Joint resource allocation method for underwater cloud-edge collaborative network

WO2024193729A3PCT designated stage expired Publication Date: 2024-11-21ZHEJIANG UNIV
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2024/094378
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-03-21
Filing Date
2024-05-21
Publication Date
2024-11-21

AI Technical Summary

Technical Problem

Traditional cloud computing has problems such as insufficient real-time performance, insufficient bandwidth, high energy consumption, lack of mobility support and location awareness when processing underwater sensor data in the marine environment, resulting in low efficiency in processing massive ocean data. Existing edge computing is under water The application of scenarios has not been fully studied, especially the lack of effective strategies for resource optimization algorithms and energy loss and delay optimization.

Method used

The resource joint allocation method of the underwater edge cloud collaborative network is adopted. The water area is divided into rectangular grids. Underwater sensors and mobile submersibles are set up in each grid. The APPROX-TSP-TOUR algorithm is used to plan the Hamiltonian cycle and calculate the system time. Delay and energy loss, build a resource allocation model that takes into account delay and energy loss, and use linear programming to solve the optimal resource allocation strategy.

Benefits of technology

It improves the resource allocation efficiency of data collection in underwater environments, saves energy, reduces latency, avoids uneven resource allocation, and ensures data security and privacy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2024094378_21112024_PF_FP_ABST
    Figure CN2024094378_21112024_PF_FP_ABST
Patent Text Reader

Abstract

Disclosed in the present invention is a joint resource allocation method for an underwater cloud-edge collaborative network. The method comprises the following steps: according to geographic locations, dividing a water region into several rectangular grids having equal areas; obtaining a Hamiltonian loop according to an APPROX-TSP-TOUR algorithm; calculating a system delay and an energy loss, wherein the system delay comprises: a service transmission delay, a service calculation delay and a service movement delay, and the energy loss comprises an underwater moving-ahead energy loss, calculation loss and communication transmission loss of an underwater mobile submersible vehicle; and constructing a resource allocation model in which both the system delay and the energy loss are taken into consideration, and performing calculation by means of linear programming, so as to obtain an optimal resource allocation strategy. In the present invention, a regional collection strategy is specified for underwater sensor data, and a collection path is programmed, such that the efficiency is improved, the energy is saved, and the phenomenon of uneven resource allocation is avoided; and a resource allocation model in which both a system delay and an energy loss are taken into consideration is constructed, such that a relatively short delay is ensured while the energy loss is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

A joint resource allocation method for underwater edge-cloud collaborative networks

[0001] This application claims priority to the Chinese patent application filed with the Patent Office of China on March 21, 2023, with application number 202310275403.6 and invention name “A method for joint resource allocation in an underwater edge-cloud collaborative network”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present invention relates to the field of edge computing, and in particular to a resource joint allocation method for an underwater edge-cloud collaborative network. Background Art

[0003] With the continuous innovation of technologies such as the Internet of Things and Big Data, the era of the Internet of Everything has arrived. This sustained and rapid growth in data volumes has driven the evolution of computing models and, at the same time, placed higher demands on data storage and processing technologies, particularly for real-time management and intelligent analysis of services at the network edge. However, due to the inherent drawbacks of traditional cloud computing, such as insufficient real-time performance, insufficient bandwidth, high energy consumption, and a lack of mobility and location awareness, its key technologies are no longer able to efficiently process the massive amounts of data generated by edge devices. Therefore, edge computing has emerged as a new computing model. By extending computing power from cloud data centers to the network edge, it enables more flexible and controllable local data analysis and management, and is fundamental to the implementation of the Internet of Things.

[0004] Nowadays, IoT devices are widely used in marine environments, primarily for exploration and development in ocean monitoring and exploration, primarily focusing on the perception layer. This has significantly boosted the development of underwater sensor networks. With the increasing number of sensor nodes, the linear growth of centralized cloud computing is no longer sufficient to keep up with the explosive growth of massive ocean data (including measured ocean data, remote sensing data, and ocean pattern data). The burden of transmitting this massive data from the underlying devices of underwater sensor networks to cloud centers is increasing. Therefore, the emergence of edge computing has mitigated this problem. Processing data at the edge of the network reduces underlying request response times, improves battery life of underlying devices, and reduces network bandwidth while ensuring data security and privacy. Therefore, the introduction of edge computing is a significant initiative for both marine development and national sustainable development, and is of great significance.

[0005] As an emerging computing paradigm, edge computing pushes elastic resources such as computing, storage, and networking to the edge of the network, providing local intelligent computing services and addressing issues such as high latency and poor mobility in cloud computing. Compared to cloud data centers, limited edge cloud resources are a key bottleneck in improving edge computing performance, especially when computing loads and resource distribution are unevenly distributed in time and space. Therefore, designing efficient resource optimization strategies to achieve the optimal scheduling of edge-to-edge cloud computing resources and the rapid and efficient execution of computing tasks remains a key research focus and challenge in the field of edge computing.

[0006] Unlike the rapid development of edge computing in terrestrial scenarios, which are primarily based on wireless communications, research on applying this technology to the specialized underwater scenario is still in its infancy. The underwater environment is complex and dynamic, energy resupply is difficult, communication distances are limited, and latency is long. Consequently, few edge computing offloading strategies and resource optimization algorithms are available for this specific scenario. Directly applying algorithms developed for terrestrial scenarios to underwater scenarios would be impossible to analyze specific problems and would be unlikely to achieve ideal results. Furthermore, existing strategies for underwater sensor data collection mostly focus solely on planning the collection path, rarely factoring in both energy loss and system latency as optimization objectives.

[0007] Summary of the Invention

[0008] In view of the shortcomings of the existing technology, the present invention proposes a resource joint allocation method for underwater edge-cloud collaborative networks.

[0009] The specific technical solutions are as follows:

[0010] A resource joint allocation method for an underwater edge-cloud collaborative network includes the following steps:

[0011] Step 1: Divide the water area into several rectangular grids of equal size based on geographic location. Each rectangular grid contains the same number of underwater sensors, and each rectangular grid has an underwater mobile submersible independently responsible for data collection.

[0012] Step 2: Use the APPROX-TSP-TOUR algorithm to solve the Hamiltonian circuit formed by the shore-based server and the underwater sensors in any rectangular grid, that is, the movement route of a single underwater mobile submersible;

[0013] Step 3: Calculate the system delay and energy loss; the system delay includes: service transmission delay, service calculation delay and service movement delay; the service transmission delay is the sum of the transmission delay generated by the underwater sensor and the underwater mobile submersible performing underwater acoustic communication and the transmission delay generated by the underwater mobile submersible performing wireless communication with the shore-based server; the service calculation delay is the calculation delay of the data unloaded from the underwater mobile submersible to the shore-based server on the shore-based server; the service movement delay is the time it takes for the underwater mobile submersible to traverse the Hamiltonian circuit; the energy loss includes: underwater forward energy loss, calculation loss, and communication transmission loss of the underwater mobile submersible;

[0014] Step 4: Based on the system delay and energy loss, a resource allocation model that takes both system delay and energy loss into consideration is constructed, and the resource allocation model that takes both system delay and energy loss into consideration is solved using linear programming to obtain an optimal resource allocation strategy.

[0015] Furthermore, in step 3, the expression of service transmission delay is as follows:

[0016] Where D tot is the total amount of data generated by the sensors in the grid, C acou is the underwater acoustic channel capacity, W acou is the underwater acoustic bandwidth, is the underwater acoustic signal-to-noise ratio; D edge is the amount of data processed by the underwater mobile submersible, C wire is the wireless channel capacity, W wire is the wireless bandwidth, is the wireless signal-to-noise ratio;

[0017] The expression for calculating the service delay is:

[0018] Where, The CPU cycles required for the shore-based server to process 1 bit of data;

[0019] The expression of the service mobility delay is:

[0020] Where L is the path length of the Hamiltonian circuit, and V is the moving speed of the underwater mobile vehicle.

[0021] Furthermore, in step 3, the underwater forward energy loss expression of the underwater mobile submersible is:

[0022] Where, The energy loss of the underwater mobile vehicle for every 1m it moves;

[0023] The calculation loss expression of underwater mobile submersible is:

[0024] Where, The energy loss per bit of data processed;

[0025] The communication transmission loss of the underwater mobile submersible includes the receiving energy loss of the underwater acoustic communication between the sensor and the underwater mobile submersible Transmission energy loss when communicating wirelessly with an underwater mobile vehicle and a shore-based server Its expression is as follows:

[0026] Where, is the energy loss per bit of data received, is the energy loss per bit of data sent.

[0027] Furthermore, in step 4, the resource allocation model that takes into account both system delay and energy loss is expressed as follows: 0≤D edge ≤D tot ; λ≥0;

[0028] Where, E tot It is the total energy possessed by an underwater mobile vehicle.

[0029] Furthermore, in step 2, the specific solution process of the APPROX-TSP-TOUR algorithm is as follows:

[0030] Step 2.1: The sensors and shore-based servers are used as nodes, and all nodes are connected to each other to form a completely undirected graph;

[0031] Step 2.2: Use Euclidean distance as the cost function between two nodes;

[0032] Step 2.3: Use the MST-PRIM algorithm to calculate the minimum spanning tree T;

[0033] Step 2.4: Perform a pre-order traversal of the generated minimum spanning tree T, and only record the order of the nodes visited for the first time;

[0034] Step 2.5: According to the node sequence obtained in step 2.4, the sensor and shore-based server nodes are connected in sequence to obtain a Hamiltonian circuit.

[0035] The beneficial effects of the present invention are:

[0036] (1) Based on the divide-and-conquer concept, the present invention determines a regional collection strategy for underwater sensor data to avoid uneven resource distribution.

[0037] (2) The present invention plans the movement path of the underwater mobile submersible and solves the Hamiltonian circuit, thereby improving efficiency and saving energy.

[0038] (3) The present invention constructs a resource allocation model that takes into account both system delay and energy loss, thereby reducing energy loss while ensuring lower delay.

[0039] Figures in the specification

[0040] FIG1 is a flow chart of the method of the present invention.

[0041] FIG2 is a flow chart of the APPROX-TSP-TOUR algorithm. DETAILED DESCRIPTION

[0042] The present invention will be described in detail below based on the accompanying drawings and preferred embodiments. The purpose and effects of the present invention will become more apparent. The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only for explaining the present invention and are not intended to limit the present invention.

[0043] As shown in Figure 1, the resource joint allocation method of the underwater edge-cloud collaborative network includes the following steps:

[0044] Step 1: Plan the underwater sensor network, underwater mobile submersible fleet, and shore-based server as the end-edge cloud in the edge computing model. Based on the geographical location, divide the water area into several rectangular grids of equal size. Each rectangular grid has the same number of underwater sensors, and each rectangular grid has an underwater mobile submersible independently responsible for data collection.

[0045] Step 2: Use the APPROX-TSP-TOUR algorithm to solve the Hamiltonian circuit formed by the shore-based server and the underwater sensors in any rectangular grid, that is, the movement route of a single underwater mobile submersible.

[0046] As shown in Figure 2, the specific solution process of the APPROX-TSP-TOUR algorithm is as follows:

[0047] Step 2.1: Take the sensors and shore-based servers as nodes and connect all nodes to form a completely undirected graph.

[0048] Step 2.2: Use Euclidean distance as the cost function between two nodes.

[0049] Step 2.3: Use the MST-PRIM algorithm to calculate the minimum spanning tree T.

[0050] Step 2.4: Perform a pre-order traversal on the generated minimum spanning tree T, and only record the order of the nodes visited for the first time.

[0051] Step 2.5: According to the node sequence obtained in step 2.4, the loop formed by connecting the sensor and shore-based server nodes in sequence is the Hamiltonian loop.

[0052] Step 3: Calculate system delay and energy loss.

[0053] The transmission delay caused by underwater acoustic communication between underwater sensors and underwater mobile submersibles Transmission delay caused by wireless communication between underwater mobile submersible and shore-based server Add them together to get the service transmission delay, which is expressed as follows:

[0054] Where D tot is the total amount of data generated by the sensors in the grid, C acou is the underwater acoustic channel capacity, W acou is the underwater acoustic bandwidth, is the underwater acoustic signal-to-noise ratio; D edge is the amount of data processed by the underwater mobile submersible, C wire is the wireless channel capacity, W wire is the wireless bandwidth, is the wireless signal-to-noise ratio.

[0055] The service calculation delay is obtained based on the calculation delay of the data unloaded from the underwater mobile submersible to the shore-based server on the shore-based server. Its expression is as follows:

[0056] Where, It is the CPU cycle required for the shore-based server to process 1 bit of data.

[0057] According to the time it takes for the underwater mobile vehicle to traverse the Hamiltonian circuit, the service movement delay T is obtained. move , which is expressed as follows:

[0058] Where L is the path length of the Hamiltonian circuit, and V is the moving speed of the underwater mobile vehicle.

[0059] The system latency is calculated by adding the service transmission latency, service computation latency, and service mobility latency. It should be noted that the transmission latency at the sender and the processing latency at the receiver are not considered during acoustic communication between the sensor and the underwater mobile vehicle, and wireless communication between the underwater mobile vehicle and the shore-based server.

[0060] At the same time, the underwater forward energy loss, computing loss, and communication transmission loss of the underwater mobile submersible are added together to obtain the system energy loss. It should be noted that only the energy loss generated by the underwater mobile submersible operating within the system is considered, and the energy loss of the shore-based server and underwater sensors is not considered.

[0061] Among them, the underwater forward energy loss of the underwater mobile submersible is the forward energy loss E generated by a single underwater mobile submersible traversing the Hamiltonian circuit within its jurisdiction. move , whose expression is:

[0062] Where, It is the energy loss of the underwater mobile vehicle for every 1m it moves.

[0063] The computational loss of the underwater mobile submersible is the energy loss of the underwater mobile submersible in processing data. Its expression is:

[0064] Where, is the energy loss per bit of data processed.

[0065] The communication transmission loss of the underwater mobile submersible includes the receiving energy loss of the underwater acoustic communication between the sensor and the underwater mobile submersible Transmission energy loss when communicating wirelessly with an underwater mobile vehicle and a shore-based server Its expression is as follows:

[0066] Where, is the energy loss per bit of data received, is the energy loss per bit of data sent.

[0067] Step 4: Based on system delay and system energy loss, combined with the weight parameter λ, a resource allocation model that takes both system delay and energy loss into account is constructed. Linear programming is used to solve the resource allocation model that takes both system delay and energy loss into account to obtain the optimal resource allocation strategy. The expression of the resource allocation model that takes both system delay and energy loss into account is as follows: 0≤D edge ≤D tot .λ≥0.

[0068] Where, E tot It is the total energy possessed by an underwater mobile vehicle.

[0069] In the resource allocation model that takes into account system delay and energy loss, any submarine in the underwater mobile submarine formation can confirm its own D according to the distribution of sensors and shore-based servers in its jurisdiction. edge , and must traverse all sensors within its jurisdiction.

[0070] Linear programming is used to solve the resource allocation model that takes into account both system delay and energy loss. Substituting the expressions of energy and delay into the resource allocation model expression that takes into account both system delay and energy loss, we can get: 0≤D edge ≤D tot . 0≤λ.

[0071] Obtain:

[0072] Calculate E move , and The optimal resource allocation strategy is obtained.

[0073] Those skilled in the art will understand that the foregoing descriptions are merely preferred embodiments of the invention and are not intended to limit the invention. Although the invention has been described in detail with reference to the foregoing examples, those skilled in the art will still be able to modify the technical solutions described in the foregoing examples or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, etc. made within the spirit and principles of the invention shall be included within the scope of protection of the invention.

Claims

1. A resource joint allocation method for an underwater edge-cloud collaborative network, characterized in that: The following steps are involved: Step 1: Divide the water area into several rectangular grids of equal size according to the geographical location. Each rectangular grid has the same number of underwater sensors, and each rectangular grid has an underwater mobile submersible that is independently responsible for data collection. Step 2: Solve the Hamiltonian circuit formed by the shore-based server and the underwater sensors in any rectangular grid according to the APPROX-TSP-TOUR algorithm, that is, the movement route of a single underwater mobile submersible; Step 3: Calculate system delay and energy loss; the system delay includes: service transmission delay, service calculation delay, and service movement delay; the service transmission delay is the sum of the transmission delay generated by the underwater sensor and the underwater mobile submersible for hydroacoustic communication, and the transmission delay generated by the underwater mobile submersible and the shore-based server for wireless communication; the service calculation delay is the calculation delay of the data unloaded from the underwater mobile submersible to the shore-based server on the shore-based server; the service movement delay is the time it takes for the underwater mobile submersible to traverse the Hamiltonian circuit; the energy loss includes: underwater forward energy loss, calculation loss, and communication transmission loss of the underwater mobile submersible; Step 4: Based on the system delay and energy loss, a resource allocation model that takes both system delay and energy loss into consideration is constructed, and the resource allocation model that takes both system delay and energy loss into consideration is solved using linear programming to obtain an optimal resource allocation strategy.

2. The resource joint allocation method of the underwater edge cloud collaborative network according to claim 1 is characterized in that: In step 3, the expression of service transmission delay is as follows: Where D tot is the total amount of data generated by the sensors in the grid, C acou is the underwater acoustic channel capacity, W acou is the water sound frequency bandwidth, D is the underwater acoustic signal-to-noise ratio; edge is the amount of data processed by the underwater mobile submersible, C wire is the wireless channel capacity, W wire is the wireless bandwidth, is the wireless signal-to-noise ratio; The expression for the service calculation delay is: In the formula, The CPU cycle required for the shore-based server to process 1 bit of data; The expression of the service mobility delay is: Where L is the path length of the Hamiltonian circuit, and V is the moving speed of the underwater mobile vehicle.

3. The resource joint allocation method of the underwater edge cloud collaborative network according to claim 2 is characterized in that: In step 3, the underwater forward energy loss expression of the underwater mobile submersible is: In the formula, The energy loss of the underwater mobile submersible for every 1m it moves; The calculation loss expression of underwater mobile submersible is: In the formula, is the energy consumption per bit of data processed; The communication transmission loss of the underwater mobile submersible includes the receiving energy loss of the sensor in the underwater acoustic communication with the underwater mobile submersible. Transmission energy loss in wireless communication between underwater mobile submersible and shore-based server Its expression is as follows: In the formula, is the energy consumption per bit of data received, is the energy loss per bit of data sent.

4. The resource joint allocation method of the underwater edge cloud collaborative network according to claim 3 is characterized in that: In step 4, the expression of the resource allocation model that takes into account both system delay and energy loss is as follows: 0≤D edge ≤D tot ; λ≥0; In the formula, E tot It is the total energy possessed by an underwater mobile submersible.

5. The resource joint allocation method of the underwater edge cloud collaborative network according to claim 1 is characterized in that: In step 2, the specific solution process of the APPROX-TSP-TOUR algorithm is as follows: Step 2.1: The sensors and shore-based servers are taken as nodes, and all nodes are connected to each other to form a completely undirected graph; Step 2.2: Use Euclidean distance as the cost function between two nodes; Step 2.3: Use the MST-PRIM algorithm to calculate the minimum spanning tree T; Step 2.4: Perform a pre-order traversal of the generated minimum spanning tree T, and only record the order of the nodes visited for the first time; Step 2.5: According to the node sequence obtained in step 2.4, the sensor and shore-based server nodes are connected in sequence to obtain a Hamiltonian circuit.

Citation Information

Patent Citations

  • Underwater acoustic communication edge computing time delay and energy consumption optimization method for ocean internet of things

    CN112787920A

  • Underwater wireless sensor network trust model based on transfer learning

    CN113891275A

  • Resource joint allocation method for underwater side cloud collaborative network

    CN116234045A

  • Border-gateway-based method and system for migrating task of underwater ad hoc network

    WO2021217942A1