Wireless ad hoc network topology simulation system and method

Abstract

The invention discloses a wireless ad hoc network topology simulation system and method, and relates to the field of network simulation, in the system, a topology adjustment algorithm simulation unit performs simulation of a topology adjustment algorithm based on event driving; and the distributed topology construction algorithm simulation unit realizes distributed calculation of a topology construction algorithm through a distributed task system. According to the method, simulation of the wireless ad hoc network topology control algorithm can be efficiently completed in a fidelity mode, good expandability is achieved, and the use requirement of a large-scale scene is met.

Description

Technical Field

[0001] The present application relates to the field of network simulation, and in particular to a wireless ad hoc network topology simulation system and method. Background Art

[0002] In computer network research, network simulation is a technique that uses software programs to replicate the behavior of real networks by computing the interactions between various network entities (such as routers, switches, nodes, access points, and links). Experimenting in real networks typically requires a large amount of hardware, including routers, switches, and servers. The purchase, maintenance, and upgrade costs of this equipment are high, and deploying and maintaining real networks requires significant human resources. Network simulation can reduce the cost of conducting experiments in network environments and improve the efficiency of network configuration. Therefore, developing network simulation tools is a significant research issue.

[0003] Network topology management is an integral part of network simulation platforms. In mobile ad hoc networks, the network topology constantly changes due to node mobility, impacting the overall network characteristics. Therefore, researchers need to implement topology control. Topology control refers to a node management approach that dynamically changes the transmission range of nodes to maintain certain characteristics of the communication graph (e.g., connectivity) while simultaneously reducing the energy consumed by node transceivers (which is strictly related to transmission range).

[0004] In recent years, wireless networks, such as wireless sensor / mobile ad hoc networks and delay- and interference-tolerant networks, have become increasingly widespread. Topology control is a major research issue in wireless networks. Topology control not only extends the network lifecycle but also reduces signal interference. Topology control issues include discovering neighbors, identifying locations, determining transmission radius, establishing links to neighbors, scheduling node sleep and active cycles, clustering, constructing a dominating set (each node belongs to a dominating set or has neighbors in the dominating set), and maintaining the selected structure.

[0005] Topology control in wireless ad hoc networks is an iterative process, with the first step being topology construction and the second step being topology adjustment. Conventional topology construction algorithms generate the wireless ad hoc network topology from scratch, making simulation time-consuming and computationally complex. After the topology is constructed, computationally inexpensive topology adjustment algorithms are run. This allows for rapid, real-time topology adjustments to maintain optimal connectivity based on environmental changes. While computationally inexpensive, topology adjustment algorithms increase simulation time in large-scale scenarios as the number of nodes increases.

[0006] Several existing simulation technologies are currently available. The first type is based on discrete event simulators, such as NS-3 and OMNET++. Any discrete event simulation, namely the simulation framework and specific simulation model, has three core data structures: i) the simulation model's state variables, ii) a list of timestamped events, and iii) a global clock. During simulation, the scheduler continuously removes events with the smallest timestamps. As a result, the simulation process executes sequentially, lacking parallelism and resulting in excessively long simulation runs. These parallel simulation frameworks only support fixed networks and are not suitable for mobile scenarios like wireless ad hoc networks. Furthermore, they require users to manually assign nodes to different machines for simulation, making them less user-friendly. The second type of simulation tool is based on virtualization technology, such as Mininet and CORE. Mininet's centralized implementation is limited by the resources of a single PC. Its distributed implementations, Distrinet and Maxinet, do not support wireless ad hoc network simulation and lack a node mobility model. CORE lacks research on scalability in a distributed model, requiring manual assignment of different nodes to different machines for simulation, making it less user-friendly.

[0007] Although existing simulation tools can meet the needs of topology control algorithm simulation to a certain extent, there are still some obvious shortcomings:

[0008] 1. Poor scalability: Existing simulation tools have insufficient scalability. In large-scale scenarios, the simulation time of topology control algorithms is long, which is difficult to meet simulation needs.

[0009] 2. Lack of versatility: Due to the mobility of nodes, the parallel and distributed simulation frameworks of existing simulation tools do not support wireless ad hoc network scenarios.

[0010] 3. Poor usability: When users perform simulations on existing simulation platforms, they need to modify the topology control algorithm before running on the platform. Many simulation tools have high learning costs and are difficult to use for users without relevant backgrounds.

[0011] Therefore, based on the above problems, there is an urgent need to provide a topology simulation system for large-scale wireless ad hoc networks to optimize the simulation performance of the topology control algorithm and have better scalability in large-scale scenarios. Summary of the Invention

[0012] The purpose of this application is to provide a wireless ad hoc network topology simulation system and method, which can efficiently and faithfully complete the simulation of the wireless ad hoc network topology control algorithm, has good scalability, and meets the usage requirements of large-scale scenarios.

[0013] To achieve the above objectives, this application provides the following solutions:

[0014] In a first aspect, the present application provides a wireless ad hoc network topology simulation system, the wireless ad hoc network topology simulation system comprising: a distributed topology construction algorithm simulation unit and a topology adjustment algorithm simulation unit;

[0015] The distributed topology construction algorithm simulation unit includes: a working node, a controller node and a channel model;

[0016] The topology adjustment algorithm simulation unit simulates the topology adjustment algorithm based on event-driven; the topology adjustment algorithm simulation unit includes: a central controller, a pod node implemented based on the Kubernetes platform, and a monitoring module;

[0017] The distributed topology construction algorithm simulation unit is used to use the controller node to send the initial position information of all working nodes to each working node using the Asynq distributed task queue after the user submits the topology construction algorithm; after receiving the initial position information, the working node calculates the corresponding initial topology information according to the topology construction algorithm and sends it to the controller node, and at the same time sends a RESTful request to the channel model; the channel model calculates the link characteristics of each link according to the RESTful request and sends the link characteristics to the controller node; the controller node integrates the topology information and link characteristics to obtain the initial topology of all working nodes, and sends it to the central controller of the topology adjustment algorithm simulation unit;

[0018] The central controller in the topology adjustment algorithm simulation unit starts the corresponding pod node and configures the link according to the initial topology and link characteristics; runs the topology adjustment algorithm in the started pod node and starts the monitoring module; the monitoring module is used to capture the network packets of each link in real time and obtain the corresponding network packet payload; the central controller performs topology adjustment according to the network packet payload.

[0019] Optionally, the controller node specifically includes: a control module and a data module;

[0020] The control module is used to distribute the computing tasks containing global node information in the Asynq distributed task queue to multiple working nodes for computing after the user submits the initial location information of the working node;

[0021] The data module is used to integrate the initial topology information obtained by each working node according to the topology construction algorithm, and obtain the link characteristics of each link.

[0022] Optionally, the working node includes: a topology calculation module and a channel calculation module;

[0023] The topology calculation module is used to obtain global node information from the Asynq distributed task queue and calculate the corresponding initial topology information according to the topology construction algorithm provided by the user;

[0024] The channel calculation module is used to send a RESTful request to the channel model.

[0025] Optionally, the channel model is used to obtain the location information of the initial working node, the configured channel model, and the configuration parameters for the channel model calculation from the RESTful request sent by the channel calculation module of each working node; then the path loss is calculated according to the large-scale path loss model and the signal fading is calculated according to the small-scale fading model, thereby obtaining the received power; the signal-to-noise ratio is determined according to the received power, bandwidth, environmental noise, and thermal noise; the bit error rate is determined according to the signal-to-noise ratio, bandwidth, and modulation mode; the link characteristics are determined according to the bit error rate; the configuration parameters include: communication frequency, bandwidth, modulation mode, transmission rate, transmission power, and environmental noise parameters.

[0026] Optionally, the pod node runs a user-submitted topology adjustment algorithm and runs the monitoring module in sidecar mode.

[0027] Optionally, the monitoring module uses the gopacket library to monitor and capture network packets of each virtual network card of the pod node; and uses the decoder in the gopacket library to parse the network packet, decode the network packet into a gopacket.Packet object, and then obtain the payload of the network packet according to the Payload property of the gopacket.Packet object.

[0028] In a second aspect, the present application provides a wireless ad hoc network topology simulation method for implementing the wireless ad hoc network topology simulation system. The wireless ad hoc network topology simulation method includes:

[0029] Obtain topology construction algorithms and topology adjustment algorithms submitted by users;

[0030] The controller node is used to send the initial location information of all working nodes to each working node using the Asynq distributed task queue;

[0031] After receiving the initial location information, the working node calculates the corresponding initial topology information according to the topology construction algorithm and sends it to the controller node; at the same time, it sends a RESTful request to the channel model;

[0032] The channel model calculates the link characteristics of each link based on the RESTful request and sends the link characteristics to the controller node;

[0033] The controller node integrates the topology information and link characteristics to obtain the initial topology of all working nodes and sends it to the central controller of the topology adjustment algorithm simulation unit;

[0034] The central controller starts the corresponding pod nodes and configures the links based on the initial topology and link characteristics;

[0035] Run the topology adjustment algorithm in the started pod node and start the monitoring module;

[0036] The monitoring module is used to capture the network packets of each link in real time and obtain the corresponding network packet payload;

[0037] The central controller adjusts the topology according to the load of the network packets.

[0038] Optionally, the central controller performs topology adjustment according to the load of the network packet, specifically including:

[0039] If the payload of the network packet contains location information, the location information is forwarded to the central controller for location update;

[0040] If the payload of the network packet contains link change information, the link change information is forwarded to the central controller for link processing; the link processing includes: deleting a link, adding a link, and modifying a link.

[0041] Optionally, the central controller performs topology adjustment according to the load of the network packet, and then further includes:

[0042] The central controller notifies the daemon to configure the link characteristics.

[0043] Optionally, the wireless ad hoc network topology simulation method further includes:

[0044] During the simulation, each pod node executes the topology adjustment algorithm after receiving the network packet sent by the neighbor. Based on the location information, motion status or link operation contained in the network packet sent by the neighbor, it calculates the next motion state or performs the corresponding link operation and sends the calculation results to each neighbor.

[0045] According to the specific embodiments provided in this application, this application has the following technical effects:

[0046] The present application provides a wireless self-organizing network topology simulation system and method. The wireless self-organizing network topology simulation system includes: a distributed topology construction algorithm simulation unit and a topology adjustment algorithm simulation unit; the distributed topology construction algorithm simulation unit realizes distributed computing of the topology construction algorithm through a distributed task system, which can improve the simulation performance and scalability; the topology adjustment algorithm simulation unit is based on event-driven topology adjustment algorithm simulation, based on the Kubernetes platform, and runs the topology adjustment algorithm in the Pod node (physical node) to perform simulation, and performs link operations through the central controller to support scenarios with dynamic changes in the wireless self-organizing network topology, while having relatively high scalability; the network packets of each link are captured in real time by the monitoring module, which can easily capture the information of the simulation node, avoid users from introducing too much code in order to use this application, and improve the usability of this application. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0048] Figure 1 This is a schematic diagram of the structure of a wireless ad hoc network topology simulation system in one embodiment of the present application;

[0049] Figure 2 Schematic diagram of algorithm simulation unit structure for distributed topology construction;

[0050] Figure 3 This is a schematic diagram of the topology adjustment algorithm simulation unit structure;

[0051] Figure 4 This is a schematic diagram of the principle of a wireless ad hoc network topology simulation method in one embodiment of the present application. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0053] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0054] In an exemplary embodiment, Figure 1 As shown, a wireless ad hoc network topology simulation system is provided, which includes a distributed topology construction algorithm simulation unit and a topology adjustment algorithm simulation unit;

[0055] like Figure 2 As shown, the distributed topology construction algorithm simulation unit includes: a working node, a controller node and a channel model;

[0056] The topology adjustment algorithm simulation unit simulates the topology adjustment algorithm based on event driving; Figure 3 As shown, the topology adjustment algorithm simulation unit includes: a central controller, a pod node implemented based on the Kubernetes platform, and a monitoring module;

[0057] The distributed topology construction algorithm simulation unit is used to use the controller node to send the initial position information of all working nodes to each working node using the Asynq distributed task queue after the user submits the topology construction algorithm; after receiving the initial position information, the working node calculates the corresponding initial topology information according to the topology construction algorithm and sends it to the controller node, and at the same time sends a RESTful request to the channel model; the channel model calculates the link characteristics of each link according to the RESTful request and sends the link characteristics to the controller node; the controller node integrates the topology information and link characteristics to obtain the initial topology of all working nodes, and sends it to the central controller of the topology adjustment algorithm simulation unit;

[0058] The central controller in the topology adjustment algorithm simulation unit starts the corresponding pod node and configures the link according to the initial topology and link characteristics; runs the topology adjustment algorithm in the started pod node and starts the monitoring module; the monitoring module is used to capture the network packets of each link in real time and obtain the corresponding network packet payload; the central controller performs topology adjustment according to the network packet payload.

[0059] Asynq is a lightweight, high-performance asynchronous task processing library written in Go that implements distributed tasks. It's highly scalable and customizable. In this application, each worker node instance subscribes to a task queue. When the controller node adds global node information to the queue, all worker nodes receive a notification and then calculate the local topology for their respective nodes.

[0060] Channel models are used to calculate the signal power received by the receiver. These models follow a series of mathematical equations to calculate several aspects of the transmitted signal, including signal strength, signal-to-noise ratio, and bit error rate, and further convert these into equivalent network properties, such as expected packet loss.

[0061] In an exemplary embodiment, the controller node specifically includes: a control module and a data module;

[0062] The control module is used to distribute the computing tasks containing global node information in the Asynq distributed task queue to multiple working nodes for computing after the user submits the initial location information of the working node;

[0063] The data module is used to integrate the initial topology information obtained by each working node according to the topology construction algorithm and obtain the link characteristics of each link. Link characteristics include bit error rate, packet loss rate and bandwidth;

[0064] In an exemplary embodiment, the wireless ad hoc network topology simulation system provided by the present application can start multiple working nodes; the working nodes include: a topology calculation module and a channel calculation module;

[0065] The topology calculation module is used to obtain global node information from the Asynq distributed task queue and calculate the corresponding initial topology information according to the topology construction algorithm provided by the user;

[0066] The channel calculation module is used to send a RESTful request to the channel model.

[0067] The channel model is used to obtain the location information of the initial working node, the configured channel model, and the configuration parameters for the channel model calculation from the RESTful request sent by the channel calculation module of each working node; then the path loss is calculated according to the large-scale path loss model and the signal fading is calculated according to the small-scale fading model to obtain the received power; the signal-to-noise ratio is determined based on the received power, bandwidth, environmental noise, and thermal noise; the bit error rate is determined based on the signal-to-noise ratio, bandwidth, and modulation mode; and the link characteristics are determined based on the bit error rate. Configuration parameters include: communication frequency, bandwidth, modulation mode, transmission rate, transmit power, and environmental noise parameters.

[0068] In this application, users can freely configure and use large-scale path loss models such as the free space path loss model, logarithmic distance shadow loss model, Hata-Okumura model for urban environments, dual-ray ground model, and Nakagami-m small-scale fading model.

[0069] In an exemplary embodiment, a user-submitted topology adjustment algorithm is run in the pod node, and the monitoring module is run in sidecar mode.

[0070] Pod nodes are implemented based on the Kubernetes platform and use them to simulate the behavior of a wireless node. Pod nodes are connected using network plug-ins to simulate the wireless link between the two nodes.

[0071] The monitoring module uses the gopacket library to monitor and capture the network packets of each virtual network card of the pod node; and uses the decoder in the gopacket library to parse the network packets, decode the network packets into gopacket.Packet objects, and then obtain the payload of the network packets according to the Payload property of the gopacket.Packet object.

[0072] The central controller is responsible for collecting the latest locations of each node and performing link operations to update the topology of the entire network. It then notifies the daemon process to update the link characteristics of each link. The daemon process uses the Linux TrafficControl tool to configure the characteristics of each link.

[0073] Based on the same inventive concept, the embodiments of the present application also provide a wireless ad hoc network topology simulation method for implementing the wireless ad hoc network topology simulation system involved above. The implementation solution provided by this method is similar to the implementation solution described in the above method. Therefore, the specific limitations in one or more embodiments of the wireless ad hoc network topology simulation method provided below can be referred to the limitations of the wireless ad hoc network topology simulation system above, and will not be repeated here.

[0074] In an exemplary embodiment, Figure 4 As shown, a wireless ad hoc network topology simulation method is provided, including:

[0075] S1, obtain the topology construction algorithm and topology adjustment algorithm submitted by the user;

[0076] S2, uses the controller node to send the initial location information of all working nodes to each working node using the Asynq distributed task queue;

[0077] S3: After receiving the initial location information, the working node calculates the corresponding initial topology information according to the topology construction algorithm and sends it to the controller node; at the same time, it sends a RESTful request to the channel model;

[0078] S4, the channel model calculates the link characteristics of each link according to the RESTful request and sends the link characteristics to the controller node;

[0079] S5, the controller node integrates the topology information and link characteristics to obtain the initial topology of all working nodes and sends it to the central controller of the topology adjustment algorithm simulation unit;

[0080] S6: The central controller starts the corresponding pod nodes and configures the links based on the initial topology and link characteristics.

[0081] S7: Run the topology adjustment algorithm in the started pod node and start the monitoring module;

[0082] S8, the monitoring module is used to capture the network packets of each link in real time and obtain the corresponding network packet payload;

[0083] S9, the central controller adjusts the topology according to the load of the network packet.

[0084] S9 specifically includes:

[0085] If the payload of the network packet contains location information, the location information is forwarded to the central controller for location update;

[0086] If the payload of the network packet contains link change information, the link change information is forwarded to the central controller for link processing; the link processing includes: deleting a link, adding a link, and modifying a link.

[0087] S9 and later also include:

[0088] The central controller notifies the daemon to configure the link characteristics.

[0089] In an exemplary embodiment, the wireless ad hoc network topology simulation method further includes:

[0090] During the simulation, each pod node executes the topology adjustment algorithm after receiving the network packet sent by the neighbor. Based on the location information, motion status or link operation contained in the network packet sent by the neighbor, it calculates the next motion state or performs the corresponding link operation, sends the calculation result to each neighbor, and repeats the above steps.

[0091] In this application, all actions to obtain signals, information or data are carried out in compliance with the relevant data protection laws and policies of the country where they are located and with the authorization given by the owner of the corresponding device.

[0092] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0093] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A wireless ad hoc network topology simulation system, characterized in that: The wireless ad hoc network topology simulation system comprises: a distributed topology construction algorithm simulation unit and a topology adjustment algorithm simulation unit; The distributed topology construction algorithm simulation unit includes: a working node, a controller node and a channel model; The topology adjustment algorithm simulation unit simulates the topology adjustment algorithm based on event-driven; the topology adjustment algorithm simulation unit includes: a central controller, a pod node implemented based on the Kubernetes platform, and a monitoring module; The distributed topology construction algorithm simulation unit is used to use the controller node to send the initial position information of all working nodes to each working node using the Asynq distributed task queue after the user submits the topology construction algorithm; after receiving the initial position information, the working node calculates the corresponding initial topology information according to the topology construction algorithm, and sends it to the controller node, and sends a RESTful request to the channel model at the same time; the channel model calculates the link characteristics of each link according to the RESTful request, and sends the link characteristics to the controller node; the controller node integrates the topology information and link characteristics to obtain the initial topology of all working nodes, and sends it to the central controller of the topology adjustment algorithm simulation unit; The central controller in the topology adjustment algorithm simulation unit starts the corresponding pod node and configures the link according to the initial topology and link characteristics; runs the topology adjustment algorithm in the started pod node and starts the monitoring module; the monitoring module is used to capture the network packets of each link in real time and obtain the corresponding network packet load; the central controller performs topology adjustment according to the network packet load.

2. The wireless ad hoc network topology simulation system according to claim 1, characterized in that: The controller node specifically includes: a control module and a data module; The control module is used to distribute the computing tasks containing global node information in the Asynq distributed task queue to multiple working nodes for computing after the user submits the initial location information of the working node; The data module is used to integrate the initial topology information obtained by each working node according to the topology construction algorithm, and obtain the link characteristics of each link.

3. The wireless ad hoc network topology simulation system according to claim 1, characterized in that: The working node includes: a topology calculation module and a channel calculation module; The topology calculation module is used to obtain global node information from the Asynq distributed task queue and calculate the corresponding initial topology information according to the topology construction algorithm provided by the user; The channel calculation module is used to send a RESTful request to the channel model.

4. The wireless ad hoc network topology simulation system according to claim 3, characterized in that: The channel model is used to obtain the location information of the initial working node, the configured channel model, and the configuration parameters of the channel model calculation from the RESTful request sent by the channel calculation module of each working node; then the path loss is calculated according to the large-scale path loss model and the signal fading is calculated according to the small-scale fading model, and then the received power is obtained; the signal-to-noise ratio is determined according to the received power, bandwidth, environmental noise, and thermal noise; The bit error rate is determined according to the signal-to-noise ratio, bandwidth, and modulation mode; the link characteristics are determined according to the bit error rate; the configuration parameters include: communication frequency, bandwidth, modulation mode, transmission rate, transmission power, and environmental noise parameters.

5. The wireless ad hoc network topology simulation system according to claim 1, characterized in that: The topology adjustment algorithm submitted by the user runs in the pod node, and the monitoring module runs in Sidecar mode.

6. The wireless ad hoc network topology simulation system according to claim 1, characterized in that: The monitoring module uses the gopacket library to monitor and capture the network packets of each virtual network card of the pod node; and uses the decoder in the gopacket library to parse the network packets, decode the network packets into gopacket.Packet objects, and then obtain the payload of the network packets according to the Payload property of the gopacket.Packet object.

7. A wireless ad hoc network topology simulation method, used to implement the wireless ad hoc network topology simulation system according to any one of claims 1 to 6, characterized in that: The wireless ad hoc network topology simulation method comprises: Obtain the topology construction algorithm and topology adjustment algorithm submitted by the user; The controller node is used to send the initial location information of all working nodes to each working node using the Asynq distributed task queue; After receiving the initial location information, the working node calculates the corresponding initial topology information according to the topology construction algorithm and sends it to the controller node; at the same time, it sends a RESTful request to the channel model; The channel model calculates the link characteristics of each link according to the RESTful request and sends the link characteristics to the controller node; The controller node integrates the topology information and link characteristics to obtain the initial topology of all working nodes and sends it to the central controller of the topology adjustment algorithm simulation unit; The central controller starts the corresponding pod nodes and configures the links according to the initial topology and link characteristics; Run the topology adjustment algorithm in the started pod node and start the monitoring module; The monitoring module is used to capture the network packets of each link in real time and obtain the corresponding network packet payload; The central controller makes topology adjustments based on the load of network packets.

8. The wireless ad hoc network topology simulation method according to claim 7, characterized in that: The central controller performs topology adjustment according to the load of the network packet, specifically including: If the payload of the network packet contains location information, the location information is forwarded to the central controller for location update; If the payload of the network packet contains link change information, the link change information is forwarded to the central controller for link processing; the link processing includes: deleting a link, adding a link, and modifying a link.

9. The wireless ad hoc network topology simulation method according to claim 7, characterized in that: The central controller performs topology adjustment according to the load of the network packet, and then further includes: The central controller notifies the daemon to configure the link characteristics.

10. The wireless ad hoc network topology simulation method according to claim 7, characterized in that: The wireless ad hoc network topology simulation method further includes: During the simulation, after receiving the network packets sent by the neighbors, each pod node executes the topology adjustment algorithm, calculates the next movement state or performs the corresponding link operation according to the location information, movement state or link operation contained in the network packets sent by the neighbors, and sends the calculation results to each neighbor.

Images