Pub Date : 2022-07-29DOI: 10.1109/GTSD54989.2022.9989209
Dinh Thanh Viet, Tran Hong Quan
With the continuous variation of the power demand and the weather-dependent characteristics of the distributed energy resources (DERs), the balance of operation security and customers' benefits, is not easy to harmonize, especially in the context of the DERs' development such as solar, wind energy at present. In practice, we have to find a good solution to meet the objective of photovoltaic energy output's maximization and the objective of power loss's minimization and etc. But multi-objective optimization problem (MOOP) usually consumes a lot of time to solve and can not be converged in some cases with a fairly large complex network. In this paper, an enhancement of utilizing an open-source platform to solve MOOP for a distribution system integrated with DERs has been proposed. All implemented calculation and programming are optimized to reduce the consuming time, thus it is very flexible and legal to apply economically in practice. Specifically, it is expected to apply the whole model and its own results in the operation activity of power distribution companies.
{"title":"An Enhancement of Multi-objective Optimization Method in Unbalanced Power Distribution System Integrated Distributed Energy Resources","authors":"Dinh Thanh Viet, Tran Hong Quan","doi":"10.1109/GTSD54989.2022.9989209","DOIUrl":"https://doi.org/10.1109/GTSD54989.2022.9989209","url":null,"abstract":"With the continuous variation of the power demand and the weather-dependent characteristics of the distributed energy resources (DERs), the balance of operation security and customers' benefits, is not easy to harmonize, especially in the context of the DERs' development such as solar, wind energy at present. In practice, we have to find a good solution to meet the objective of photovoltaic energy output's maximization and the objective of power loss's minimization and etc. But multi-objective optimization problem (MOOP) usually consumes a lot of time to solve and can not be converged in some cases with a fairly large complex network. In this paper, an enhancement of utilizing an open-source platform to solve MOOP for a distribution system integrated with DERs has been proposed. All implemented calculation and programming are optimized to reduce the consuming time, thus it is very flexible and legal to apply economically in practice. Specifically, it is expected to apply the whole model and its own results in the operation activity of power distribution companies.","PeriodicalId":125445,"journal":{"name":"2022 6th International Conference on Green Technology and Sustainable Development (GTSD)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122854703","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-29DOI: 10.1109/GTSD54989.2022.9988988
N. Hoang, Hong–Phuc Vo, P. Le, Cao-Luong Tran, Nhat-Duy Trinh, Tran-Anh-Doi Pham
Due to technological developments and redoubled focus on renewable energy, electric vehicles are revived in the 21st century. A great deal of demand for electric vehicles is developed and some do-it-yourself (DIY) engineers begin to share technical details for electric vehicle conversions. This paper shows a design process such as problem definition, design objective, design concept, prototype, and test. The process inspires many students of groups at our universities to put the theory of energy efficiency to the test, using innovative technology, reflective thinking apologetics, and creative ideas. Then, the concept of an electric vehicle is tested for driving in Shell Eco-marathon Asia Contest with the best energy consumption.
{"title":"The Innovative Design of the Electric Vehicles for Shell Eco-Marathon Asia Contest","authors":"N. Hoang, Hong–Phuc Vo, P. Le, Cao-Luong Tran, Nhat-Duy Trinh, Tran-Anh-Doi Pham","doi":"10.1109/GTSD54989.2022.9988988","DOIUrl":"https://doi.org/10.1109/GTSD54989.2022.9988988","url":null,"abstract":"Due to technological developments and redoubled focus on renewable energy, electric vehicles are revived in the 21st century. A great deal of demand for electric vehicles is developed and some do-it-yourself (DIY) engineers begin to share technical details for electric vehicle conversions. This paper shows a design process such as problem definition, design objective, design concept, prototype, and test. The process inspires many students of groups at our universities to put the theory of energy efficiency to the test, using innovative technology, reflective thinking apologetics, and creative ideas. Then, the concept of an electric vehicle is tested for driving in Shell Eco-marathon Asia Contest with the best energy consumption.","PeriodicalId":125445,"journal":{"name":"2022 6th International Conference on Green Technology and Sustainable Development (GTSD)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123338819","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-29DOI: 10.1109/GTSD54989.2022.9989162
Phu Thuong Luu Nguyen
in the automotive industry, controlling a gasoline engine is a very popular and widespread area of study. Moreover, in laboratory and academic institutions, using a computer control transaction may not be the ultimate idea because the required operating and calibration algorithms are predefined (only the manufacturer's accessible) without allowing for significant outside interference, and research lab services in the supply chain are outrageously costly. As a result, in this article, we introduce a minimal algorithm for starting and operating a petrol engine. The displayed solvent can currently be customized to work on commercially available efficiency ECUs at a reasonable cost. The algorithm presented here was created in LabVIEW. This paper describes the design of electronic fuel injection system behavior in diverse steady-state conditions as well as the method of determining injection pulse width and ignition timing using two virtual prediction models made with the software National Instruments LabVIEW and values taken from the actual experimental display. The comparison of simulation system results and experimental data can be used to determine whether the simulation system is accurate and reliable.
{"title":"A Study on Simulate Minimal Algorithm for Operating a Gasoline Engine Using LabView","authors":"Phu Thuong Luu Nguyen","doi":"10.1109/GTSD54989.2022.9989162","DOIUrl":"https://doi.org/10.1109/GTSD54989.2022.9989162","url":null,"abstract":"in the automotive industry, controlling a gasoline engine is a very popular and widespread area of study. Moreover, in laboratory and academic institutions, using a computer control transaction may not be the ultimate idea because the required operating and calibration algorithms are predefined (only the manufacturer's accessible) without allowing for significant outside interference, and research lab services in the supply chain are outrageously costly. As a result, in this article, we introduce a minimal algorithm for starting and operating a petrol engine. The displayed solvent can currently be customized to work on commercially available efficiency ECUs at a reasonable cost. The algorithm presented here was created in LabVIEW. This paper describes the design of electronic fuel injection system behavior in diverse steady-state conditions as well as the method of determining injection pulse width and ignition timing using two virtual prediction models made with the software National Instruments LabVIEW and values taken from the actual experimental display. The comparison of simulation system results and experimental data can be used to determine whether the simulation system is accurate and reliable.","PeriodicalId":125445,"journal":{"name":"2022 6th International Conference on Green Technology and Sustainable Development (GTSD)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115447082","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-29DOI: 10.1109/GTSD54989.2022.9989082
Nguyen Hai Phong, Dang Xuan Ba
In the automation control field, the model predictive controller is a modern controller with a simple control method, applied in the process of controlling the robot, motor,… In order to achieve desired quality, the control law is built based on the model datasets in the past, the present, and the future. The practical application of this method is hindered because it is so difficult to accurately determine model parameters. The paper proposes an advanced control method for position control of DC motors. The controller is combined from a neural network with an advanced model predictive controller instead of a classic predictive controller. In the first step, the technique employs a state-feedback control signal to stabilize the dynamical model of the system. Once the stable model has been obtained, in the second step, a proper neural network is designed with adaptive learning rules to learn the system behaviors. To realize the control objective, in the last step, a predictive control law is developed based on the online estimation results obtained from the network. The effectiveness of the proposed controller was carefully verified through in-depth simulation results.
{"title":"A State Feedback Model-Free Predictive Controller for DC Motors Using Neural Network","authors":"Nguyen Hai Phong, Dang Xuan Ba","doi":"10.1109/GTSD54989.2022.9989082","DOIUrl":"https://doi.org/10.1109/GTSD54989.2022.9989082","url":null,"abstract":"In the automation control field, the model predictive controller is a modern controller with a simple control method, applied in the process of controlling the robot, motor,… In order to achieve desired quality, the control law is built based on the model datasets in the past, the present, and the future. The practical application of this method is hindered because it is so difficult to accurately determine model parameters. The paper proposes an advanced control method for position control of DC motors. The controller is combined from a neural network with an advanced model predictive controller instead of a classic predictive controller. In the first step, the technique employs a state-feedback control signal to stabilize the dynamical model of the system. Once the stable model has been obtained, in the second step, a proper neural network is designed with adaptive learning rules to learn the system behaviors. To realize the control objective, in the last step, a predictive control law is developed based on the online estimation results obtained from the network. The effectiveness of the proposed controller was carefully verified through in-depth simulation results.","PeriodicalId":125445,"journal":{"name":"2022 6th International Conference on Green Technology and Sustainable Development (GTSD)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132611569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In 2019–2020, with encouragement from the Government in promoting the development of renewable energy sources, Vietnam has witnessed the rapid growth of solar and wind power sources. By the end of 2020, there were 16,700MW of solar power capacity connected to the national grid and accounted for 24 percent of the capacity of the whole national grid. These renewable energy sources are mainly concentrated in the Ninh Thuan and Binh Thuan provinces of Vietnam. The transmission power grid has not developed in time in this area to relieve all power sources, so there has been an overcapacity situation that has led to a reduction in the generating capacity of power plants, causing a waste of resources. In this paper we introduce renewable energy source storage technology based on pumped-storage hydroelectricity (PSH) technology, evaluating the role of a PSH plant in balancing the capacity of the power system when the system is connected to unstable power sources such as solar and wind power. Also, in this research, we propose Model Predictive Controller (MPC) built through LabView software to control the power balance on the grid. The results of the research show that the solution to building a PHS plant to optimize renewable energy sources in the central provinces of Vietnam is the right solution for Geographically favorable conditions, PHS also brings economic profit and stabilizes Vietnam's electricity system
{"title":"Renewable Energy Source Optimization Based on Pumped-Storage Hydroelectricity","authors":"Tran Ngoc Huy Thinh, Nguyen Huu Chau Minh, Lam Hoang Cat Tien, Võ Hoài Nam, Ly Phuc Lac","doi":"10.1109/GTSD54989.2022.9989292","DOIUrl":"https://doi.org/10.1109/GTSD54989.2022.9989292","url":null,"abstract":"In 2019–2020, with encouragement from the Government in promoting the development of renewable energy sources, Vietnam has witnessed the rapid growth of solar and wind power sources. By the end of 2020, there were 16,700MW of solar power capacity connected to the national grid and accounted for 24 percent of the capacity of the whole national grid. These renewable energy sources are mainly concentrated in the Ninh Thuan and Binh Thuan provinces of Vietnam. The transmission power grid has not developed in time in this area to relieve all power sources, so there has been an overcapacity situation that has led to a reduction in the generating capacity of power plants, causing a waste of resources. In this paper we introduce renewable energy source storage technology based on pumped-storage hydroelectricity (PSH) technology, evaluating the role of a PSH plant in balancing the capacity of the power system when the system is connected to unstable power sources such as solar and wind power. Also, in this research, we propose Model Predictive Controller (MPC) built through LabView software to control the power balance on the grid. The results of the research show that the solution to building a PHS plant to optimize renewable energy sources in the central provinces of Vietnam is the right solution for Geographically favorable conditions, PHS also brings economic profit and stabilizes Vietnam's electricity system","PeriodicalId":125445,"journal":{"name":"2022 6th International Conference on Green Technology and Sustainable Development (GTSD)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115855409","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-29DOI: 10.1109/GTSD54989.2022.9989182
V. Pham, Giang D. Ha, Quyet D. Nguyen, Thu Trang Nguyen
Reasonable selection of cross-sectional area of conductors for overhead transmission lines has great effects on reaping economic benefits during the entire project's life cycle. Economic current density is an essential reference for the selection of conductor size. The traditional economic current density put forward in the 1950s and widely used in the electric power industry in Vietnam takes no account of the time value of money and assumes constant values of the marginal cost of electricity and wire price. These prices, however, can profoundly affect economic current density values. Therefore, these values need to be updated. This paper proposes a novel methodology based on life cycle cost (LCC) to scientifically and comprehensively determine economic current density values, complying with the current market economy conditions. The total LCC can be expressed as the sum of the initial capital investment cost (CIC) and the total cost of operation (TCO), comprising the cost of maintenance and electrical energy loss. Analytical function of CIC relating to conductor cross-sectional area and nominal voltage is obtained using available data from previously constructed overhead lines and regression analysis. The electrical energy loss is determined using equivalent hours of loss, which in turn depends on equivalent hours of utilization. Analytical expression of equivalent hours of loss with respect to equivalent hours of utilization is attained using the regression method from historical load data. Finally, a practical case study of a 110 kV overhead line in Vietnam is leveraged to validate the viability and effectiveness of the proposed approach. The calculation results show that the life cycle cost using the economic current density developed in this work is lower than that from the Vietnam standard.
{"title":"Reassessment of Economic Current Density based on Life Cycle Cost under Market Economy Condition: a Case Study in Vietnam","authors":"V. Pham, Giang D. Ha, Quyet D. Nguyen, Thu Trang Nguyen","doi":"10.1109/GTSD54989.2022.9989182","DOIUrl":"https://doi.org/10.1109/GTSD54989.2022.9989182","url":null,"abstract":"Reasonable selection of cross-sectional area of conductors for overhead transmission lines has great effects on reaping economic benefits during the entire project's life cycle. Economic current density is an essential reference for the selection of conductor size. The traditional economic current density put forward in the 1950s and widely used in the electric power industry in Vietnam takes no account of the time value of money and assumes constant values of the marginal cost of electricity and wire price. These prices, however, can profoundly affect economic current density values. Therefore, these values need to be updated. This paper proposes a novel methodology based on life cycle cost (LCC) to scientifically and comprehensively determine economic current density values, complying with the current market economy conditions. The total LCC can be expressed as the sum of the initial capital investment cost (CIC) and the total cost of operation (TCO), comprising the cost of maintenance and electrical energy loss. Analytical function of CIC relating to conductor cross-sectional area and nominal voltage is obtained using available data from previously constructed overhead lines and regression analysis. The electrical energy loss is determined using equivalent hours of loss, which in turn depends on equivalent hours of utilization. Analytical expression of equivalent hours of loss with respect to equivalent hours of utilization is attained using the regression method from historical load data. Finally, a practical case study of a 110 kV overhead line in Vietnam is leveraged to validate the viability and effectiveness of the proposed approach. The calculation results show that the life cycle cost using the economic current density developed in this work is lower than that from the Vietnam standard.","PeriodicalId":125445,"journal":{"name":"2022 6th International Conference on Green Technology and Sustainable Development (GTSD)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123426905","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-29DOI: 10.1109/GTSD54989.2022.9989027
Thanh-Hoan Nguyen, Q. Pham, Vu-Thuy Nguyen, V. Trương, H. Nguyen, D. Truong
Power load forecasting is an important issue in a microgrid (MG) energy management. Accurate load forecasting is urgently required for effective power management for MG. This paper proposes a new method for short-term load forecasting (STLF). This method uses both long and short data series provided for a Wavenet-based model inspired by a Long Short-Term Memory (LSTM), to forecast hourly load demand. To increase the accuracy of the prediction model, this study used the Harris Hawks Optimization (HHO) algorithm to include in the calculation in the Wavenet network. In order to demonstrate the effectiveness of the model, we work with the load data set of an MG model belonging to the Ho Chi Minh City power grid. The forecasting model is compared with the previous forecasting models. The results show that our proposed model outperforms other deep learning-based models in terms of root mean square error (RMSE) and mean absolute percentage error (MAPE).
{"title":"Hybrid HHO-Wavenet Model Applies in Short-term Load Forecasting for Microgrid System","authors":"Thanh-Hoan Nguyen, Q. Pham, Vu-Thuy Nguyen, V. Trương, H. Nguyen, D. Truong","doi":"10.1109/GTSD54989.2022.9989027","DOIUrl":"https://doi.org/10.1109/GTSD54989.2022.9989027","url":null,"abstract":"Power load forecasting is an important issue in a microgrid (MG) energy management. Accurate load forecasting is urgently required for effective power management for MG. This paper proposes a new method for short-term load forecasting (STLF). This method uses both long and short data series provided for a Wavenet-based model inspired by a Long Short-Term Memory (LSTM), to forecast hourly load demand. To increase the accuracy of the prediction model, this study used the Harris Hawks Optimization (HHO) algorithm to include in the calculation in the Wavenet network. In order to demonstrate the effectiveness of the model, we work with the load data set of an MG model belonging to the Ho Chi Minh City power grid. The forecasting model is compared with the previous forecasting models. The results show that our proposed model outperforms other deep learning-based models in terms of root mean square error (RMSE) and mean absolute percentage error (MAPE).","PeriodicalId":125445,"journal":{"name":"2022 6th International Conference on Green Technology and Sustainable Development (GTSD)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127564132","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-29DOI: 10.1109/GTSD54989.2022.9988766
Tuan-Tu Huynh, D. Pham, Nguyen Thanh Son
This paper combines a BELC (brain emotional learning controller) and a CMAC (cerebellar model articulation control) to form a mixed neural network named as the FCBC (brain emotional learning cerebellar model articulation controller) for chaos synchronization and image secure communication. First, a master-slave 3D Satellite chaotic system is illustrated. Then, its application is applied to image secure communication. A color original image is added to one of the three states of the chaotic system and it can be used as the encoded carrier signal at the transmitter, then the synchronization using the FCBC is used for the decryption at the receiver, so the decoded image is received and the original image can be recovered. Comparisons of the results using different methods are given to show their effectiveness.
{"title":"Image Secure Communication Using BELC-CMAC and Chaos Synchronization","authors":"Tuan-Tu Huynh, D. Pham, Nguyen Thanh Son","doi":"10.1109/GTSD54989.2022.9988766","DOIUrl":"https://doi.org/10.1109/GTSD54989.2022.9988766","url":null,"abstract":"This paper combines a BELC (brain emotional learning controller) and a CMAC (cerebellar model articulation control) to form a mixed neural network named as the FCBC (brain emotional learning cerebellar model articulation controller) for chaos synchronization and image secure communication. First, a master-slave 3D Satellite chaotic system is illustrated. Then, its application is applied to image secure communication. A color original image is added to one of the three states of the chaotic system and it can be used as the encoded carrier signal at the transmitter, then the synchronization using the FCBC is used for the decryption at the receiver, so the decoded image is received and the original image can be recovered. Comparisons of the results using different methods are given to show their effectiveness.","PeriodicalId":125445,"journal":{"name":"2022 6th International Conference on Green Technology and Sustainable Development (GTSD)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127730416","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-29DOI: 10.1109/GTSD54989.2022.9988756
Quynh Anh Tran, Quang Hung Dang, Tung Le, Huy-Tien Nguyen, T. Le
Air pollution has been a growing concern in the twenty-first century, affecting the surrounding environment and public health. The previous studies have recently undertaken significant research on air pollution and air quality monitoring. Unfortunately, this area continues to be challenged by unresolved issues. This paper proposes an IoT-based Air Quality Monitoring and Forecasting System to monitor and predict air pollution for a specific area based on various pollution factors. Using Arduino UNO R3 and various low-cost sensors, our IoT system can collect and monitor pollutants, such as PM2.5, CO2, CO, as well as temperature and humidity. The air quality data was collected for several months. To overcome the problems of instability of low-cost devices in monitoring, machine learning (ML) algorithms, such as K-Nearest-Neighbour (KNN), Expectation-Maximization (EM), Multiple Imputation by Chained Equations (MICE), and Autoregressive-Moving-Average (ARMA), are applied to address missing data and outliers due to technical issues. The KNN model outperformed all others in terms of RMSE, MSE, MAE, R-squared, and execution time. Then, Autoregressive Integrated Moving Average (ARIMA) and Long Short-Term Memory (LSTM) algorithms are applied to predict future air quality. The result shows that our system can predict the air quality factors over the next hour with the highest accuracy at 96 %. Finally, a web interface was created to monitor and forecast air quality in real-time.
空气污染在21世纪日益受到关注，影响着周围环境和公众健康。以往的研究最近在空气污染和空气质量监测方面进行了重要的研究。不幸的是，这一领域继续受到未解决问题的挑战。本文提出了一种基于物联网的空气质量监测预报系统，基于各种污染因素对特定区域的空气污染进行监测和预测。利用Arduino UNO R3和各种低成本传感器，我们的物联网系统可以收集和监测污染物，如PM2.5, CO2, CO，以及温度和湿度。空气质量数据收集了几个月。为了克服低成本设备在监测中的不稳定性问题，机器学习(ML)算法，如K-Nearest-Neighbour (KNN)， Expectation-Maximization (EM)， Multiple Imputation by Chained Equations (MICE)和autoregresregression - moving - average (ARMA)，被应用于解决由于技术问题而导致的数据缺失和异常值。KNN模型在RMSE、MSE、MAE、r平方和执行时间方面优于所有其他模型。然后，应用自回归综合移动平均(ARIMA)和长短期记忆(LSTM)算法对未来空气质量进行预测。结果表明，该系统对未来一小时的空气质量因子预测准确率最高，达到96%。最后，建立了一个实时监测和预报空气质量的网络界面。
{"title":"Air Quality Monitoring and Forecasting System using IoT and Machine Learning Techniques","authors":"Quynh Anh Tran, Quang Hung Dang, Tung Le, Huy-Tien Nguyen, T. Le","doi":"10.1109/GTSD54989.2022.9988756","DOIUrl":"https://doi.org/10.1109/GTSD54989.2022.9988756","url":null,"abstract":"Air pollution has been a growing concern in the twenty-first century, affecting the surrounding environment and public health. The previous studies have recently undertaken significant research on air pollution and air quality monitoring. Unfortunately, this area continues to be challenged by unresolved issues. This paper proposes an IoT-based Air Quality Monitoring and Forecasting System to monitor and predict air pollution for a specific area based on various pollution factors. Using Arduino UNO R3 and various low-cost sensors, our IoT system can collect and monitor pollutants, such as PM2.5, CO2, CO, as well as temperature and humidity. The air quality data was collected for several months. To overcome the problems of instability of low-cost devices in monitoring, machine learning (ML) algorithms, such as K-Nearest-Neighbour (KNN), Expectation-Maximization (EM), Multiple Imputation by Chained Equations (MICE), and Autoregressive-Moving-Average (ARMA), are applied to address missing data and outliers due to technical issues. The KNN model outperformed all others in terms of RMSE, MSE, MAE, R-squared, and execution time. Then, Autoregressive Integrated Moving Average (ARIMA) and Long Short-Term Memory (LSTM) algorithms are applied to predict future air quality. The result shows that our system can predict the air quality factors over the next hour with the highest accuracy at 96 %. Finally, a web interface was created to monitor and forecast air quality in real-time.","PeriodicalId":125445,"journal":{"name":"2022 6th International Conference on Green Technology and Sustainable Development (GTSD)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124587286","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-29DOI: 10.1109/GTSD54989.2022.9989043
Nguyen Tran Minh Nguyet, Dang Xuan Ba
In robotic control engineering, the conventional computed-torque control algorithm is a simple method to control robots achieving the desired quality by using model parameters including internal dynamics and external disturbances to establish the control law. Practical applicability of this method is normally low since it is difficult to accurately determine such the parameters. In this paper, we propose an intelligent computed-torque control approach for tracking control problems of robotic systems. A neural network structure is first employed for online estimation of the system dynamics in which the learning process is stimulated by a nonlinear mapping function of the control error. From there, the computed-torque control signal is then synthesized using the estimation result and a proportional-derivative control term to result in expected control performance. Stability of the closed-loop system is maintained by Lyapunov analyses. Effectiveness of the proposed control method is extensively verified through intensive simulation results.
{"title":"A Computed Torque Controller for Robotic Manipulators Using Nonlinear Neural Network","authors":"Nguyen Tran Minh Nguyet, Dang Xuan Ba","doi":"10.1109/GTSD54989.2022.9989043","DOIUrl":"https://doi.org/10.1109/GTSD54989.2022.9989043","url":null,"abstract":"In robotic control engineering, the conventional computed-torque control algorithm is a simple method to control robots achieving the desired quality by using model parameters including internal dynamics and external disturbances to establish the control law. Practical applicability of this method is normally low since it is difficult to accurately determine such the parameters. In this paper, we propose an intelligent computed-torque control approach for tracking control problems of robotic systems. A neural network structure is first employed for online estimation of the system dynamics in which the learning process is stimulated by a nonlinear mapping function of the control error. From there, the computed-torque control signal is then synthesized using the estimation result and a proportional-derivative control term to result in expected control performance. Stability of the closed-loop system is maintained by Lyapunov analyses. Effectiveness of the proposed control method is extensively verified through intensive simulation results.","PeriodicalId":125445,"journal":{"name":"2022 6th International Conference on Green Technology and Sustainable Development (GTSD)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117220395","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：