AU2021103738A4 - ARTIFICIAL INTELLIGENCE ENABLED DYNAMIC BANDWIDTH ALLOCATION OPTIMIZATION IN IoT FOR IMPROVED QoS - Google Patents
ARTIFICIAL INTELLIGENCE ENABLED DYNAMIC BANDWIDTH ALLOCATION OPTIMIZATION IN IoT FOR IMPROVED QoS Download PDFInfo
- Publication number
- AU2021103738A4 AU2021103738A4 AU2021103738A AU2021103738A AU2021103738A4 AU 2021103738 A4 AU2021103738 A4 AU 2021103738A4 AU 2021103738 A AU2021103738 A AU 2021103738A AU 2021103738 A AU2021103738 A AU 2021103738A AU 2021103738 A4 AU2021103738 A4 AU 2021103738A4
- Authority
- AU
- Australia
- Prior art keywords
- iot
- devices
- bandwidth
- artificial intelligence
- qos
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
- 238000005457 optimization Methods 0.000 title claims abstract description 36
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 25
- 238000013528 artificial neural network Methods 0.000 claims abstract description 15
- 239000000779 smoke Substances 0.000 claims abstract description 8
- 238000013459 approach Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 8
- 239000002245 particle Substances 0.000 abstract description 5
- 230000006855 networking Effects 0.000 abstract description 3
- 230000003203 everyday effect Effects 0.000 abstract description 2
- 238000000034 method Methods 0.000 description 15
- 238000012517 data analytics Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 230000008278 dynamic mechanism Effects 0.000 description 1
- 244000144992 flock Species 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0896—Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0896—Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities
- H04L41/0897—Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities by horizontal or vertical scaling of resources, or by migrating entities, e.g. virtual resources or entities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/70—Admission control; Resource allocation
- H04L47/82—Miscellaneous aspects
- H04L47/822—Collecting or measuring resource availability data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/02—Arrangements for optimising operational condition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/02—Traffic management, e.g. flow control or congestion control
- H04W28/08—Load balancing or load distribution
- H04W28/09—Management thereof
- H04W28/0958—Management thereof based on metrics or performance parameters
- H04W28/0967—Quality of Service [QoS] parameters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/16—Central resource management; Negotiation of resources or communication parameters, e.g. negotiating bandwidth or QoS [Quality of Service]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/70—Services for machine-to-machine communication [M2M] or machine type communication [MTC]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W72/00—Local resource management
- H04W72/04—Wireless resource allocation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W72/00—Local resource management
- H04W72/50—Allocation or scheduling criteria for wireless resources
- H04W72/54—Allocation or scheduling criteria for wireless resources based on quality criteria
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Environmental & Geological Engineering (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
ARTIFICIAL INTELLIGENCE ENABLED DYNAMIC BANDWIDTH
ALLOCATION OPTIMIZATION IN IoT FOR IMPROVED QoS
ABSTRACT
The Internet of Things (IoT) is a collection of intelligently connected devices that are
connect to the internet. Every day, as technology advances, an IoT device outnumbers
humans on the world. The Internet of Things (IoT) systems would connect not only
physical users and devices, but also virtual networks and devices that have already been
implemented in various scenarios using new networking, computing, and integrated
system technologies. With the rapid advancement of technology, the number of devices
involved grows rapidly. IoT systems have crucial issues in supplying sufficient
bandwidth to IoT Devices for Improving Quality in Services provided in the form of
QoS (Quality of Service) parameters, depending on the volume of devices and data. The
present invention disclosed herein is an Artificial Intelligence Enabled Dynamic
Bandwidth Allocation Optimization in IoT for Improved QoS comprising of IoT
Devices (101), Router (102), Bandwidth Data (103), KM-PSO Clustering (104), Deep
Alternative Neural Network (DANN) (105), Dynamic Bandwidth Allocation
Optimization (106), and QoS Estimation (107); provides a scalable solution for
allocating the bandwidth for the IoT enabled devices for improving QoS parameters.
The present invention uses K-Means-Particle Swarm Optimization (KM-PSO) for
generating the optimum number of clusters for improving the accuracy of the present
invention. Once the optimal number of clusters are generated, a Deep Alternative
Neural Network (DANN) used in the present invention detects the traffic from the IoT
devices, predicts the required bandwidth to be allocated. The Artificial Intelligence
enabled Dynamic Bandwidth Allocation Optimization (AIEDBAO) uses Fuzzy Logic
Controller (FLC) for allocating Bandwidth based on the traffic rules generated. The
improved QoS parameters achieved with the present invention are Bandwidth
Consumption of 34.5Mbps, Packet Delivery Delay (PDD) of 32ms, Packet Loss of 4%
and Throughput of 99% at supply of 50Mbps.
1/2
ARTIFICIAL INTELLIGENCE ENABLED DYNAMIC BANDWIDTH
ALLOCATION OPTIMIZATION IN IoT FOR IMPROVED QoS
DRAWINGS
IoT DEVICES
101
S'.-TV Thermogat Smoke
102 ROUTER BANDWIDTH
DATA
KM-PSO CLUSTERING
107 106 105
DYNAMIC BANDWIDTH LLAJ DEEP ALTERNATIVE
QoS ESTIMATION ALLOCATION
J OPTIMIZATION NEURAL NETWORK
Figure 1: Artificial Intelligence Enabled Dynamic Bandwidth Allocation Optimization
in IoT for Improved QoS.
201
IoT DEVICES
DATA USAGEPATTERN 202
KM-PSO CLUSTERING 203
CLASSIFICATION 204
Figure 2: Framework of KM-PSO Clustering.
Description
1/2
ARTIFICIAL INTELLIGENCE ENABLED DYNAMIC BANDWIDTH ALLOCATION OPTIMIZATION IN IoT FOR IMPROVED QoS
IoT DEVICES
101 S'.-TV Thermogat Smoke
ROUTER BANDWIDTH DATA 102 KM-PSO CLUSTERING
107 106 105
QoS ESTIMATION DYNAMIC BANDWIDTH ALLOCATION LLAJ DEEP ALTERNATIVE J OPTIMIZATION NEURAL NETWORK
Figure 1: Artificial Intelligence Enabled Dynamic Bandwidth Allocation Optimization
in IoT for Improved QoS.
201 IoT DEVICES
DATA USAGEPATTERN 202
KM-PSO CLUSTERING 203
CLASSIFICATION 204
Figure 2: Framework of KM-PSO Clustering.
ARTIFICIAL INTELLIGENCE ENABLED DYNAMIC BANDWIDTH ALLOCATION OPTIMIZATION IN IoT FOR IMPROVED QoS
[0001] The present invention relates to the technical field of Computer Science Engineering.
[0002] Particularly, the present invention is related to Artificial Intelligence Enabled Dynamic Bandwidth Allocation Optimization in IoT for Improved QoS of the broader Internet of Things in Computer Science Engineering.
[0003] More particularly, the present invention is relates to Artificial Intelligence Enabled Dynamic Bandwidth Allocation Optimization in IoT for Improved QoS, in particularly in IoT Systems. This invention provides a scalable solution for allocating the bandwidth for the IoT enabled devices for improving QoS parameters based on the Artificial Intelligence (AI).
[0004] The Internet of Things (IoT) refers to networks of linked devices that are equipped with sensors and actuators that can transmit and receive data via the internet. It includes gadgets such as smart household appliances, health-care devices, agricultural equipment, and industrial automation. The Internet of Things (IoT) has become a buzzword in the industry. IoT systems, on the other hand, do more than just control devices over the internet; they also collect data from devices and store it in the cloud for data analytics. It allows the system to work without human intervention based on data analytics.
[0005] Dynamic bandwidth allocation to IoT devices includes a series of steps, such as bandwidth-based clustering devices, on-demand measurement of cluster prediction, dynamic bandwidth allocation and improved service quality. Cluster IoT devices are used to classify devices into clusters based on the use of bandwidth attributes, like low, medium and high. Clustering is an essential phase for the classification of devices which helps assign the bandwidth between the threshold and the highest levels. In IoT clusters, different factors such as energy usage, data transmission and bandwidth use must be observed. An IoT device often produces mass volume data and uploads for data analytics to the clouds. On demand bandwidth and QoS are only handled by adding an additional bandwidth not bandwidth management by dynamic bandwidth allocation methods. Most Dynamic bandwidth algorithms don't match IoT devices Wireless and wireless device support techniques are not available. To offer a reliable backbone for IoT connectivity, Quality of Service (QoS) maintains network capabilities and resources. By classifying traffic and recording channel constraints, QoS will manage delays, delay variation, bandwidth, and packet loss in order to provide secure and predictable services. There are a variety of technologies that allow smart devices to communicate and exchange information with one another. Wired and wireless communications are two major categories for these technologies. The ideal connectivity solution would use very little power, have a long range, and be capable of transmitting enormous amounts of data (high bandwidth). Unfortunately, there is no such thing as optimal connectivity.
[0006] The Internet of Things (IoT) is a collection of intelligently connected devices that are connecting to the internet. Every day, as technology advances, an IoT device outnumbers humans on the world. The Internet of Things (IoT) systems would connect not only physical users and devices, but also virtual networks and devices that have already been implemented in various scenarios using new networking, computing, and integrated system technologies. With the rapid advancement of technology, the number of devices involved grows rapidly. IoT systems have crucial issues in supplying sufficient bandwidth to IoT Devices for Improving Quality in Services provided in the form of QoS (Quality of Service) parameters, depending on the volume of devices and data. There is a need of an Artificial intelligence based method for allocating the bandwidth for the IoT devises for improving the Quality of Services (QoS) of each IoT devices.
[0007] Referring to Figure 1, illustrates the present invention and main embodiment of current disclosure that is Artificial Intelligence Enabled Dynamic Bandwidth Allocation Optimization in IoT for Improved QoS comprising of IoT Devices (101), Router (102), Bandwidth Data (103), KM-PSO Clustering (104), Deep Alternative Neural Network (DANN) (105), Dynamic Bandwidth Allocation Optimization (106), and QoS Estimation (107); provides a scalable solution for allocating the bandwidth for the IoT enabled devices for improving QoS parameters.
[0008] The present invention disclosed herein is taking IoT Devices such as Smart TV, Thermostat, Smoke Alarm, Surveillance Camera, Smart Door Lock, Smart Watch, Smart AC, and Smart Light; these are generally available in a smart home or in smart offices. All these IoT Devices are connected together with Internet through Router. Router creates Home WiFi network or Office WiFi network. The Bandwidth Data consumed or the Data of Bandwidth consumed by the each IoT Device are noted from the router. The KM-PSO Clustering is the hybrid combination of the K-means and Particle Swarm Optimization (PSO). This hybrid combination method is used in the invention for clustering the IoT devices based on the Bandwidth utilized by them. The clustering is unsupervised method forms the clusters based on the bandwidth usage pattern of the IoT Devices. In the present invention a new clustering approach is established KM-PSO to detect the ideal number of clusters of an IoT device. The clustering accuracy of 97.6% with optimal value of k=3 is obtained with this hybrid combination. Three Clusters are formed with similar nodes as High, Medium, and Low Clusters.
[0009] The Deep Alternative Neural Network (DANN) comprising of several layers is a neural network, trained and generates the traffic rules based on the packets transmitted and received by the IoT devices in the clusters. The DANN predict the demand of Bandwidth to be supplied for each cluster, to the individual IoT devices in each cluster. The Dynamic Bandwidth Allocation Optimization is Artificial Intelligence enabled Dynamic Bandwidth Allocation Optimization (AIEDBAO) that uses Fuzzy Logic Controller to allocate the optimized bandwidth to each IoT devices. The traffic Data rules generated by DANN and forecast details. Based on the traffic rules and forecasting details, Fuzzy Logic Controller allocating bandwidth dynamically. The sufficient Bandwidth is provided by the Fuzzy controller to improving the QoS (107) parameters. The improved QoS parameters achieved with the present invention are Bandwidth Consumption of 34.5Mbps, Packet Delivery Delay (PDD) of 32ms, Packet Loss of 4% and Throughput of 99% at supply of 50Mbps.
[0010] The Summary of the Invention, as well as the attached sketches and the Detailed Description of the Invention, describe the present invention in various levels of detail, and the inclusion or omission of components, sections, or other things in this Summary of the Invention is not intended to limit the scope of the present disclosure. The summary of the Invention can be read with the detailed description for better understanding of the current disclosure.
[0011] The accompanying drawings are used for better understanding of the innovation, the accompanying drawings are incorporated into and form part of this specification. The drawing, when viewed in conjunction with the explanation, shows exemplary embodiments of the current disclosure and assists understanding of its principles. The drawings are for illustrative purposes only and do not limit the scope of the disclosure in any way. The elements are comparable but not identical, as seen by the use of the same reference numerals. Different reference numerals, on the other hand, may be used to define related components. Some embodiments might lack such elements and/or components, whereas others may use elements or components not depicted in the sketches.
[0012] Referring to Figure 1, illustrates the present invention and main embodiment of current disclosure that is Artificial Intelligence Enabled Dynamic Bandwidth Allocation Optimization in IoT for Improved QoS comprising of IoT Devices (101), Router (102), Bandwidth Data (103), KM-PSO Clustering (104), Deep Alternative Neural Network (DANN) (105), Dynamic Bandwidth Allocation Optimization (106), and QoS Estimation (107); provides a scalable solution for allocating the bandwidth for the IoT enabled devices for improving QoS parameters, in accordance with an exemplary embodiment of the present disclosure to understand the method of allocating the Bandwidth to the IoT devices dynamically and accompanied drawing. This drawing is considered to understand how all components present in the proposed method, the invention is not limited to this drawing, and this illustration is given to aid comprehension of the disclosure and should not be construed as limiting the disclosure's breadth, scope, or applicability. However, some aspects and/or components may not be present in embodiments, and others may be used in different forms than those indicated in the sketches. The usage of single language to describe a component or element might encompass a plural number of such components or elements, depending on the context, and vice versa.
[0013] Referring to Figure 2, illustrates Framework of KM-PSO Clustering comprising of IoT Devices (201), Data Usage Pattern (202), KM-PSO Clustering (203), and Classification (204), in accordance with another exemplary embodiment of the present disclosure to understand framework for generating the optimal number of clusters of IoT Devices of the present disclosure, the invention is not limited only to this drawing, and this illustration is provided to assist comprehension of the disclosure and should not be construed as restricting the depth, nature, or applicability of the disclosure.
[0014] Referring to Figure 3, illustrates Deep Alternative Neural Network (DANN) comprising of Input (301), Input Layer (302), Alternative Layer (303), Max Pool Layer (304), Soft Max Layer (305), and Output (306), in accordance with another exemplary embodiment of the present disclosure to understand the Traffic demand prediction for allocating Bandwidth to the IoT devices of the present disclosure, the invention is not limited only to this drawing, and this illustration is provided to assist comprehension of the disclosure and should not be construed as restricting the depth, nature, or applicability of the disclosure.
[0015] Referring to Figure 4, illustrates QoS Parameters, in accordance with another exemplary embodiment of the present disclosure to understand QoS Parameters improved of the present disclosure, the invention is not limited only to this drawing, and this illustration is provided to assist comprehension of the disclosure and should not be construed as restricting the depth, nature, or applicability of the disclosure.
[0016] As a result of the following detailed discussion, the invention will become more well-known, and objects other than those described below will become evident. This description makes use of the appended drawings. When considering the following thorough description of the invention, the invention will become more well-known, and objects other than those listed above will become clear. This description refers to the invention's accompanying drawings. It's also worth noting that additional or alternative measures should be done. Embodiments are provided so that a person skilled in the art can fully understand the current disclosure. Several specifics relating to various components and processes are provided in order to provide a thorough understanding of embodiments of the present disclosure. As is apparent for those who are qualified in the art, the information provided in the embodiments should not be seen to restrict the extent of this disclosure. In the process and procedure of this invention, the order of steps revealed must not be understood as requiring the order defined or illustrated. Additional or alternative steps should also be considered.
[0017] Referring to Figure 1, illustrates the present invention and main embodiment of current disclosure that is Artificial Intelligence Enabled Dynamic Bandwidth Allocation Optimization in IoT for Improved QoS comprising of IoT Devices (101), Router (102), Bandwidth Data (103), KM-PSO Clustering (104), Deep Alternative Neural Network (DANN) (105), Dynamic Bandwidth Allocation Optimization (106), and QoS Estimation (107); provides a scalable solution for allocating the bandwidth for the IoT enabled devices for improving QoS parameters. The IoT Devices (101) are smart internet connected devices for exchanging the information or the data. These IoT Devices (101) are non-standard computing devices such as sensors, actuators, Small Electronic Devices, Machines connected to Internet, and smart devices which are connected wirelessly through Internet. The present invention disclosed herein is taking IoT Devices (101) such as Smart TV, Thermostat, Smoke Alarm, Surveillance Camera, Smart Door Lock, Smart Watch, Smart AC, and Smart Light; these are generally available in a smart home or in smart offices. All these IoT Devices (10 1) are connected together with Internet can be accessed remotely for controlling through Internet application. The Router (102) provides internet access to all the IoT devices wirelessly.
The Router (102) is a smart Internet Gateway and networking device for IoT Devices (101) to transmit and receive Data Packets. Router creates Home WiFi network or Office WiFi network. In the present invention total of eight IoT Devices are connected to the Router (102). The Bandwidth Data (103) consumed or the Data of Bandwidth consumed by the each IoT Device (101) are noted in the Table 1.
TABLE 1
Bandwidth Usage (Mbps) of IoT Devices of Present Invention
IoT Devices Type of Client BandwidthsUsage
Smart TV Active Wireless Client 3.83 Thermostat Active Wireless Client 4.6 Smoke Alarm Active Wireless Client 1.5 Surveillance Camera Active Wireless Client 8.56 Smart Door Lock Active Wireless Client 3.8 Smart Watch Active Wireless Client 5.2 Smart AC Active Wireless Client 7.22 Smart Light Active Wireless Client 2.4
[0018] In the Table 1, the highest Bandwidth is used by the Surveillance Camera IoT device due to continuous monitoring and sharing the Data through internet. The client indicates an IoT device, its state as Active means IoT Device is said to be "ON" and is connected wirelessly. IoT Devices can also be connected with wired connections. The IoT devices listed in Table 1 are continuously transmitting the Data through the Internet; the bandwidth utilized by the IoT devices should be forecasted and should be allotted as per the IoT device demand. There is requirement of dynamic mechanism to predict the demand and allocating the bandwidth to each device so as to provide better Quality of Services.
[0019] The KM-PSO Clustering (104) is the hybrid combination of the K-means and Particle Swarm Optimization (PSO). This hybrid combination method is used in the invention for clustering the IoT devices based on the Bandwidth utilized by them. The clustering is unsupervised method forms the clusters based on the bandwidth usage pattern of the IoT Devices (101). The K-means uses Similarity function to measure the closeness of the pattern of bandwidth used by each IoT Device. It measures the optimum value for the cluster. The optimum value for the K is determined as 3 in the present invention disclosed herein. The PSO operates by randomly initially initializing a flock of birds over the search area where every bird is known to be a 'part' Consider that some "particles" fly at certain speeds to achieve the global solution in an iterative process. The PSO algorithm is a highly optimistic global search algorithm. But the convergence of the PSO algorithm is very slow near the solution. But K-Means converges quickly to optimal local results, but the ability to find a global solution is weak. In the present invention a new clustering approach is established as KM-PSO to detect the ideal number of clusters of IoT devices (101). The clustering accuracy of 97.6% with optimal value of k=3 is obtained with this hybrid combination. Three Clusters are formed with similar nodes as High, Medium, and Low Clusters. The Clustering of IoT devices into three classes are listed in Table 2.
TABLE2
Clustering of IoT devices into three classes by KM-PSO
IoT Devices Cluster Class Band(wdpsUsage
Smart TV Medium 3.83
Thermostat High 4.6 Smoke Alarm Low 1.5 Surveillance Camera High 8.56 Smart Door Lock Medium 3.8 Smart Watch High 5.2 Smart AC High 7.22 Smart Light Medium 2.4
[0020]The Clusters are formed based on the Bandwidth used by each IoT devices and the corresponding values are also listed in the Table 2. The Deep Alternative Neural Network (DANN) (105) comprising of several layers is a neural network, trained and generates the traffic rules based on the packets transmitted and received by the IoT devices in the clusters. The Traffic rules are again categorized into High, Medium, and
Low. In addition to this, DANN finds alternative paths for routing the packets to the IoT devices present in the clusters to improve QoS of each IoT devices, and forecast the bandwidth required for each IoT device. The DANN predict the demand of Bandwidth to be supplied for each cluster, to the individual IoT devices in each cluster. The Dynamic Bandwidth Allocation Optimization (106) is Artificial Intelligence enabled Dynamic Bandwidth Allocation Optimization (AIEDBAO) that uses Fuzzy Logic Controller to allocate the optimized bandwidth to each IoT devices. The traffic Data rules generated by DANN and forecast details. Based on the traffic rules and forecasting details, Fuzzy Logic Controller allocating bandwidth dynamically. The Fuzzy Logic Controller allocates bandwidth based on the set of fuzzy rules, rules are frames based on the traffic rules provided by the DANN. The sufficient Bandwidth is provided by the Fuzzy controller to improving the QoS (107) parameters. The improved QoS parameters achieved with the present invention are Bandwidth Consumption of 34.5Mbps, Packet Delivery Delay (PDD) of 32ms, Packet Loss of 4% and Throughput of 99% at supply of Mbps. The optimized Bandwidths allocated for each IoT devices in the present invention are listed in Table 3.
TABLE3
Optimized Bandwidths allocated for each IoT devices by AIEDBAO
IoT Devices Bandwidth Usage Optimized Bandwidth (Mbps) Allocated (Mbps) Smart TV 3.83 5 Thermostat 4.6 6 Smoke Alarm 1.5 3 Surveillance Camera 8.56 10 Smart Door Lock 3.8 5 Smart Watch 5.2 6 Smart AC 7.22 10 Smart Light 2.4 4
[0021] Referring to Figure 2, illustrates Framework of KM-PSO Clustering comprising of IoT Devices (201), Data Usage Pattern (202), KM-PSO Clustering (203), and Classification (204), in accordance with another exemplary embodiment of the present disclosure to understand framework for generating the optimal number of clusters of IoT Devices of the present disclosure. The IoT Devices (201) are smart internet connected devices for exchanging the information or the data. These IoT Devices (101) are non-standard computing devices such as sensors, actuators, Small Electronic Devices, Machines connected to Internet, and smart devices which are connected wirelessly through Internet. The Data Usage Pattern (202) is identified based on the packets transmitted. The KM-PSO Clustering (203) is the hybrid combination of the K means and Particle Swarm Optimization (PSO). This hybrid combination method is used in the invention for clustering the IoT devices based on the Bandwidth utilized by them. The clustering is unsupervised method forms the clusters based on the bandwidth usage pattern of the IoT Devices (201). Three Clusters are formed with similar nodes as High, Medium, and Low Clusters, the classification (204) is as High, Medium, and Low based on the Data used.
[0022] Referring to Figure 3, illustrates Deep Alternative Neural Network (DANN) comprising of Input (301), Input Layer (302), Alternative Layer (303), Max Pool Layer (304), Soft Max Layer (305), and Output (306), in accordance with another exemplary embodiment of the present disclosure to understand the Traffic demand prediction for allocating Bandwidth to the IoT devices. The input layer (201) senses the traffic of each IoT devices in the Cluster group. The Alternative Layer (303) is a recurrent convolutional layer provides the details of the number of packets transmitted, data usage for the transmitted packets. The Max Pool Layer (304), and Soft Max Layer (305) are the pooling layers are used to reweights the data usage values for predicting the sufficient bandwidth values as output (306).
[0023] Referring to Figure 4, illustrates QoS Parameters bar graph plotted for the IoT devices at 50Mbps bandwidth Allocated. The QoS parameters achieved with the present invention are Bandwidth Consumption of 34.5Mbps, Packet Delivery Delay (PDD) of 32ms, Packet Loss of 4% and Throughput of 99% at supply of 50Mbps. From the plot, it is showing that the Packet Loss is decreasing with increased throughput for increased optimized bandwidth allocation.
[0024] Several specific details are set out in the above exemplary explanation in order to provide a more detailed understanding of embodiments of the invention. An artisan of ordinary skill, on the other hand, might notice that the existing innovation can be practiced without integrating any of the specific information mentioned herein. The main embodiments of the present disclosure are considered dynamic bandwidth allocation. The subsequent description gives the details about the how the component assigns bandwidth. To provide an Al enabled Dynamic Bandwidth Allocation to the IoT devices based on the data usage pattern, the method and the way of the present embodiment is provided in the above layout and it shall not limit the scope of the present disclosure.
Claims (5)
1. Artificial Intelligence Enabled Dynamic Bandwidth Allocation Optimization in IoT for Improved QoS comprising of IoT Devices (101), Router (102), Bandwidth Data (103), KM-PSO Clustering (104), Deep Alternative Neural Network (DANN) (105), Dynamic Bandwidth Allocation Optimization (106), and QoS Estimation (107); provides a scalable solution for allocating the bandwidth for the IoT enabled devices for improving QoS parameters.
2. Artificial Intelligence Enabled Dynamic Bandwidth Allocation Optimization in IoT for Improved QoS as claimed in claim 1, wherein eight IoT Devices such as Smart TV, Thermostat, Smoke Alarm, Surveillance Camera, Smart Door Lock, Smart Watch, Smart AC, and Smart Light are connected to the Router and corresponding Bandwidth usage are observed.
3. Artificial Intelligence Enabled Dynamic Bandwidth Allocation Optimization in IoT for Improved QoS as claimed in claim 1, wherein new clustering approach is established as KM-PSO to detect the ideal number of clusters of IoT devices. The clustering accuracy of 97.6% with optimal value of k=3 is obtained with this hybrid combination; three Clusters are formed with similar nodes as High, Medium, and Low Clusters.
4. Artificial Intelligence Enabled Dynamic Bandwidth Allocation Optimization in IoT for Improved QoS as claimed in claim 1, wherein Deep Alternative Neural Network (DANN) comprising of Input Layer, Alternative Layer, Max Pool Layer, and Soft Max Layer is trained, and generates the traffic rules based on the packets transmitted and received by the IoT devices in the clusters. The Traffic rules are again categorized into High, Medium, and Low; predict the demand of Bandwidth to be supplied for each cluster, to the individual IoT devices in each cluster.
5. Artificial Intelligence Enabled Dynamic Bandwidth Allocation Optimization in IoT for Improved QoS as claimed in claim 1, wherein Artificial Intelligence enabled Dynamic Bandwidth Allocation Optimization (AIEDBAO) that uses Fuzzy Logic Controller to allocate the optimized bandwidth to each IoT devices; Based on the traffic rules and forecasting details, Fuzzy Logic Controller allocating bandwidth dynamically; improved QoS parameters achieved with the present invention are Bandwidth Consumption of 34.5Mbps, Packet Delivery Delay (PDD) of 32ms, Packet Loss of 4% and Throughput of 99% at supply of 50Mbps.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2021103738A AU2021103738A4 (en) | 2021-06-30 | 2021-06-30 | ARTIFICIAL INTELLIGENCE ENABLED DYNAMIC BANDWIDTH ALLOCATION OPTIMIZATION IN IoT FOR IMPROVED QoS |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2021103738A AU2021103738A4 (en) | 2021-06-30 | 2021-06-30 | ARTIFICIAL INTELLIGENCE ENABLED DYNAMIC BANDWIDTH ALLOCATION OPTIMIZATION IN IoT FOR IMPROVED QoS |
Publications (1)
Publication Number | Publication Date |
---|---|
AU2021103738A4 true AU2021103738A4 (en) | 2021-08-19 |
Family
ID=77274320
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
AU2021103738A Ceased AU2021103738A4 (en) | 2021-06-30 | 2021-06-30 | ARTIFICIAL INTELLIGENCE ENABLED DYNAMIC BANDWIDTH ALLOCATION OPTIMIZATION IN IoT FOR IMPROVED QoS |
Country Status (1)
Country | Link |
---|---|
AU (1) | AU2021103738A4 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116867090A (en) * | 2023-09-01 | 2023-10-10 | 华南师范大学 | Internet of things resource allocation method, device, equipment and storage medium |
-
2021
- 2021-06-30 AU AU2021103738A patent/AU2021103738A4/en not_active Ceased
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116867090A (en) * | 2023-09-01 | 2023-10-10 | 华南师范大学 | Internet of things resource allocation method, device, equipment and storage medium |
CN116867090B (en) * | 2023-09-01 | 2024-01-09 | 华南师范大学 | Internet of things resource allocation method, device, equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Rezaee et al. | A fuzzy congestion control protocol based on active queue management in wireless sensor networks with medical applications | |
Sun et al. | Autonomous resource slicing for virtualized vehicular networks with D2D communications based on deep reinforcement learning | |
US10609147B2 (en) | Target wake time and grouping scheme for IoT transmitters | |
CN107846371B (en) | QoE resource allocation method for multimedia service | |
CN111953510A (en) | Smart grid slice wireless resource allocation method and system based on reinforcement learning | |
US11451456B2 (en) | Learning stable representations of devices for clustering-based device classification systems | |
Hatamian et al. | Congestion-aware routing and fuzzy-based rate controller for wireless sensor networks | |
US11100364B2 (en) | Active learning for interactive labeling of new device types based on limited feedback | |
Stewart et al. | Dynamic iot management system using k-means machine learning for precision agriculture applications | |
AU2021103738A4 (en) | ARTIFICIAL INTELLIGENCE ENABLED DYNAMIC BANDWIDTH ALLOCATION OPTIMIZATION IN IoT FOR IMPROVED QoS | |
Zhou et al. | Digital twin-empowered network planning for multi-tier computing | |
Yadav et al. | Mitigating congestion in wireless sensor networks through clustering and queue assistance: a survey | |
Anitha et al. | Decision Tree Algorithm for Intelligent Resource Management in Wireless Networks | |
Shokrnezhad et al. | Near-optimal cloud-network integrated resource allocation for latency-sensitive b5g | |
Srilakshmi et al. | Selection of machine learning techniques for network lifetime parameters and synchronization issues in wireless networks | |
Jarwan et al. | Information-oriented traffic management for energy-efficient and loss-resilient iot systems | |
Chai et al. | Real-time communication model based on OPC UA wireless network for intelligent production line | |
Liu et al. | Multiple layer design for mass data transmission against channel congestion in IoT | |
CN108292122B (en) | Communication between distributed information agents within a data and energy storage internet architecture | |
Moslehi et al. | A QoS optimization technique with deep reinforcement learning in SDN-based IoT | |
Salma et al. | Software defined networking based for improved wireless sensor network | |
Roselind et al. | Artificial Intelligence enabled Dynamic Bandwidth Allocation Optimization in IoT for improved QoS | |
Mahajan et al. | Congestion control protocols in wireless sensor networks: a comprehensive Survey | |
Abegaz et al. | Multi-agent Federated Reinforcement Learning for Resource Allocation in UAV-enabled Internet of Medical Things Networks | |
SelvaKumar et al. | Network Traffic Control Using AI |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
FGI | Letters patent sealed or granted (innovation patent) | ||
MK22 | Patent ceased section 143a(d), or expired - non payment of renewal fee or expiry |