AN ARTIFICIAL INTELLIGNCE (AI)-BASED SYSTEM AND A METHOD OF TOPOLOGY DESIGNING FOR IoT NETWORKS

Abstract

ABSTRACT AN ARTIFICIAL INTELLIGNCE (AI)-BASED SYSTEM AND A METHOD OF TOPOLOGY DESIGNING FOR IoT NETWORKS The present disclosure envisages an Artificial Intelligence (AI)-based system (100) for topology designing for distributed Internet of Things (IoT) networks. The system (100) comprises a plurality of IoT nodes (N), and a network configuration module (102). The plurality of IoT nodes (N) is configured to communicate in a network topology, where each node has an initial energy level and is configured to perform a distributed average consensus algorithm (ACA) to reach a consensus value. A control unit (114) of the network configuration module (102) is configured to perform the average consensus after forming fuzzy and small world topologies. This system (100) provides the AI-based optimal topological mechanism to balance the energy consumption and faster convergence time in distributed IoT networks.

Specification

Description:FIELD
The present disclosure generally relates to network technology. Particularly, the present disclosure relates to generating and designing a network topology.
BACKGROUND
The background information herein below relates to the present disclosure but is not necessarily prior art.
In distributed Internet of Things (IoT) consensus networks, designing communication topologies is very critical in such networks. Generally, the communication topology control system in the IoT consensus networks offers to design large-scale and energy-efficient IoT networks. The main aim of the topology control system is to design the topologies so as to balance the energy consumption and convergence time in the IoT consensus networks.
Further, it was observed that in the large-scale sparse IoT consensus networks, there are numerous IoT nodes. Basically, the IoT nodes are configured to connect a physical world in a closed environment with an open environment (Internet). Thus, these IoT nodes require more energy and take a longer time to converge to a global average.
However, the conventional topology control systems were not able to overcome the issue of less energy consumption and less convergence time. In detail, the conventional systems fail to achieve scalability and provide energy efficiency in the IoT networks. Furthermore, the conventional topology control systems are not suitable for delay tolerant IoT consensus networks.
There is, therefore, felt a need to develop an Artificial Intelligence (AI)-based system and a method of topology designing for IoT networks to ensure uniform energy consumption and faster convergence thereof, to alleviate the aforementioned disadvantages.
OBJECTS
Some of the objects of the present disclosure, which at least one embodiment herein satisfies, are as follows:
An object of the present disclosure is to provide an Artificial Intelligence (AI)-based system and a method for topology designing for IoT networks.
Another object of the present disclosure is to provide an AI-based system and a method for topology designing for IoT networks that achieve low convergence time and energy-efficient data gathering in IoT consensus networks.
Another object of the present disclosure is to provide an AI-based system and a method for topology designing for IoT networks that provides uniform energy consumption and faster convergence.
Yet another object of the present disclosure is to provide an AI-based system and a method for topology designing for IoT networks that provides the AI-based optimal topological mechanism to balance the energy consumption and convergence time in distributed IoT networks.
Still another object of the present disclosure is to provide an AI-based system and a method for topology designing for IoT networks that is suitable for delay tolerant IoT networks.
Yet another object of the present disclosure is to provide an AI-based system and a method for topology designing for IoT networks, that is simple, easy, reliable and fault tolerant.
Other objects and advantages of the present disclosure will be more apparent from the following description, which is not intended to limit the scope of the present disclosure.
SUMMARY
The present disclosure envisages an Artificial Intelligence (AI)-based system for topology designing for distributed Internet of Things (IoT) networks. The AI-based system comprises a plurality of IoT nodes, and a network configuration module. The plurality of IoT nodes (N) is configured to communicate in a network topology, each node having an initial energy level and configured to perform a distributed average consensus algorithm (ACA) to reach a consensus value. The network configuration module is embedded with an input unit, an assigning unit, a computing unit, a consensus network generation unit, a link adjustment unit, and a control unit. The input unit is configured to receive a plurality of network parameters associated with the network topology. The network parameters include a total number of IoT nodes (N), a number of randomly selected nodes (NRan), a short-range link (θ1), a long-range link (θ2), a consensus network threshold value (α), a small world consensus network threshold value (β), and a fuzzy-based small world consensus network threshold value (γ). The assigning unit is configured to assign random coordinates to each node (N) in a coordinate matrix within the network topology. The computing unit is configured to calculate Euclidean distance (Dij) between each pair of nodes based on the assigned random coordinates to the nodes. The consensus network generation unit is configured to establish short-range links (θ1) between the pair of nodes based on the threshold value (α) for the consensus network, forming an initial consensus IoT network. The link adjustment unit is configured to selectively integrate long-range links (θ2) into the initial consensus IoT network by, establishing the long-range links (θ2) based on small world links that connect randomly selected nodes (NRan) fuzzy logic criteria that consider network parameters including energy levels and Euclidean distances, and guiding the integration of the long-range links (θ2) based on the small world consensus network threshold value (β) and the fuzzy-based small world consensus network threshold value (γ), resulting in a modified consensus IoT network with lower convergence time and optimized energy consumption. The control unit is configured to iteratively adjust network topology until the IoT nodes (N) converge to an average consensus value.
In an embodiment, the consensus network generation unit is further configured to remove the short-range links (θ1) and add the long-range links (θ2) from the consensus IoT network after the initial network formation and updating the adjacency matrix to reflect the removal of these links.
In another embodiment, the adjacency matrix updates dynamically after each iterative step to reflect changes made by the addition or removal of short-range or long-range links.
In still another embodiment, the network configuration module further comprises an evaluation unit configured to calculate small world characteristics, including an Average Clustering Coefficient (ACC) and an Average Path Length (APL) of the consensus IoT network.
In yet another embodiment, the evaluation unit is further configured to calculate accuracy of the consensus algorithm using the given below expression:
δ=(∑_(i=0)^n▒A_V -Abs(i))/A_V
where AV denotes the average consensus value in the consensus IoT network, and Abs denotes an absolute consensus value, respectively.
In an embodiment, the calculation of the Average Clustering Coefficient (ACC) is performed by averaging the clustering coefficients of all nodes within the consensus IoT network to ensure high local connectivity among short-range nodes.
In another embodiment, the Average Path Length (APL) is calculated by determining the shortest path between each node pair and averaging these path lengths across the entire consensus IoT network to enhance global efficiency.
In still another embodiment, the control unit is configured to iteratively adjust the topology until target values for node/link density, convergence time, and energy efficiency are achieved.
In yet another embodiment, the consensus network threshold value (α), the small world consensus network threshold value (β), and the fuzzy-based small world consensus network threshold value (γ), are selected based on a predefined optimization criterion aimed at balancing network energy efficiency and path redundancy.
In an embodiment, the network configuration module includes a fuzzy logic unit configured to add the long-range links dynamically based on real-time network metrics, including residual energy levels and relative inter-node distances, to ensure uniform energy distribution across the consensus IoT network.
In another embodiment, the network configuration module includes a node density assessment unit configured to dynamically adjust long-range links connectivity using a fuzzy logic-based small-world model to accelerate convergence as the number of nodes increases, wherein the fuzzy logic-based small-world model enhances connectivity among sparsely located nodes in the consensus IoT network.
In an embodiment, the network configuration module includes a link density assessment unit configured to vary by increasing the number of short-range links (θ1) and keeping the long-range links (θ2) constant iteratively, wherein increased connectivity facilitates faster achievement of the consensus value by reducing the number of required iterations
The present disclosure, further envisages a method for topology designing for distributed IoT networks. The method comprises:
receiving, by an input unit within a network configuration module, a plurality of network parameters associated with the IoT networks, the network parameters including total number of IoT nodes (N), a number of randomly selected nodes (NRan), a short-range link (θ1), a long-range link (θ2), a consensus network threshold value (α), a small world consensus network threshold value (β), and a fuzzy-based small world consensus network threshold value (γ);
assigning, by an assigning unit within the network configuration module, random coordinates to each node (N) within a coordinate matrix in the network topology;
computing, by an computing unit within the network configuration module, an Euclidean distance between each pair of nodes based on their assigned coordinates;
establishing, by a consensus network generation unit within the network configuration module, short-range links (θ1) between pairs of nodes based on the consensus network threshold value (α), thereby forming an initial consensus IoT network;
selectively integrating, by an link adjustment unit within the network configuration module, the long-range links (θ2) into the initial consensus IoT network by:
establishing long-range links (θ2) between randomly selected nodes (NRan) for a small world consensus network,
establishing long-range links (θ2) for a fuzzy world consensus network based on a fuzzy logic criteria, which considers network parameters including energy levels and Euclidean distances between nodes, and
guiding the integration of the long-range links (θ2) using the small world consensus network threshold value (β) and the fuzzy-based small world consensus network threshold value (γ), creating a modified consensus IoT network with reduced convergence time and optimized energy usage; and
iteratively adjusting, by a control unit within the network configuration module, the network topology, through the control unit, until the IoT nodes (N) converge to an average consensus value.

BRIEF DESCRIPTION OF THE ACCOMPANYING DRAWING
An Artificial Intelligence (AI)-based system and a method for topology designing for IoT networks, of the present disclosure will now be described with the help of the accompanying drawing, in which:
Figure 1 illustrates an Artificial Intelligence (AI)-based system for topology designing for distributed IoT networks, in accordance with an embodiment of the present disclosure;
Figures 2a-2c illustrate a flow chart depicting steps performed for topology designing for distributed IoT networks of Figure 1, in accordance with an embodiment of the present disclosure; and
Figure 3 illustrates a graphical representation of node density, fuzzy logic-based small-world consensus networks when the number of nodes in the network is increased, in accordance with an embodiment of the present disclosure;
Figure 3 illustrates a graphical representation of node density when the number of nodes in the network is increased, in accordance with an embodiment of the present disclosure;
Figure 4 illustrates a graphical representation of long-range links added to the network for each iteration, in accordance with an embodiment of the present disclosure;
Figure 5 illustrates a graphical representation of the effect of node density on Total Relative Error, in accordance with an embodiment of the present disclosure; and
Figure 6 illustrates a graphical representation of the effect of link density on Total Relative Error, in accordance with an embodiment of the present disclosure.
LIST OF REFERENCE NUMERALS USED IN THE DESCRIPTION AND DRAWING:
100 System
102 Network Configuration Module
104 Input Unit
106 Assigning Unit
108 Computing Unit
110 Consensus Network Generation Unit
112 Link Adjustment Unit
114 Control Unit
116 Evaluation Unit
118 Node Density Assessment Unit
120 Link Density Assessment Unit
122 Fuzzy Logic Unit
DETAILED DESCRIPTION
Embodiments, of the present disclosure, will now be described with reference to the accompanying drawing.
Embodiments are provided so as to thoroughly and fully convey the scope of the present disclosure to the person skilled in the art. Numerous details are set forth, relating to specific components, and methods, to provide a complete understanding of embodiments of the present disclosure. It will be apparent to the person skilled in the art that the details provided in the embodiments should not be construed to limit the scope of the present disclosure. In some embodiments, well-known apparatus structures, and well-known techniques are not described in detail.
The terminology used, in the present disclosure, is only for the purpose of explaining a particular embodiment and such terminology shall not be considered to limit the scope of the present disclosure. As used in the present disclosure, the forms "a", "an" and "the" may be intended to include the plural forms as well, unless the context clearly suggests otherwise. The terms "comprises", "comprising", "including" and "having" are open-ended transitional phrases and therefore specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not forbid the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
When an element is referred to as being "mounted on", "engaged to", "connected to" or "coupled to" another element, it may be directly on, engaged, connected, or coupled to the other element. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed elements.
Generally, the main aim of the topology control system is to design the topologies so as to balance the energy consumption and convergence time in the Internet of Things (IoT) consensus networks. However, the conventional topology control systems were not able to overcome the issue of less energy consumption and less convergence time. In detail, the conventional systems fail to achieve scalability and provide energy efficiency in the IoT networks. Furthermore, the conventional topology control systems are not suitable for delay tolerant IoT consensus networks.
To overcome the aforementioned problems, the present disclosure envisages an Artificial Intelligence (AI)-based mechanism that leverages small-world network properties to achieve low convergence time and energy-efficient data gathering in IoT consensus networks. The present disclosure leverages a fuzzy logic technology to ensure uniform energy consumption and faster convergence.
With reference to Figure 1, the present disclosure envisages an artificial intelligence (AI)-based system (hereinafter referred to as system 100), for topology designing for distributed IoT networks. The system (100) comprises a plurality of IoT nodes (N), and a network configuration module (102). The plurality of IoT nodes (N) is configured to communicate in a network topology. Each node (N) has an initial energy level and is configured to perform a distributed average consensus algorithm (ACA) to reach a consensus value. The network configuration module (102) is embedded with an input unit (104), an assigning unit (106), a computing unit (108), a consensus network generation unit (110), a link adjustment unit (112), and a control unit (114). The input unit (104) is configured to receive a plurality of network parameters associated with the network topology. In an embodiment, the network parameters include a total number of IoT nodes (N), a number of randomly selected nodes (NRan), a short-range link (θ1), a long-range link (θ2), a consensus network threshold value (α), a small world consensus network threshold value (β), and a fuzzy-based small world consensus network threshold value (γ). The assigning unit (106) is configured to assign random coordinates to each node (N) in a coordinate matrix within the network topology. The computing unit (108) is configured to calculate Euclidean distance (Dij) between each pair of nodes based on the assigned random coordinates to the nodes. The consensus network generation unit (110) is configured to establish the short-range links (θ1) and between the pair of nodes based on the threshold value (α) for the consensus network, forming an initial consensus IoT network.
The link adjustment unit (112) is configured to selectively integrate long-range links (θ2) into the initial consensus IoT network. In detail, the link adjustment unit (112) cooperates with the input unit (104) to establish the long-range links (θ2) for a small world consensus network between randomly selected nodes (NRan). Further, in a fuzzy world consensus network, the link adjustment unit (112) establish the long-range links (θ2) based on a fuzzy logic criteria, which considers network parameters including energy levels and Euclidean distances (Dij) between nodes (N). The link adjustment unit (112) further guides the integration of the long-range links (θ2) based on the small world consensus network threshold value (β) and the fuzzy-based small world consensus network threshold value (γ), resulting in a modified consensus IoT network with lower convergence time and optimized energy consumption.
The control unit (114) is configured to perform the average consensus after forming fuzzy and small world topologies, where the IoT nodes (N) converge to an average consensus value. The control unit (114) is further configured to iteratively adjust the topology until target values for node/link density, convergence time, and to achieve the energy efficiency.
In an embodiment, an average consensus algorithm (ACA) is disclosed. Let Xk (0) denote the initial real scalar value associated with the node k at t=0, then the goal of the average consensus algorithm is to compute the average xavg: at every node through a distributed approach without any centralized node.
x_avg=(∑_(k=1)^n▒〖x_k (0) 〗)/n
This average consensus algorithm operates through a linear iterative process, wherein each node (N) communicates only with its direct neighbors nodes, updating its value by averaging the information received from them. The number of iterations or the amount of time required for all nodes to converge to the average value x_avg=(∑_(k=1)^n▒〖x_k (0) 〗)/n is referred to as the convergence time. Therefore, at time instant t+1, the real scalar value at node 'k' is expressed as
x_k (t+1)=x_k (t)+∑_(j∈N_k)▒(x_j (t)-x_k (t)) , k=1,…,n, … (1)
In an embodiment, the consensus network generation unit (110) is further configured to remove the short-range links (θ1) and add the long-range links (θ2) from the consensus IoT network after the initial network formation and updating adjacency matrix to reflect the removal of the short-range links and long-range links. Further, the adjacency matrix updates dynamically after each iterative step to reflect changes made by the addition or removal of short-range or long-range links (θ1 and θ2).
In an embodiment, the network configuration module (102) further comprises an evaluation unit (116). The evaluation unit (116) is further configured to calculate accuracy of the consensus algorithm using given below expression:
δ=(∑_(i=0)^n▒A_V -Abs(i))/A_V …. (2)
where, AV denotes the average consensus value in the consensus IoT network, and Abs denotes an absolute consensus value, respectively.
The evaluation unit (116) is configured to calculate small world characteristics, including an Average Clustering Coefficient (ACC) and an Average Path Length (APL) of the consensus IoT network.
In one embodiment, the calculation of the Average Clustering Coefficient (ACC) is performed by averaging the clustering coefficients of all nodes within the consensus IoT network to ensure high local connectivity among short-range nodes.
In another embodiment, the Average Path Length (APL) is calculated by determining the shortest path between each node pair and averaging these path lengths across the entire consensus IoT network, thereby enhancing a global efficiency.
In an embodiment, the network configuration module (102) includes a fuzzy logic unit (122). The fuzzy logic unit (122) is configured to add the long-range links (θ2) dynamically based on real-time network metrics, including residual energy levels and relative inter-node distances, to ensure uniform energy distribution across the consensus IoT network.
In another embodiment, the network configuration module (102) includes a node density assessment unit (118) configured to dynamically adjust long-range links (θ2) connectivity using a fuzzy logic-based small-world model to accelerate convergence as the number of nodes increases. The fuzzy logic-based small-world model enhances connectivity among sparsely located nodes in the consensus IoT network.
In detail, the fuzzy logic-based small-world model in the consensus IoT networks achieves the average consensus value faster than other networks when the number of nodes in the consensus IoT network is increased. The consensus IoT network efficiently selects long-range links (θ2) to connect distant nodes (N) for communication. This leads to achieving consensus at a faster rate (as shown in Figure 3). The fuzzy logic-based small-world consensus network provides an added advantage when it comes to completing the average consensus technology. As the number of nodes in the network increases, it becomes more difficult to achieve consensus with less connectivity in the network. Thus, the average consensus IoT value increases with the iteration in a node-density network.
In still another embodiment, the network configuration module (102) includes a link density assessment unit (120) configured to vary the short-range links (θ1) by increasing the number of short-range links (θ1) and keeping the long-range links (θ2) constant iteratively. This leads to increased connectivity that facilitates faster achievement of the consensus value by reducing the number of required iterations.
When the number of short-range links (θ1) added to the consensus IoT networks for each iteration increases, the connectivity of the consensus IoT networks becomes stronger, thereby making it easier to achieve the average consensus value. As a result, the fuzzy logic-based small-world consensus network achieves the average consensus value much faster than other conventional networks (as shown in Figure 4, where the average consensus value is achieved faster as the network links increase, depicting a downward trend).
The consensus network threshold value (α), the small world consensus network threshold value (β), and the fuzzy-based small world consensus network threshold value (γ), are selected based on a predefined optimization criterion aimed at balancing network energy efficiency and path redundancy.
Figures 2a-2c illustrates a flow chart depicting steps performed for topology designing for distributed IoT networks of Figure 1. The present AI-based system (100) is configured to perform a method 200 for topology designing for distributed IoT networks, the method 200 comprising:
At block 210: receiving a plurality of network parameters associated with the IoT networks by an input unit (104) within a network configuration module (102). The network parameters including total number of IoT nodes (N), a number of randomly selected nodes (NRan), a short-range link (θ1), a long-range link (θ2), a consensus network threshold value (α), a small world consensus network threshold value (β), and a fuzzy-based small world consensus network threshold value (γ);
At block 220: assigning random coordinates to each node (N) within a coordinate matrix in the network topology, by an assigning unit (106) within the network configuration module (102);
At block 230: computing, a Euclidean distance (Dij) between each pair of nodes based on their assigned coordinates, by a computing unit (108) within the network configuration module (102);
At block 240: establishing short-range links (θ1) between pairs of nodes based on the consensus network threshold value (α), thereby forming an initial consensus IoT network, by a consensus network generation unit (110) within the network configuration module (102);
At block 250: selectively integrating the long-range links (θ2) into the initial consensus IoT network, by link adjustment unit (112) within the network configuration module (102), by:
establishing long-range links (θ2) between randomly selected nodes (NRan) for a small world consensus network;
establishing long-range links (θ2) for a fuzzy world consensus network based on a fuzzy logic criteria, which considers network parameters including energy levels and Euclidean distances between nodes; and
guiding the integration of the long-range links (θ2) using the small world consensus network threshold value (β) and the fuzzy-based small world consensus network threshold value (γ), creating a modified consensus IoT network with reduced convergence time and optimized energy usage; and
At block 260: iteratively adjusting the network topology, through the link adjustment unit (112), until the IoT nodes (N) converge to an average consensus value, by a control unit (114) within the network configuration module (102).
In an embodiment, the present AI-based system (100) is simple, fault tolerant and a distributed mechanism. The present AI-based system (100) is suitable for low-power wireless networks such as WSN and IoT networks.
EXPERIMENTAL DATA AND TEST RESULTS
Node Density: The average consensus algorithm (ACA) has been run for simulations on a regular consensus, a small-world consensus, and a fuzzy-based small-world consensus networks. The relative errors for the networks were computed using (2). The simulation results are displayed in Figure 5. According to the results, the fuzzy logic-based small-world consensus network had better accuracy because it achieved the average consensus value more accurately compared to the other networks
Link Density: A trend similar to Figure 5 was observed when links were varied in Figure 6. The fuzzy logic-based small-world consensus network was found to have better accuracy when performing the ACA compared to the consensus and small-world consensus network.
Total Energy Consumption:
The total energy consumption of the regular consensus, small-world consensus, and fuzzy logic-based small world consensus networks were calculated using equations (3), (5), and (7) respectively.

E_CN=T⋅∑_(i=0)^n▒∑_(j=0)^n▒C(ij)(E_rx+E_tx+E_a ) +2βE_(fs∑_(i=0)^n▒∑_(j=0)^n▒〖d_sr (ij)^2 〗) (3)

E_(R_CN )=E_A-∑_(i=0)^n▒∑_(j=0)^n▒〖E_CN (ij) 〗 (4)

E_SW=T⋅∑_(i=0)^n▒∑_(j=0)^n▒〖C_sw (ij)(E_rx+E_tx+E_a ) 〗+βE_fs ∑_(i=0)^n▒∑_(j=0)^n▒〖d_sw (ij)^2 〗 + βE_mp ∑_(l=0)^m▒∑_(k=0)^m▒〖d(lk)_lr^4 〗 (5)

E_(R_SW )=E_A-∑_(i=0)^n▒∑_(j=0)^n▒〖E_SW (ij) 〗 (6)

E_fuzzy=T⋅∑_(i=0)^n▒∑_(j=0)^n▒〖C_fuzzy (ij)(E_rx+E_tx+E_a ) 〗+βE_fs ∑_(i=0)^n▒∑_(j=0)^n▒〖d_fuzzy (ij)^2 〗+βE_mp ∑_(l=0)^m▒∑_(k=0)^m▒〖d(lk)_(lr )^4 〗 (7)

E_(R_fuzzy )=E_A-∑_(i=0)^n▒∑_(j=0)^n▒〖E_fuzzy (ij) 〗 (8)

Table I discloses the evaluation of Energy Consumption Values for the present AI-based system (100) with respect to Nodes (N).

No. of Nodes Total Energy Consumption for CN Total Energy Consumption for SWCN Total Energy Consumption for FZ-SWCN Total Residual Energy Consumption for CN Total Residual Energy Consumption for SWCN Total Residual Energy Consumption for FZ-SWCN
100 4.794 * 104 J 2.1734 * 107J 2.4285 * 108J 1 * 1015J 1 * 1015J 9.99998 * 1014J
200 2.751 *105J 7.1721 * 108J 1.5492 * 1010J 1 * 1015J 9.99993 * 1014J 9.99845 * 1014J
300 1.647 * 106 J 2.1127 * 109J 5.4906 * 1010J 1 * 1015J 9.99979 * 1014J 9.99451 * 1014J
400 9.598 * 106J 3.2007 * 1010J 1.3606 * 1011J 1 * 1015J 9.9968 * 1014J 9.98639 * 1014J
500 3.191 * 107J 6.7089 * 1010J 2.0959 * 1011J 1 * 1015J 9.99329 * 1014J 9.97904 * 1014J

Table I
Node Density: When the number of nodes varied in the consensus network, the energy consumption was higher for the fuzzy logic-based small world consensus network compared to the other two networks, as shown in Table I. This is because the long-range links (θ2) in the fuzzy logic-based small-world consensus network could connect nodes located at a greater distance between clusters, unlike in a small-world consensus network. Since the distance between the nodes (N) is directly proportional to the energy consumed, as mentioned in equations (3), (5), and (7), the energy consumption was higher in the fuzzy-based small-world network.
Link Density: When the links varied in the consensus network network, the energy consumption decreased due to reduced ACA value. The fuzzy logic-based small-world consensus network consumes more energy than the other two networks because the distance connectivity of the long-range links (θ2) is higher in the fuzzy logic-based small-world network.
Total Residual Energy Consumption: The total residual energy is defined as the leftover energy after completing the communication process in the network.
Node Density: The total residual energy was computed for the consensus, small world, and small world by using equations (4), (6), and (8). According to Table II, the fuzzy logic-based small-world consensus network had less residual energy than other networks because it consumed more energy than the other networks.
Link Density: A reverse trend was observed when the number of links in the network was increased. Table II discloses the evaluation of Energy Consumption Values for The Proposed Mechanism with respect to Links. The comparison between the three networks is shown in Table II.
No. of Links Total Energy Consumption for CN Total Energy Consumption for SWCN Total Energy Consumption for FZ-SWCN Total Residual Energy Consumption for CN Total Residual Energy Consumption for SWCN Total Residual Energy Consumption for FZ-SWCN
4000 2.639 * 107J 1.5400 *1010J 4.5298 * 1010J 1 * 1015J 9.99985 * 1014J 9.99955 * 1014J
8000 1.147 * 107J 1.5053 *1010J 4.4821 * 1010J 1 * 1015J 9.99985 * 1014J 9.99956 * 1014J
12000 7.214 * 106 J 1.4771 *1010J 4.3935 * 1010J 1 * 1015J 9.99985 * 1014J 9.99957 * 1014J
16000 5.410 * 106 J 1.3412 *1010J 4.3172 * 1010J 1 * 1015J 9.99987 * 1014J 9.99958 * 1014J
20000 4.197 * 106 J 1.1102 *1010J 4.0548 * 1010J 1 * 1015J 9.99987 * 1014J 9.99959 * 1014J

Table II
The foregoing description of the embodiments has been provided for purposes of illustration and is not intended to limit the scope of the present disclosure. Individual components of a particular embodiment are generally not limited to that particular embodiment, but, are interchangeable. Such variations are not to be regarded as a departure from the present disclosure, and all such modifications are considered to be within the scope of the present disclosure.
TECHNICAL ADVANCEMENTS
The present disclosure described herein above has several technical advantages including, but not limited to, the realization of an artificial intelligence (AI)-based system and a method for topology designing for IoT networks, that:
achieve low convergence time and energy-efficient data gathering in IoT consensus networks;
provides uniform energy consumption and faster convergence;
provides an Artificial Intelligence (AI) based optimal topological mechanism to balance the energy consumption and faster convergence time in distributed IoT networks;
is suitable for delay tolerant IoT networks; and
is simple, easy, reliable, and fault tolerant.
The embodiments herein and the various features and advantageous details thereof are explained with reference to the non-limiting embodiments in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein may be practiced and to further enable those of skill in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.
The foregoing description of the specific embodiments so fully reveals the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the spirit and scope of the embodiments as described herein.
The use of the expression "at least" or "at least one" suggests the use of one or more elements or ingredients or quantities, as the use may be in the embodiment of the disclosure to achieve one or more of the desired objects or results.
Any discussion of documents, acts, materials, devices, articles, or the like that has been included in this specification is solely for the purpose of providing a context for the disclosure. It is not to be taken as an admission that any or all of these matters form a part of the prior art base or were common general knowledge in the field relevant to the disclosure as it existed anywhere before the priority date of this application.
The numerical values mentioned for the various physical parameters, dimensions, or quantities are only approximations and it is envisaged that the values higher/lower than the numerical values assigned to the parameters, dimensions or quantities fall within the scope of the disclosure, unless there is a statement in the specification specific to the contrary.
While considerable emphasis has been placed herein on the components and component parts of the preferred embodiments, it will be appreciated that many embodiments can be made and that many changes can be made in the preferred embodiments without departing from the principles of the disclosure. These and other changes in the preferred embodiment as well as other embodiments of the disclosure will be apparent to those skilled in the art from the disclosure herein, whereby it is to be distinctly understood that the foregoing descriptive matter is to be interpreted merely as illustrative of the disclosure and not as a limitation. , Claims:WE CLAIM:
An Artificial Intelligence (AI)-based system (100) for topology designing for distributed Internet of Things (IoT) networks, said system (100) comprising:
a plurality of IoT nodes (N) configured to communicate in a network topology, each node (N) having an initial energy level and configured to perform a distributed average consensus algorithm (ACA) to reach a consensus value; and
a network configuration module (102) embedded with:
an input unit (104) configured to receive a plurality of network parameters associated with the network topology, said network parameters including total number of IoT nodes (N), a number of randomly selected nodes (NRan), a short-range link (θ1), a long-range link (θ2), a consensus network threshold value (α), a small world consensus network threshold value (β), and a fuzzy-based small world consensus network threshold value (γ);
an assigning unit (106) configured to assign random coordinates to each node (N) in a coordinate matrix within the network topology;
an computing unit (108) configured to calculate Euclidean distance (Dij) between each pair of nodes based on the assigned random coordinates to the nodes;
a consensus network generation unit (110) configured to establish short-range links (θ1) between the pair of nodes based on the threshold value (α) for the consensus network, forming an initial consensus IoT network;
a link adjustment unit (112) configured to selectively integrate long-range links (θ2) into said initial consensus IoT network by:
establishing long-range links (θ2) between randomly selected nodes (NRan) for a small world consensus network;
establishing long-range links (θ2) for a fuzzy world consensus network based on a fuzzy logic criteria, which considers network parameters including energy levels and Euclidean distances between nodes; and
guiding the integration of the long-range links (θ2) based on the small world consensus network threshold value (β) and the fuzzy-based small world consensus network threshold value (γ), resulting in a modified consensus IoT network with lower convergence time and optimized energy consumption; and
a control unit (114) configured to iteratively adjust network topology until the IoT nodes (N) converge to an average consensus value.

The AI-based system (100) as claimed in claim 1, wherein said consensus network generation unit (110) is further configured to remove the short-range links (θ1) and add the long-range links (θ2) from the consensus IoT network after the initial network formation and updating adjacency matrix to reflect the removal of these links.
The AI-based system (100) as claimed in claim 2, wherein the adjacency matrix updates dynamically after each iterative step to reflect changes made by the addition or removal of short-range or long-range links.
The AI-based system (100) as claimed in claim 1, wherein said network configuration module (102) further comprises an evaluation unit (116) configured to calculate small world characteristics, including an Average Clustering Coefficient (ACC) and an Average Path Length (APL) of said consensus IoT network.
The AI-based system (100) as claimed in claim 4, wherein said evaluation unit (116) is further configured to calculate accuracy of the consensus algorithm using given below expression:
δ=(∑_(i=0)^n▒A_V -Abs(i))/A_V
where AV denotes the average consensus value in said consensus IoT network, and Abs denotes an absolute consensus value, respectively.
The AI-based system (100) as claimed in claim 4, wherein calculation of the Average Clustering Coefficient (ACC) is performed by averaging the clustering coefficients of all nodes within the consensus IoT network to ensure high local connectivity among short-range nodes.
The AI-based system (100) as claimed in claim 4, wherein the Average Path Length (APL) is calculated by determining the shortest path between each node pair and averaging these path lengths across the entire consensus IoT network to enhance global efficiency
The AI-based system (100) as claimed in claim 4, wherein said control unit (114) is configured to iteratively adjust the topology until target values for node/link density, convergence time, and energy efficiency are achieved.
The AI-based system (100) as claimed in claim 1, wherein the consensus network threshold value (α), the small world consensus network threshold value (β), and the fuzzy-based small world consensus network threshold value (γ), are selected based on a predefined optimization criterion aimed at balancing network energy efficiency and path redundancy.
The AI-based system (100) as claimed in claim 1, wherein said network configuration module (102) includes a fuzzy logic unit (122) configured to add the long-range links (θ2) dynamically based on real-time network metrics, including residual energy levels and relative inter-node distances, to ensure uniform energy distribution across the consensus IoT network.
The AI-based system (100) as claimed in claim 1, wherein said network configuration module (102) includes a node density assessment unit (118) configured to dynamically adjust long-range links connectivity using a fuzzy logic-based small-world model to accelerate convergence as the number of nodes increases, wherein the fuzzy logic-based small-world model enhances connectivity among sparsely located nodes in the consensus IoT network.
The AI-based system (100) as claimed in claim 1, wherein said network configuration module (102) includes a link density assessment unit (120) configured to vary by increasing the number of short-range links (θ1) and keeping the long-range links (θ2) constant iteratively, wherein increased connectivity facilitates faster achievement of the consensus value by reducing the number of required iterations
A method (200) for topology designing for distributed IoT networks, said method comprising:
receiving (210), by an input unit (104) within a network configuration module (102), a plurality of network parameters associated with the IoT networks, said network parameters including total number of IoT nodes (N), a number of randomly selected nodes (NRan), a short-range link (θ1), a long-range link (θ2), a consensus network threshold value (α), a small world consensus network threshold value (β), and a fuzzy-based small world consensus network threshold value (γ);
assigning (220), by an assigning unit (106) within the network configuration module (102), random coordinates to each node (N) within a coordinate matrix in the network topology;
computing (230), by an computing unit (108) within the network configuration module (102), an Euclidean distance between each pair of nodes based on their assigned coordinates;
establishing (240), by a consensus network generation unit (110) within the network configuration module (102), short-range links (θ1) between pairs of nodes based on the consensus network threshold value (α), thereby forming an initial consensus IoT network;
selectively integrating (250), by a link adjustment unit (112) within the network configuration module (102), the long-range links (θ2) into said initial consensus IoT network by:
establishing long-range links (θ2) between randomly selected nodes (NRan) for a small world consensus network;
establishing long-range links (θ2) for a fuzzy world consensus network based on a fuzzy logic criteria, which considers network parameters including energy levels and Euclidean distances between nodes;
guiding the integration of the long-range links (θ2) using the small world consensus network threshold value (β) and the fuzzy-based small world consensus network threshold value (γ), creating a modified consensus IoT network with reduced convergence time and optimized energy usage; and
iteratively adjusting (260), by a control unit (114) within the network configuration module (102), the network topology, through said link adjustment unit (112), until the IoT nodes (N) converge to an average consensus value.
Dated this 26th Day of October, 2024

_______________________________
MOHAN RAJKUMAR DEWAN, IN/PA - 25
OF R. K. DEWAN & CO.
AUTHORIZED AGENT OF APPLICANT

TO,
THE CONTROLLER OF PATENTS
THE PATENT OFFICE, AT CHENNAI

Documents