Towards artificial intelligence-based reduction of greenhouse gas emissions in the telecommunications industry
This paper presents the assessment and management of emissions of pollutant gases at telecommunication base stations (BSs) due to the operations of diesel generators. A model combining the source testing method with an artificial neural network (ANN) technique and the Internet of Things (IoT) system...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-07-01
|
| Series: | Scientific African |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2468227621001277 |
| _version_ | 1818599868752461824 |
|---|---|
| author | Gift Bonire Abiodun Gbenga-Ilori |
| author_facet | Gift Bonire Abiodun Gbenga-Ilori |
| author_sort | Gift Bonire |
| collection | DOAJ |
| description | This paper presents the assessment and management of emissions of pollutant gases at telecommunication base stations (BSs) due to the operations of diesel generators. A model combining the source testing method with an artificial neural network (ANN) technique and the Internet of Things (IoT) system is proposed in this paper. The actual concentration of gases and particles like carbon dioxide (CO2), carbon monoxide (CO), nitrogen dioxide (NO2), sulphur dioxide (SO2), and particulate matter in the atmosphere due to the operation of base stations in Abuja, Nigeria is studied. The results show that measured emission of CO2 gas was the highest; ranging from 1976 to 4498 ppm at the BS sites and exceeding the normal outdoor level and maximum permissible safety level. Generally, all gases and particles measured at the generator sites exceeded the acceptable limit, thereby exposing workers at these BSs to health hazards. Measured emissions for NO2 at locations away from the BS sites surpassed the set limits, which highlights the need for cleaner sources of energy to power the BSs especially given the toxicity of this gas. Furthermore, about 48% of the measured data for SO2 gas exceeded the recommended limit. The values measured for PM2.5 and PM10 also exceed the recommended 150 µg/m3 limit, thereby posing health risks to the site workers and residents in the neighbourhood. The ANN technique is employed to analyse the data and ensure that future emissions from base stations can be predicted with a degree of accuracy, and to assess the factors that affect these emissions. The result shows that the proposed ANN model efficiently predicted the emissions of the pollutant gases with an overall correlation coefficient value of 0.93719, thus making it a good fit in forecasting. An IoT-based system is also proposed as a solution to reduce these greenhouse gases. |
| first_indexed | 2024-12-16T12:26:26Z |
| format | Article |
| id | doaj.art-f6734724bef943edbf893d164cf2724e |
| institution | Directory Open Access Journal |
| issn | 2468-2276 |
| language | English |
| last_indexed | 2024-12-16T12:26:26Z |
| publishDate | 2021-07-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Scientific African |
| spelling | doaj.art-f6734724bef943edbf893d164cf2724e2022-12-21T22:31:49ZengElsevierScientific African2468-22762021-07-0112e00823Towards artificial intelligence-based reduction of greenhouse gas emissions in the telecommunications industryGift Bonire0Abiodun Gbenga-Ilori1Department of Electrical and Electronics Engineering, University of Lagos, Akoka, Lagos, NigeriaCorresponding author.; Department of Electrical and Electronics Engineering, University of Lagos, Akoka, Lagos, NigeriaThis paper presents the assessment and management of emissions of pollutant gases at telecommunication base stations (BSs) due to the operations of diesel generators. A model combining the source testing method with an artificial neural network (ANN) technique and the Internet of Things (IoT) system is proposed in this paper. The actual concentration of gases and particles like carbon dioxide (CO2), carbon monoxide (CO), nitrogen dioxide (NO2), sulphur dioxide (SO2), and particulate matter in the atmosphere due to the operation of base stations in Abuja, Nigeria is studied. The results show that measured emission of CO2 gas was the highest; ranging from 1976 to 4498 ppm at the BS sites and exceeding the normal outdoor level and maximum permissible safety level. Generally, all gases and particles measured at the generator sites exceeded the acceptable limit, thereby exposing workers at these BSs to health hazards. Measured emissions for NO2 at locations away from the BS sites surpassed the set limits, which highlights the need for cleaner sources of energy to power the BSs especially given the toxicity of this gas. Furthermore, about 48% of the measured data for SO2 gas exceeded the recommended limit. The values measured for PM2.5 and PM10 also exceed the recommended 150 µg/m3 limit, thereby posing health risks to the site workers and residents in the neighbourhood. The ANN technique is employed to analyse the data and ensure that future emissions from base stations can be predicted with a degree of accuracy, and to assess the factors that affect these emissions. The result shows that the proposed ANN model efficiently predicted the emissions of the pollutant gases with an overall correlation coefficient value of 0.93719, thus making it a good fit in forecasting. An IoT-based system is also proposed as a solution to reduce these greenhouse gases.http://www.sciencedirect.com/science/article/pii/S2468227621001277Greenhouse gasesEmissionsBase stationsAnnTelecommunications |
| spellingShingle | Gift Bonire Abiodun Gbenga-Ilori Towards artificial intelligence-based reduction of greenhouse gas emissions in the telecommunications industry Scientific African Greenhouse gases Emissions Base stations Ann Telecommunications |
| title | Towards artificial intelligence-based reduction of greenhouse gas emissions in the telecommunications industry |
| title_full | Towards artificial intelligence-based reduction of greenhouse gas emissions in the telecommunications industry |
| title_fullStr | Towards artificial intelligence-based reduction of greenhouse gas emissions in the telecommunications industry |
| title_full_unstemmed | Towards artificial intelligence-based reduction of greenhouse gas emissions in the telecommunications industry |
| title_short | Towards artificial intelligence-based reduction of greenhouse gas emissions in the telecommunications industry |
| title_sort | towards artificial intelligence based reduction of greenhouse gas emissions in the telecommunications industry |
| topic | Greenhouse gases Emissions Base stations Ann Telecommunications |
| url | http://www.sciencedirect.com/science/article/pii/S2468227621001277 |
| work_keys_str_mv | AT giftbonire towardsartificialintelligencebasedreductionofgreenhousegasemissionsinthetelecommunicationsindustry AT abiodungbengailori towardsartificialintelligencebasedreductionofgreenhousegasemissionsinthetelecommunicationsindustry |