematic diagram illustrating comparison of performances of a satellite-ground cooperative network low-latency cloud edge-side cooperative computing method according to an embodiment of the present invention;
fig. 8 is a schematic diagram of a satellite-ground cooperative network low-latency cloud edge-side cooperative computing device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood, however, that the description herein of specific embodiments is only intended to illustrate the invention and not to limit the scope of the invention. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present invention.
The embodiment of the invention provides a satellite-ground cooperative network low-delay cloud edge-side cooperative computing method, and with reference to fig. 1, the method comprises the following steps:
s1, collecting transmission power information, channel information, calculation task information and cloud end delay information required by the satellite-ground cooperative communication system to finish calculation migration;
the process of collecting the transmission power information, the channel information, the calculation task information, and the cloud delay information required for the satellite-ground cooperative communication system to complete the calculation migration is described in detail below, and is not described herein again.
S2, determining a system delay optimization problem based on a cloud edge cooperative computing mode;
the cloud side collaborative computing mode means that computing tasks of each user are collaboratively computed through user local computing, base station edge computing and cloud server cloud computing. The system delay optimization problem represents minimizing the total delay from the generation of the computation tasks to the acquisition of the computation results for all users while satisfying the system resource constraints. The process is described in detail below and will not be described herein.
S3, solving the system delay optimization problem to obtain the calculation migration strategy of each user and each base station;
the calculation and migration strategy of each user and each base station comprises a base station time slot allocation strategy, a satellite time slot allocation strategy, a base station calculation resource allocation strategy and a task decomposition strategy. The process is described in detail below, and is not described herein again.
And S4, migrating the user computing task to the base station and the cloud server for cloud-side cooperative computing based on the obtained computing migration strategy, and returning the result to the user.
Compared with the existing satellite-ground network edge computing method, in the low-delay cloud edge-side collaborative computing method for the satellite-ground collaborative network provided by the embodiment of the invention, transmission power information, channel information, computing task information and cloud end delay information required by a satellite-ground collaborative communication system for completing computing migration are collected firstly; then, determining a system delay optimization problem based on a cloud edge cooperative computing mode; then, solving the system delay optimization problem to obtain a calculation migration strategy of each user and each base station; finally, based on the obtained computing migration strategy, migrating the user computing task to the base station and the cloud server for cloud-side cooperative computing, and returning the result to the user; the method can fully utilize the multi-level network architecture in the satellite-ground cooperative communication system, obviously reduce the system delay through the cloud edge-end cooperative computing, and ensure the transmission of the user delay sensitive service.
The foregoing briefly introduces a satellite-ground collaborative network low-latency cloud edge-side collaborative computing method, and details of the specific contents involved therein are described below.
In an alternative embodiment, referring to fig. 2, a satellite-to-ground cooperative communication system includes:
the satellite-ground cooperative communication system comprises a space section and a ground section;
the space section consists of satellites, and the satellites can be low-orbit satellites, medium-orbit satellites and high-orbit satellites according to an actual network, and the transmission delay and the service capacity of the satellites in different orbits are different;
the ground section consists of a user, a base station, a ground station and a cloud server;
the satellite is connected with a ground station, the ground station is connected with a cloud server, and the cloud server can provide cloud computing service; the satellite is connected with a ground base station in the coverage range of the satellite, and the satellite provides return transmission for the ground base station;
the total number of base stations in the system is N, and the base stations are provided with edge servers which can be used for computing services and can provide edge computing services for users;
base stations are connected to users within their coverage area, each base station serving within the coverage area
The user is only connected with the subordinate base station, the subordinate base station means that the user is positioned in the coverage range of the base station, and the user obtains the calculation service through the base station;
the user has computing capacity, and computing tasks can be computed locally by the user, can be migrated to a base station, or can be further migrated to a cloud server through a satellite for computing; for any user k within the coverage range of any base station n, the user only generates one calculation task at the same time, and the calculation process is as follows:
the user k divides the calculation task into two parts, one part carries out local calculation, and the other part is transmitted to the base station n through a wireless channel;
after part of the calculation task of the user k is transmitted to the base station, the base station further divides the part of the calculation task into two parts, one part carries out edge calculation at the base station, and the other part is transmitted to the satellite through a wireless channel;
and after part of the computing tasks of the user k are transmitted to the satellite, the satellite further transfers the part of the computing tasks to the cloud server for computing.
Optionally, referring to fig. 3, collecting transmission power information, channel information, computation task information, and cloud delay information required for the satellite-ground cooperative communication system to complete computation migration includes:
s11, collecting the uplink transmission power information of each user and the uplink transmission power information of each base station;
the uplink transmission power of user k in the coverage of base station n is
The uplink transmission power of base station n is
。
S12, collecting the uplink average transmission channel information from each user to the base station and the uplink average transmission channel information from each base station to the satellite;
the average transmission channel information represents the average transmission channel information in the process that the user completes the calculation task transmission, the average value can be obtained based on the channel large-scale fading and historical channel information, and the uplink average transmission channel from the user k to the base station n is represented as
The average transmission channel of the base station n to the satellite is denoted as
；
S13, collecting the input data volume of each calculation task and the CPU calculation volume required by each bit of data of each calculation task;
in the system, each user has a computing task that requires computing. For user k in the coverage area of base station n, the calculation task is expressed as
Wherein
In order to calculate the amount of input data for a task,
is the amount of CPU computation required to compute each bit of data for a task, so that the total amount of computation required for each task is
；
S14, collecting bidirectional propagation delay information from each base station to a cloud server;
due to the long time delay of the satellite-ground link, when a computing task is migrated from a base station n to a satellite and further from the satellite to a cloud server, the bidirectional propagation delay caused by link transmission needs to be considered, and the bidirectional propagation delay from the base station n to the cloud server is expressed as:
wherein
Is the transmission distance of the base station n to the satellite,
is the transmission distance of the satellite to the ground station,
it is the speed of light that is,
is the two-way propagation delay from the ground station to the cloud server.
Optionally, referring to fig. 4, determining a system delay optimization problem based on a distributed collaborative computing migration method includes:
s21, for each user, calculating the average uplink transmission rate from the user to the base station, calculating the uplink transmission delay based on the average uplink transmission rate, and calculating the calculation delay of the user task at the base station;
for each user, communicating with the base station based on time division multiple access, migrating the computation task to the base station. Order to
In order to be able to transmit the bandwidth,
is the noise power spectral density, so the average uplink transmission rate of user k in the coverage area of base station n is:
order to
Representing computational tasks
The proportion of data calculated locally at the user,
for each time frame length, the time slot length allocated to user k is
And the time slot allocation strategy is kept unchanged in the transmission process, so that the average uplink transmission delay from the user to the base station is as follows:
in addition, the return data volume of the calculation result is far smaller than the input data volume of the calculation task, so that the downlink transmission delay for retrieving the calculation result from the base station is ignored.
Order to
Representing computational tasks
The proportion of data calculated at the base station,
indicating allocated base station computing resources, in computing tasks
After migrating to the base station, computing tasks
The calculated delay at the base station is:
s22, for each base station, calculating the average uplink transmission rate from the base station to the satellite, and calculating the uplink transmission delay based on the average uplink transmission rate;
for each base station, communicating with the base station based on time division multiple access, migrating the computing task to the satellite. Order to
In order to be able to transmit the bandwidth,
is the noise power spectral density, so the average uplink transmission rate from base station n to the satellite is:
order to
Representing computational tasks
The proportion of data calculated at the cloud server,
for each time frame length, the time slot length allocated to user k is
And the time slot allocation strategy is kept unchanged in the transmission process, so that the average uplink transmission delay of the user task from the base station to the satellite is as follows:
furthermore, the amount of returned data for the calculation results is considered to be much smaller than the amount of input data for the calculation tasks, so that the downlink transmission delay for retrieving the calculation results from the satellite is ignored.
Based on a large antenna and Ku/Ka frequency band broadband transmission, the downlink transmission from a satellite to a ground station can realize higher transmission rate from hundreds of MB/s to GB/s. On the other hand, the amount of data input by the user's computing task is typically on the order of tens of KB to hundreds of KB, much smaller than the satellite downlink transmission rate, so that the transmission delay from the satellite to the ground station, and the transmission delay from the ground station back to the satellite, can be neglected. Due to the long time delay of the satellite-ground link, when a computing task is migrated to a cloud server, the bidirectional propagation time delay from a base station to the cloud server still needs to be considered
。
S23, calculating local calculation data delay of the user task, base station calculation data delay and cloud server calculation data delay for each user;
for user k in the coverage of base station n, order
Representing user computational capacity, tasks
The local computation data delay is
Task
The base station calculates the data delay of
Task
The cloud server computing data delay is
The total time delay of the user task is
S24, minimizing the total system delay under the system constraint to obtain a system delay optimization problem;
the system delay optimization problem is as follows:
wherein
Representing the total calculated capacity of each base station; the system constraint comprises a time frame length constraint of each base station, a time frame length constraint of a satellite, a calculation task decomposition constraint of each task and a total calculation capacity constraint of each base station; optimization variable is base station time slot allocation strategy
Satellite time slot allocation strategy
Base station computing resource allocation strategy
Task decomposition strategy
(ii) a The total system delay is the sum of the total delays of all user tasks in the system.
Optionally, referring to fig. 5, solving the system delay optimization problem to obtain the migration policy of each user and base station includes:
s31, initializing a base station time slot allocation strategy, a satellite time slot allocation strategy, a base station computing resource allocation strategy, a task decomposition strategy and an iteration upper limit;
initialized to a size of
Of particles of (a), each particle having a position vector of
Is shown byOne possible combination of base station time slot allocation strategy, satellite time slot allocation strategy and base station computing resource allocation strategy, wherein
Indicating the base station time slot allocation strategy in the strategy combination,
indicating the slot allocation policy for the satellites in the policy combination,
indicating the base station computing resource allocation strategy in the strategy combination. The velocity vector of each particle is
Represents a moving tendency of each particle, wherein
Indicating the moving trend of the base station time slot allocation strategy,
indicating the trend of the satellite time slot allocation strategy,
representing the moving trend of the base station computing resource allocation strategy. During the search, each particle will record the local best position that the particle has experienced
At the same time, use
The global best position experienced by all particles is recorded.
The initial position and initial velocity of each particle satisfy the following conditions
Initializing task decomposition policies
Initializing a maximum number of iterations
。
S32, updating a base station time slot allocation strategy, a satellite time slot allocation strategy and a base station computing resource allocation strategy based on the resource updating strategy;
in each iteration, the position and velocity of each particle is updated as follows
Wherein
Is the number of iterations that are to be performed,
is the weight of the inertia, and,
is the acceleration factor of the vehicle as a function of time,
are independent random variables.
S33, for each task, updating a task decomposition strategy based on the updated base station time slot allocation strategy, the satellite time slot allocation strategy and the base station computing resource allocation strategy, and minimizing the total time delay of the task;
for each task
Updated base station time slot allocation strategy
Is composed of
In (1)
Updated satellite slot allocation strategy
Is composed of
In (1)
And the updated base station computing resource allocation strategy
Is composed of
In (1)
(ii) a Updating task decomposition strategy based on updated base station time slot allocation strategy, satellite time slot allocation strategy and base station computing resource allocation strategy
Minimizing the total delay of the task
(ii) a The process is described in detail below and will not be described herein.
S34, comparing the updated total system delay with the total system delay before updating, and setting a base station time slot allocation strategy, a satellite time slot allocation strategy, a base station computing resource allocation strategy and a task decomposition strategy which are stored in the iteration process as a delay smaller strategy;
order to
Indicating particle
Calculating the total system delay under a corresponding calculation resource allocation strategy;
local best position update of each particle to
Global best location update as
S35, judging whether the iteration number reaches the upper limit;
judging the number of iterations
Whether or not the maximum number of iterations has been reached
。
S36, if the upper limit is reached, the iteration is finished, and a user and base station calculation migration strategy is obtained;
obtaining a base station time slot allocation strategy, a satellite time slot allocation strategy and a base station computing resource allocation strategy as the global best position
Corresponding computing resource allocation strategy, and obtaining task decomposition strategy as global best position
Counting based on step S33And (5) calculating a task decomposition strategy.
S37, if the upper limit is not reached, the iteration process is repeatedly executed until the iteration is finished;
returning to step S32, the iteration is repeatedly executed until the iteration is finished.
Optionally, referring to fig. 6, for each task, updating the task decomposition policy based on the updated base station time slot allocation policy, the satellite time slot allocation policy, and the base station computing resource allocation policy, where minimizing the total time delay of the task includes:
s331, setting data migrated to a cloud server as zero for each task, calculating a task decomposition strategy when the local calculation data delay of the task and the calculation data delay of a base station are equal, and calculating the calculation delay of the task at the base station;
for each task
Setting up
The task decomposition strategy for calculating when the task local calculation data delay and the base station calculation data delay are equal is
Calculating the calculation delay of the task at the base station as
S332, judging the size relation between the calculation delay of the task in the base station and the bidirectional propagation delay from the base station to the cloud server;
judgment of
And
the magnitude relationship between them.
S333, if the calculation delay of the task at the base station is not larger than the bidirectional propagation delay from the base station to the cloud server, updating the task decomposition strategy into the strategy obtained in the S331;
if it is
The task is not migrated to the cloud server, and a task decomposition strategy is obtained as
S334, if the calculation delay of the task at the base station is greater than the bidirectional propagation delay from the base station to the cloud server, setting the data transferred to the cloud server to be nonzero, and calculating and updating a task decomposition strategy to be the task decomposition strategy when the calculation delay of the task local calculation data, the calculation delay of the base station and the calculation delay of the cloud server are equal;
if it is
The task is migrated to the cloud server to obtain a task decomposition strategy of
The invention provides a low-delay cloud-edge collaborative computing method for a satellite-ground collaborative network. The original calculation migration problem is decomposed and decoupled, calculation migration strategies of a user and a base station are obtained through solution respectively, and total system delay is minimized.
A schematic diagram of the satellite-ground cooperative communication system of the present invention is shown in fig. 2, wherein the total number of base stations is 10, and each base station serves 5 users within a coverage area of 250 m. For each task, the amount of input data is [100, 500 ]]Randomly distributed in Kb range, the calculation amount required by each bit is 1000 CPU cycles, and the total calculation capacity of the user is
cycle/s, total calculated capacity of base station of
cycle/s. Referring to fig. 7 (comparison of the proposed cloud edge-side cooperative computing policy with the local computing policy and the edge computing policy), it can be seen that the proposed cloud edge-side cooperative computing policy can effectively reduce the satellite-ground cooperative communication system computing delay, which can be reduced by 85% of the total system delay compared to the local computing policy and can be reduced by 55% of the total system delay compared to the edge computing policy.
The computer program product of the satellite-ground cooperative network low-latency cloud edge-side cooperative computing method provided by the embodiment of the present invention includes a computer-readable storage medium storing a program code, where instructions included in the program code may be used to execute the method described in the foregoing method embodiment, and specific implementation may refer to the method embodiment, which is not described herein again.
It can be clearly understood by those skilled in the art that, for convenience and simplicity of description, the specific working process of the system and the apparatus described above may refer to the corresponding process in the foregoing method embodiment, and details are not described herein again.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Referring to fig. 8, an embodiment of the present invention further provides a satellite-ground cooperative network low-latency cloud edge-side cooperative computing apparatus, further including a memory and one or more processors, where the memory stores executable codes, and when the one or more processors execute the executable codes, the one or more processors are configured to implement the satellite-ground cooperative network low-latency cloud edge-side cooperative computing method in the foregoing embodiment.
The embodiment of the invention relates to a satellite-ground cooperative network low-delay cloud edge-side cooperative computing device, which can be applied to any equipment with data processing capability, such as computers and other equipment or devices. The device embodiments may be implemented by software, or by hardware, or by a combination of hardware and software. The software implementation is taken as an example, and as a logical device, the device is formed by reading corresponding computer program instructions in the nonvolatile memory into the memory for running through the processor of any device with data processing capability. From a hardware aspect, as shown in fig. 8, the present invention is a hardware structure diagram of any device with data processing capability where a satellite-ground cooperative network low-latency cloud edge-side cooperative computing apparatus is located, where, in addition to the processor, the memory, the network interface, and the nonvolatile memory shown in fig. 8, any device with data processing capability where the apparatus is located in the embodiment may also include other hardware according to the actual function of the any device with data processing capability, which is not described again. The implementation process of the functions and actions of each unit in the above device is specifically described in the implementation process of the corresponding step in the above method, and is not described herein again.
For the device embodiment, since it basically corresponds to the method embodiment, reference may be made to the partial description of the method embodiment for relevant points. The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the invention. One of ordinary skill in the art can understand and implement it without inventive effort.
The embodiment of the invention also provides a computer-readable storage medium, wherein a program is stored on the computer-readable storage medium, and when the program is executed by a processor, the low-latency cloud edge-side collaborative computing method of the satellite-ground collaborative network in the embodiment is realized.
The computer readable storage medium may be an internal storage unit, such as a hard disk or a memory, of any data processing capability device described in any of the foregoing embodiments. The computer readable storage medium may also be any external storage device of a device with data processing capabilities, such as a plug-in hard disk, a Smart Media Card (SMC), an SD Card, a Flash memory Card (Flash Card), etc. provided on the device. Further, the computer readable storage medium may include both an internal storage unit and an external storage device of any data processing capable device. The computer-readable storage medium is used for storing the computer program and other programs and data required by the arbitrary data processing-capable device, and may also be used for temporarily storing data that has been output or is to be output.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents or improvements made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (7)
1. A satellite-ground cooperative network low-delay cloud edge-side cooperative computing method is characterized by comprising the following steps: the method comprises the following steps:
s1: collecting transmission power information, channel information, calculation task information and cloud end delay information required by the satellite-ground cooperative communication system to finish calculation and migration;
s2: the method comprises the following steps of determining a system delay optimization problem based on a cloud edge collaborative computing mode, wherein the specific substeps are as follows:
s21: calculating the average uplink transmission rate from each user to the base station, calculating uplink transmission delay based on the average uplink transmission rate, and calculating the calculation delay of the user task at the base station;
s22: calculating the average uplink transmission rate from each base station to the satellite, and calculating uplink transmission delay based on the average uplink transmission rate;
s23: calculating local calculation data delay of each user task, base station calculation data delay and cloud server calculation data delay; the user task total delay is the larger of task local computing data delay, base station computing data delay and cloud server computing data delay; the local calculation data delay is the delay required by the task to complete the calculation on partial data calculated locally by the user; the base station computing data delay is the sum of the uplink transmission delay of the task transmitted from the user to the base station and the computing delay of the task in the base station; the cloud server computing data delay is the sum of uplink transmission delay of a task transmitted from a user to a base station, uplink transmission delay of the task transmitted from the base station to a satellite and bidirectional propagation delay of the base station to the cloud server;
s24: minimizing the total system delay under the system constraint to obtain the system delay optimization problem; the system constraints comprise a time frame length constraint of each base station, a time frame length constraint of a satellite, a calculation task decomposition constraint of each task and a total calculation capacity constraint of each base station; the total system delay is the sum of the total delays of all user tasks in the system;
s3: solving the system delay optimization problem to obtain a calculation migration strategy of each user and each base station, wherein the specific substeps are as follows:
s31: initializing a base station time slot allocation strategy, a satellite time slot allocation strategy, a base station computing resource allocation strategy, a task decomposition strategy and an upper limit of iteration times;
s32: updating a base station time slot allocation strategy, a satellite time slot allocation strategy and a base station computing resource allocation strategy based on a resource updating strategy; the resource updating strategy is a resource updating strategy which enables the total delay of the system to be reduced;
s33: for each task, updating a task decomposition strategy based on an updated base station time slot allocation strategy, a satellite time slot allocation strategy and a base station computing resource allocation strategy, and minimizing the total time delay of the task, wherein the specific substeps are as follows:
s331: for each task, setting data migrated to the cloud server to be zero, calculating a task decomposition strategy when the task local calculation data delay and the base station calculation data delay are equal, and calculating the calculation delay of the task at the base station;
s332: judging the size relationship between the calculation delay of the base station and the bidirectional propagation delay from the base station to the cloud server of the task calculated in the step S331;
s333: if the calculation delay of the task at the base station, which is calculated in the step S331, is not greater than the bidirectional propagation delay from the base station to the cloud server, updating the task decomposition strategy to the strategy obtained in the step S331;
if the calculation delay of the task at the base station obtained by calculation in the step S331 is greater than the bidirectional propagation delay from the base station to the cloud server, setting the data migrated to the cloud server to be nonzero, and calculating and updating the task decomposition strategy to be the task decomposition strategy when the task local calculation data delay, the base station calculation data delay and the cloud server calculation data delay are equal;
s34: comparing the updated total system delay with the system total delay before updating, and setting a base station time slot allocation strategy, a satellite time slot allocation strategy, a base station computing resource allocation strategy and a task decomposition strategy which are stored in the iteration process into a delay smaller strategy;
s35: judging whether the iteration times reach the upper limit or not, if so, ending the iteration, and obtaining the calculation migration strategy of the user and the base station, namely the base station time slot allocation strategy, the satellite time slot allocation strategy, the base station calculation resource allocation strategy and the task decomposition strategy obtained in the step S34; if not, returning to the step S32, and repeatedly executing the iteration process until the iteration is finished;
s4: and based on the obtained computing migration strategy, migrating the user computing task to the base station and the cloud server for cloud-side cooperative computing, and returning the result to the user.
2. The satellite-ground cooperative network low-latency cloud edge-side cooperative computing method according to claim 1, characterized in that: in the step S1, the satellite-ground cooperative communication system includes a space segment and a ground segment; the space segment comprises a plurality of satellites, and the ground segment comprises a user, a base station, a ground station and a cloud server; the satellite is connected with the ground station, the ground station is connected with the cloud server, and the cloud server provides cloud computing service; a plurality of base stations are covered under the satellite, the satellite is connected with the base stations within the coverage range of the satellite, and an edge server for computing service is arranged in each base station; the base station is covered with a plurality of users, the base station is connected with the users in the coverage range of the base station, and the users have the calculation capacity of performing local calculation; the user generates a computing task through computing, and the computing task is computed locally at the user or is migrated to a base station and a cloud server.
3. The satellite-ground cooperative network low-latency cloud edge-side cooperative computing method according to claim 1, characterized in that: in step S1, the transmission power information includes uplink transmission power information of each user and uplink transmission power information of each base station; the channel information comprises uplink average transmission channel information from each user to a base station and uplink average transmission channel information from each base station to a satellite; the calculation task information comprises the input data volume of each calculation task and the CPU calculation volume required by each bit of data of each calculation task; the cloud time delay information is two-way propagation time delay information from each base station to the cloud server, and the time delay is fixed link time delay generated by transmission distance and comprises fixed link time delay transmitted from the base station to the cloud server and fixed link time delay transmitted from the cloud server back to the base station.
4. The satellite-ground cooperative network low-latency cloud edge-side cooperative computing method according to claim 1, characterized in that: in step S2, the cloud-side cooperative computing mode indicates that the computing task of each user is cooperatively computed by the user local computing, the base station edge computing, and the cloud server cloud computing.
5. The satellite-ground cooperative network low-latency cloud edge-side cooperative computing method according to claim 1, characterized in that: the system delay optimization problem represents minimizing the total delay from the generation of the calculation tasks to the acquisition of the calculation results by all users while satisfying the system resource constraints.
6. The method for low-latency cloud-edge collaborative computing of the satellite-ground collaborative network according to claim 1, wherein: the step S4 includes the following sub-steps:
s41: each user locally calculates part of calculation tasks according to the calculated migration strategy obtained by solving;
s42: each user migrates part of the calculation tasks to the base station according to the calculation migration strategy obtained by solving, and the base station returns the calculation result to the user after completing the calculation;
s43: and the base station migrates part of the computing tasks to the cloud server according to the computed migration strategy obtained by solving, the cloud server returns the computing result to the base station after completing computing, and the base station further returns the result to the user.
7. The utility model provides a low time delay cloud limit of satellite-ground cooperative network side cooperative computing device which characterized in that: the device comprises a memory and one or more processors, wherein executable codes are stored in the memory, and when the one or more processors execute the executable codes, the one or more processors are used for realizing the satellite-to-ground cooperative network low-latency cloud edge-side cooperative computing method in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210763892.5A CN114827152B (en) | 2022-07-01 | 2022-07-01 | Low-delay cloud edge-side cooperative computing method and device for satellite-ground cooperative network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210763892.5A CN114827152B (en) | 2022-07-01 | 2022-07-01 | Low-delay cloud edge-side cooperative computing method and device for satellite-ground cooperative network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114827152A CN114827152A (en) | 2022-07-29 |
| CN114827152B true CN114827152B (en) | 2022-09-27 |
Family
ID=82523166
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210763892.5A Active CN114827152B (en) | 2022-07-01 | 2022-07-01 | Low-delay cloud edge-side cooperative computing method and device for satellite-ground cooperative network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114827152B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115801091B (en) * | 2022-10-11 | 2024-08-20 | 西安电子科技大学 | Large-scale constellation network resource scheduling method for satellite-ground cooperative computing |
| WO2024183050A1 (en) * | 2023-03-09 | 2024-09-12 | 之江实验室 | Satellite-ground cooperative network content caching method in differentiated interest and access mode |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112272198A (en) * | 2020-09-03 | 2021-01-26 | 中国空间技术研究院 | Satellite network-oriented collaborative computing task migration method and device |
| CN113709775A (en) * | 2021-10-27 | 2021-11-26 | 之江实验室 | Distributed cooperative computing migration method for satellite-ground cooperative communication system |
| CN113939034A (en) * | 2021-10-15 | 2022-01-14 | 华北电力大学 | Cloud edge-side cooperative resource allocation method for stereo heterogeneous power Internet of things |
| WO2022021176A1 (en) * | 2020-07-28 | 2022-02-03 | 苏州大学 | Cloud-edge collaborative network resource smooth migration and restructuring method and system |
| CN114143355A (en) * | 2021-12-08 | 2022-03-04 | 华北电力大学 | Low-delay safety cloud side end cooperation method for power internet of things |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10659526B2 (en) * | 2018-01-03 | 2020-05-19 | Verizon Patent And Licensing Inc. | Edge compute systems and methods |
| CN111629400B (en) * | 2019-02-27 | 2022-03-29 | 华为技术有限公司 | Method, device and system for satellite cooperative communication |
| CN114051254B (en) * | 2021-11-08 | 2024-05-03 | 南京大学 | Green cloud edge collaborative computing unloading method based on star-ground fusion network |
| CN114268357B (en) * | 2021-11-28 | 2023-04-25 | 西安电子科技大学 | Method, system, equipment and application for unloading computing tasks based on low-orbit satellite edges |
| CN114520990B (en) * | 2022-01-24 | 2023-05-26 | 重庆邮电大学 | Mobile edge computing task unloading method based on star-ground cloud cooperation |
-
2022
- 2022-07-01 CN CN202210763892.5A patent/CN114827152B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022021176A1 (en) * | 2020-07-28 | 2022-02-03 | 苏州大学 | Cloud-edge collaborative network resource smooth migration and restructuring method and system |
| CN112272198A (en) * | 2020-09-03 | 2021-01-26 | 中国空间技术研究院 | Satellite network-oriented collaborative computing task migration method and device |
| CN113939034A (en) * | 2021-10-15 | 2022-01-14 | 华北电力大学 | Cloud edge-side cooperative resource allocation method for stereo heterogeneous power Internet of things |
| CN113709775A (en) * | 2021-10-27 | 2021-11-26 | 之江实验室 | Distributed cooperative computing migration method for satellite-ground cooperative communication system |
| CN114143355A (en) * | 2021-12-08 | 2022-03-04 | 华北电力大学 | Low-delay safety cloud side end cooperation method for power internet of things |
Non-Patent Citations (1)
| Title |
|---|
| 边缘计算迁移研究综述;朱友康等;《电信科学》;20190430(第04期);80-100 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114827152A (en) | 2022-07-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114827152B (en) | Low-delay cloud edge-side cooperative computing method and device for satellite-ground cooperative network | |
| CN112689303B (en) | Edge cloud cooperative resource joint allocation method, system and application | |
| CN111400001B (en) | Online computing task unloading scheduling method facing edge computing environment | |
| CN112015545B (en) | Task unloading method and system in vehicle edge computing network | |
| CN114153572A (en) | Calculation unloading method for distributed deep learning in satellite-ground cooperative network | |
| CN113346938B (en) | Edge computing resource fusion management method for space-time integrated network | |
| CN110417456B (en) | Information transmission method based on unmanned aerial vehicle | |
| CN111163519A (en) | Wireless body area network resource allocation and task unloading algorithm with maximized system benefits | |
| Wu et al. | Intelligent resource allocation scheme for cloud-edge-end framework aided multi-source data stream | |
| CN113709775B (en) | Distributed cooperative computing migration method for satellite-ground cooperative communication system | |
| CN114051254B (en) | Green cloud edge collaborative computing unloading method based on star-ground fusion network | |
| CN113344255B (en) | Vehicle-mounted network application data transmission and charging optimization method based on mobile edge calculation and block chain | |
| CN108601074A (en) | A kind of network resource allocation method and device based on isomery joint caching | |
| Lyu et al. | Computation bits maximization in UAV-enabled mobile-edge computing system | |
| CN110401936A (en) | A kind of task unloading and resource allocation methods based on D2D communication | |
| CN116489708B (en) | Meta universe oriented cloud edge end collaborative mobile edge computing task unloading method | |
| CN112822707A (en) | Task unloading and resource allocation method in computing resource limited MEC | |
| CN114697978B (en) | Intelligent reflecting surface-assisted uplink movement edge calculation method and system | |
| CN114449490A (en) | Multi-task joint computing unloading and resource allocation method based on D2D communication | |
| Li et al. | Multi-task offloading scheme for UAV-enabled fog computing networks | |
| CN116112981A (en) | Unmanned aerial vehicle task unloading method based on edge calculation | |
| CN117040594A (en) | Internet remote sensing satellite real-time service system oriented to mobile terminal user | |
| CN113378369B (en) | Path planning and task scheduling method based on unmanned aerial vehicle calculation unloading | |
| Chen et al. | Distributed task offloading game in multiserver mobile edge computing networks | |
| CN116419325A (en) | Task unloading, resource allocation and track planning method and system for collaborative calculation of multiple unmanned aerial vehicles |
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 |