Generalizable Machine-Learning-Based Modeling of Radiowave Propagation in Stadiums
Providing high throughput and quality of service in modern stadiums necessitates the placement of hundreds of access points (APs). Optimizing the locations of APs in such venues via measurements requires significant resources. Even simulation methods, such as ray-tracing, can be computationally cost...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Open Journal of Antennas and Propagation |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10234577/ |
| _version_ | 1827676288192610304 |
|---|---|
| author | Aristeidis Seretis Vladan Jevremovic Ali Jemmali Costas D. Sarris |
| author_facet | Aristeidis Seretis Vladan Jevremovic Ali Jemmali Costas D. Sarris |
| author_sort | Aristeidis Seretis |
| collection | DOAJ |
| description | Providing high throughput and quality of service in modern stadiums necessitates the placement of hundreds of access points (APs). Optimizing the locations of APs in such venues via measurements requires significant resources. Even simulation methods, such as ray-tracing, can be computationally costly. We provide a solution to this problem by building a propagation model based on machine learning (ML) that rapidly predicts received signal strengths in stadiums. We train the model with a small set of simulated data generated by a ray-tracer. We use input features, such as the electrical distance between the transmitter and the receiver, and the antenna gain along the direct path between the two, to generalize to new transmitter locations, antenna patterns and stadium geometries. Geometry and pattern generalization have not been included in existing propagation models for stadiums. Finally, we present a novel sampling approach for the input features in a given stadium, ensuring the computational efficiency and accuracy of the ML model. The results demonstrate the accuracy of our propagation model for new transmitter locations, patterns and stadiums. The trained model is also considerably faster than a ray-tracer, making it an efficient tool for resource planning tasks, such as optimal placement of APs. |
| first_indexed | 2024-03-10T05:21:31Z |
| format | Article |
| id | doaj.art-3ab8589afede4d3aae58dcca01253642 |
| institution | Directory Open Access Journal |
| issn | 2637-6431 |
| language | English |
| last_indexed | 2024-03-10T05:21:31Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Antennas and Propagation |
| spelling | doaj.art-3ab8589afede4d3aae58dcca012536422023-11-23T00:00:44ZengIEEEIEEE Open Journal of Antennas and Propagation2637-64312023-01-0141116112810.1109/OJAP.2023.331038210234577Generalizable Machine-Learning-Based Modeling of Radiowave Propagation in StadiumsAristeidis Seretis0https://orcid.org/0000-0001-7107-0768Vladan Jevremovic1Ali Jemmali2https://orcid.org/0000-0001-6111-7833Costas D. Sarris3https://orcid.org/0000-0003-4857-8330Edward S. Rogers Sr. Department of Electrical and Computer Engineering, University of Toronto, Toronto, CanadaiBwave, Saint-Laurent, CanadaiBwave, Saint-Laurent, CanadaEdward S. Rogers Sr. Department of Electrical and Computer Engineering, University of Toronto, Toronto, CanadaProviding high throughput and quality of service in modern stadiums necessitates the placement of hundreds of access points (APs). Optimizing the locations of APs in such venues via measurements requires significant resources. Even simulation methods, such as ray-tracing, can be computationally costly. We provide a solution to this problem by building a propagation model based on machine learning (ML) that rapidly predicts received signal strengths in stadiums. We train the model with a small set of simulated data generated by a ray-tracer. We use input features, such as the electrical distance between the transmitter and the receiver, and the antenna gain along the direct path between the two, to generalize to new transmitter locations, antenna patterns and stadium geometries. Geometry and pattern generalization have not been included in existing propagation models for stadiums. Finally, we present a novel sampling approach for the input features in a given stadium, ensuring the computational efficiency and accuracy of the ML model. The results demonstrate the accuracy of our propagation model for new transmitter locations, patterns and stadiums. The trained model is also considerably faster than a ray-tracer, making it an efficient tool for resource planning tasks, such as optimal placement of APs.https://ieeexplore.ieee.org/document/10234577/Radio propagationelectromagnetic propagationray tracingneural networks |
| spellingShingle | Aristeidis Seretis Vladan Jevremovic Ali Jemmali Costas D. Sarris Generalizable Machine-Learning-Based Modeling of Radiowave Propagation in Stadiums IEEE Open Journal of Antennas and Propagation Radio propagation electromagnetic propagation ray tracing neural networks |
| title | Generalizable Machine-Learning-Based Modeling of Radiowave Propagation in Stadiums |
| title_full | Generalizable Machine-Learning-Based Modeling of Radiowave Propagation in Stadiums |
| title_fullStr | Generalizable Machine-Learning-Based Modeling of Radiowave Propagation in Stadiums |
| title_full_unstemmed | Generalizable Machine-Learning-Based Modeling of Radiowave Propagation in Stadiums |
| title_short | Generalizable Machine-Learning-Based Modeling of Radiowave Propagation in Stadiums |
| title_sort | generalizable machine learning based modeling of radiowave propagation in stadiums |
| topic | Radio propagation electromagnetic propagation ray tracing neural networks |
| url | https://ieeexplore.ieee.org/document/10234577/ |
| work_keys_str_mv | AT aristeidisseretis generalizablemachinelearningbasedmodelingofradiowavepropagationinstadiums AT vladanjevremovic generalizablemachinelearningbasedmodelingofradiowavepropagationinstadiums AT alijemmali generalizablemachinelearningbasedmodelingofradiowavepropagationinstadiums AT costasdsarris generalizablemachinelearningbasedmodelingofradiowavepropagationinstadiums |