<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>The big energy data and carbon emission monitoring system is designed to collect carbon emission-related data for pollution gas management. This paper constructs a carbon emission monitoring system in the context of carbon neutrality and peaking. A multi-layer perceptron algorithm is introduced based on the principle of perception, and a BP-MLP neural network model is proposed by optimizing the perceptron weights using BP neural network. For the sensors in the carbon emission monitoring system, the node redundancy is processed, and the optimal sensor distribution is proved by using the correlation coefficient. Finally, the evaluation analysis of the carbon monitoring system was carried out in three aspects: relevance coefficient de-redundancy, number of iterations and daily emissions. The results show that when the correlation threshold is 0.8, the sensor distribution of the monitoring system can satisfy the monitoring under various wind conditions, and when the number of iterations is 600, the difference between the real value and the monitored value is only 3.63% and the daily emission peaks at 5.243 mg/m3 at 14:00 a.m. This shows that the carbon emission monitoring system constructed based on the BP-MLP model can effectively collect and analyze carbon emission data. Data collection and analysis, and provide corresponding data support for the management of gas pollution.</p>
</abstract>

The big energy data and carbon emission monitoring system is designed to collect carbon emission-related data for pollution gas management. This paper constructs a carbon emission monitoring system in the context of carbon neutrality and peaking. A multi-layer perceptron algorithm is introduced based on the principle of perception, and a BP-MLP neural network model is proposed by optimizing the perceptron weights using BP neural network. For the sensors in the carbon emission monitoring system, the node redundancy is processed, and the optimal sensor distribution is proved by using the correlation coefficient. Finally, the evaluation analysis of the carbon monitoring system was carried out in three aspects: relevance coefficient de-redundancy, number of iterations and daily emissions. The results show that when the correlation threshold is 0.8, the sensor distribution of the monitoring system can satisfy the monitoring under various wind conditions, and when the number of iterations is 600, the difference between the real value and the monitored value is only 3.63% and the daily emission peaks at 5.243 mg/m3 at 14:00 a.m. This shows that the carbon emission monitoring system constructed based on the BP-MLP model can effectively collect and analyze carbon emission data. Data collection and analysis, and provide corresponding data support for the management of gas pollution.

Design of energy big data and carbon emission monitoring system based on perceptron model in the context of carbon neutral and carbon peaking

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

The big energy data and carbon emission monitoring system is designed to collect carbon emission-related data for pollution gas management. This paper...

Design of energy big data and carbon emission monitoring system based on perceptron model in the context of carbon neutral and carbon peaking

Online veröffentlicht: 28. Aug. 2023

Seitenbereich: -

Eingereicht: 03. Nov. 2022

Akzeptiert: 08. März 2022

DOI: https://doi.org/10.2478/amns.2023.2.00260

Schlüsselwörter
Perceptron, BP-MLP model, Carbon emissions, Monitoring system, Correlation coefficient

© 2023 Yuanyuan Hu et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Design of energy big data and carbon emission monitoring system based on perceptron model in the context of carbon neutral and carbon peaking

Online veröffentlicht: 28. Aug. 2023

Seitenbereich: -

Eingereicht: 03. Nov. 2022

Akzeptiert: 08. März 2022

DOI: https://doi.org/10.2478/amns.2023.2.00260

SchlüsselwörterPerceptron, BP-MLP model, Carbon emissions, Monitoring system, Correlation coefficient

© 2023 Yuanyuan Hu et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Schlüsselwörter
Perceptron, BP-MLP model, Carbon emissions, Monitoring system, Correlation coefficient