A Machine Learning Based Connectivity Restoration Strategy for Industrial IoTs
The connectivity restoration has significance for Industrial IoTs (IIoTs). If the connectivity is compromised, mobile data collectors can be deployed to restore the connectivity. The aggregation ratio, which is the proportion of data successfully delivered to the sink over all data, is considered as...
| Päätekijät: | , , , , |
|---|---|
| Aineistotyyppi: | Artikkeli |
| Kieli: | English |
| Julkaistu: |
IEEE
2020-01-01
|
| Sarja: | IEEE Access |
| Aiheet: | |
| Linkit: | https://ieeexplore.ieee.org/document/9064553/ |
| _version_ | 1830351548249538560 |
|---|---|
| author | Jiong Wang Hua Zhang Zhiqiang Ruan Tao Wang Xiaoding Wang |
| author_facet | Jiong Wang Hua Zhang Zhiqiang Ruan Tao Wang Xiaoding Wang |
| author_sort | Jiong Wang |
| collection | DOAJ |
| description | The connectivity restoration has significance for Industrial IoTs (IIoTs). If the connectivity is compromised, mobile data collectors can be deployed to restore the connectivity. The aggregation ratio, which is the proportion of data successfully delivered to the sink over all data, is considered as a crucial index. However, previous works only consider the travel distance, the load balance, the latency and the energy cost over the aggregation ratio. In this paper, a machine learning based connectivity restoration strategy CRrbf, that utilizes a Radial Basis Function Neural Network (RBFNN) along with an Unscented Kalman Filter (UKF), is proposed to maximize the aggregation ratio meanwhile reduce the energy cost. The theoretical analysis and simulation results indicate that CRrbf outperforms both distance based strategies and terrain based strategies in the aggregation ratio, the network latency and the network throughput. And the energy cost of CRrbf is less than that of distance based strategies. |
| first_indexed | 2024-12-20T00:40:06Z |
| format | Article |
| id | doaj.art-b6217dac5f444b92b81d61a5a85d01d5 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-20T00:40:06Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-b6217dac5f444b92b81d61a5a85d01d52022-12-21T19:59:38ZengIEEEIEEE Access2169-35362020-01-018711367114510.1109/ACCESS.2020.29873499064553A Machine Learning Based Connectivity Restoration Strategy for Industrial IoTsJiong Wang0https://orcid.org/0000-0002-0671-0332Hua Zhang1https://orcid.org/0000-0002-0177-9429Zhiqiang Ruan2https://orcid.org/0000-0002-1144-2440Tao Wang3https://orcid.org/0000-0002-9063-6955Xiaoding Wang4https://orcid.org/0000-0002-3822-5964College of Computer and Control Engineering, Minjiang University, Fuzhou, ChinaCollege of Computer and Control Engineering, Minjiang University, Fuzhou, ChinaCollege of Computer and Control Engineering, Minjiang University, Fuzhou, ChinaCollege of Computer and Control Engineering, Minjiang University, Fuzhou, ChinaFujian Provincial Key Laboratory of Network Security and Cryptology, College of Mathematics and Informatics, Fujian Normal University, Fuzhou, ChinaThe connectivity restoration has significance for Industrial IoTs (IIoTs). If the connectivity is compromised, mobile data collectors can be deployed to restore the connectivity. The aggregation ratio, which is the proportion of data successfully delivered to the sink over all data, is considered as a crucial index. However, previous works only consider the travel distance, the load balance, the latency and the energy cost over the aggregation ratio. In this paper, a machine learning based connectivity restoration strategy CRrbf, that utilizes a Radial Basis Function Neural Network (RBFNN) along with an Unscented Kalman Filter (UKF), is proposed to maximize the aggregation ratio meanwhile reduce the energy cost. The theoretical analysis and simulation results indicate that CRrbf outperforms both distance based strategies and terrain based strategies in the aggregation ratio, the network latency and the network throughput. And the energy cost of CRrbf is less than that of distance based strategies.https://ieeexplore.ieee.org/document/9064553/IIoTsconnectivity restorationmachine learning |
| spellingShingle | Jiong Wang Hua Zhang Zhiqiang Ruan Tao Wang Xiaoding Wang A Machine Learning Based Connectivity Restoration Strategy for Industrial IoTs IEEE Access IIoTs connectivity restoration machine learning |
| title | A Machine Learning Based Connectivity Restoration Strategy for Industrial IoTs |
| title_full | A Machine Learning Based Connectivity Restoration Strategy for Industrial IoTs |
| title_fullStr | A Machine Learning Based Connectivity Restoration Strategy for Industrial IoTs |
| title_full_unstemmed | A Machine Learning Based Connectivity Restoration Strategy for Industrial IoTs |
| title_short | A Machine Learning Based Connectivity Restoration Strategy for Industrial IoTs |
| title_sort | machine learning based connectivity restoration strategy for industrial iots |
| topic | IIoTs connectivity restoration machine learning |
| url | https://ieeexplore.ieee.org/document/9064553/ |
| work_keys_str_mv | AT jiongwang amachinelearningbasedconnectivityrestorationstrategyforindustrialiots AT huazhang amachinelearningbasedconnectivityrestorationstrategyforindustrialiots AT zhiqiangruan amachinelearningbasedconnectivityrestorationstrategyforindustrialiots AT taowang amachinelearningbasedconnectivityrestorationstrategyforindustrialiots AT xiaodingwang amachinelearningbasedconnectivityrestorationstrategyforindustrialiots AT jiongwang machinelearningbasedconnectivityrestorationstrategyforindustrialiots AT huazhang machinelearningbasedconnectivityrestorationstrategyforindustrialiots AT zhiqiangruan machinelearningbasedconnectivityrestorationstrategyforindustrialiots AT taowang machinelearningbasedconnectivityrestorationstrategyforindustrialiots AT xiaodingwang machinelearningbasedconnectivityrestorationstrategyforindustrialiots |