Pub Date : 2020-11-02DOI: 10.1109/IGESSC50231.2020.9285132
Parinaz Farajiparvar, Nima Hoseinzadeh, Lee D. Han, A. Hedayatipour
Traffic speed prediction is an ongoing challenge for researchers, transportation agencies, and navigation applications. Involving real-world speed data makes the prediction complex and dynamic. The stochastic nature of traffic makes predictions using traditional statistical methods unsatisfying in terms of accuracy and performance. Recently, deep learning methods have gained more attention to capture this chaotic characteristic. This study conducts an encoder-decoder sequence to sequence learning manner and WaveNet with a side information model and compares the results with Autoregressive Integrated Moving Average. Using Waze crowdsourced speed data collected from 31 segments of Interstate 40 (I-40) in Tennessee, the proposed algorithms are trained and tested for short- and long term speed prediction (time steps from 5-minutes to 2-hours). Our experimental results demonstrate the WaveNet model with side information achieves the best performance with MAPE 4.40% for 5-minuets and MAPE 5.58% for 2-hours prediction.
{"title":"Deep Learning Techniques for Traffic Speed Forecasting with Side Information","authors":"Parinaz Farajiparvar, Nima Hoseinzadeh, Lee D. Han, A. Hedayatipour","doi":"10.1109/IGESSC50231.2020.9285132","DOIUrl":"https://doi.org/10.1109/IGESSC50231.2020.9285132","url":null,"abstract":"Traffic speed prediction is an ongoing challenge for researchers, transportation agencies, and navigation applications. Involving real-world speed data makes the prediction complex and dynamic. The stochastic nature of traffic makes predictions using traditional statistical methods unsatisfying in terms of accuracy and performance. Recently, deep learning methods have gained more attention to capture this chaotic characteristic. This study conducts an encoder-decoder sequence to sequence learning manner and WaveNet with a side information model and compares the results with Autoregressive Integrated Moving Average. Using Waze crowdsourced speed data collected from 31 segments of Interstate 40 (I-40) in Tennessee, the proposed algorithms are trained and tested for short- and long term speed prediction (time steps from 5-minutes to 2-hours). Our experimental results demonstrate the WaveNet model with side information achieves the best performance with MAPE 4.40% for 5-minuets and MAPE 5.58% for 2-hours prediction.","PeriodicalId":437709,"journal":{"name":"2020 IEEE Green Energy and Smart Systems Conference (IGESSC)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116487720","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 : 2020-11-02DOI: 10.1109/IGESSC50231.2020.9285006
R. McCann, Mireille Tankoua Sandjong
This paper considers the impact of Industry 4.0 technologies in streamlining global supply chains for the sourcing of electric motors while meeting the rapidly changing demands for new product features and customization. Methods of comparing these new technologies to conventional methods has not been well established. This research presents a method using timed Petri nets to account for design and process uncertainty in the manufacturing of electric motors. The results of a case study for an induction motor rotor cage supports the cost effectiveness in adopting Industry 4.0 manufacturing practices that is market responsive and minimizes waste in the product lifecycle. A case study of an induction motor cage rotor is presented that indicates the benefits of the proposed design and manufacturing processes.
{"title":"Timed Petri Nets for Industry 4.0 Electric Motor Manufacturing","authors":"R. McCann, Mireille Tankoua Sandjong","doi":"10.1109/IGESSC50231.2020.9285006","DOIUrl":"https://doi.org/10.1109/IGESSC50231.2020.9285006","url":null,"abstract":"This paper considers the impact of Industry 4.0 technologies in streamlining global supply chains for the sourcing of electric motors while meeting the rapidly changing demands for new product features and customization. Methods of comparing these new technologies to conventional methods has not been well established. This research presents a method using timed Petri nets to account for design and process uncertainty in the manufacturing of electric motors. The results of a case study for an induction motor rotor cage supports the cost effectiveness in adopting Industry 4.0 manufacturing practices that is market responsive and minimizes waste in the product lifecycle. A case study of an induction motor cage rotor is presented that indicates the benefits of the proposed design and manufacturing processes.","PeriodicalId":437709,"journal":{"name":"2020 IEEE Green Energy and Smart Systems Conference (IGESSC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129726899","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 : 2020-11-02DOI: 10.1109/IGESSC50231.2020.9284981
M. Arifujjaman, R. Salas, A. Johnson, Austen DLima, J. Araiza, J. Mauzey, J. Castaneda
The integration of Distributed Energy Resources (DER) into the existing Southern California Edison (SCE) grid has evolved rapidly to accommodate California’s Green House Gas (GHG) reduction goals. The Photovoltaic (PV) systems remain a dominant choice among other DERs and requires an inverter that historically exhibits non-linear characteristics. This criterion underscores the need for a comprehensive PV-inverter model and a sophisticated test bench for demonstrating the operational dynamics and protection functionalities of the system. Given this, a novel impedance-based mathematical modeling is proposed for the PV and inverter. The development of an advanced Hardware-in-the-Loop (HIL) testbed at SCE’s DER Laboratory has described interfaces commercial Rule 21 and IEEE 1547 compliant inverters with the traditional induction and synchronous generator based generations in Real Time Digital Simulator (RTDS) to replicate the simulated model of a medium voltage distribution circuit. Some preliminary simulation and experimentation results yield tremendous agreement and confirm the validity of the modeling approach. The future simulation and demonstration plans are exposed, which show the value of the model and testbed and this contributes evidence to other utilities to further model and develop a testbed for performance evaluations of DER systems.
{"title":"Modeling and Development of a HIL Testbed for DER Dynamics Integration Demonstration","authors":"M. Arifujjaman, R. Salas, A. Johnson, Austen DLima, J. Araiza, J. Mauzey, J. Castaneda","doi":"10.1109/IGESSC50231.2020.9284981","DOIUrl":"https://doi.org/10.1109/IGESSC50231.2020.9284981","url":null,"abstract":"The integration of Distributed Energy Resources (DER) into the existing Southern California Edison (SCE) grid has evolved rapidly to accommodate California’s Green House Gas (GHG) reduction goals. The Photovoltaic (PV) systems remain a dominant choice among other DERs and requires an inverter that historically exhibits non-linear characteristics. This criterion underscores the need for a comprehensive PV-inverter model and a sophisticated test bench for demonstrating the operational dynamics and protection functionalities of the system. Given this, a novel impedance-based mathematical modeling is proposed for the PV and inverter. The development of an advanced Hardware-in-the-Loop (HIL) testbed at SCE’s DER Laboratory has described interfaces commercial Rule 21 and IEEE 1547 compliant inverters with the traditional induction and synchronous generator based generations in Real Time Digital Simulator (RTDS) to replicate the simulated model of a medium voltage distribution circuit. Some preliminary simulation and experimentation results yield tremendous agreement and confirm the validity of the modeling approach. The future simulation and demonstration plans are exposed, which show the value of the model and testbed and this contributes evidence to other utilities to further model and develop a testbed for performance evaluations of DER systems.","PeriodicalId":437709,"journal":{"name":"2020 IEEE Green Energy and Smart Systems Conference (IGESSC)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114751978","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 : 2020-11-02DOI: 10.1109/IGESSC50231.2020.9285157
T. Nguyen
This paper describes innovative frameworks and associated mathematical models using Machine Learning and Artificial Intelligent (ML-AI) technology to address signal distortions caused by the satellite transponder (TXDER) and related operational conditions. The operating conditions include unknown Input Power Back-Off (IPBO) and unknown TXDER operating temperature due to satellite exposure to the space environment. The paper also presents and discusses an End-to-End Satellite System and Mathematical Model (E2E-SSM2) that can be used for generating training data and demonstrating of the proposed ML-AI frameworks.
{"title":"Advanced Mathematical Modeling of Machine Learning and Artificial Intelligent Addressing Satellite Transponder Distortions","authors":"T. Nguyen","doi":"10.1109/IGESSC50231.2020.9285157","DOIUrl":"https://doi.org/10.1109/IGESSC50231.2020.9285157","url":null,"abstract":"This paper describes innovative frameworks and associated mathematical models using Machine Learning and Artificial Intelligent (ML-AI) technology to address signal distortions caused by the satellite transponder (TXDER) and related operational conditions. The operating conditions include unknown Input Power Back-Off (IPBO) and unknown TXDER operating temperature due to satellite exposure to the space environment. The paper also presents and discusses an End-to-End Satellite System and Mathematical Model (E2E-SSM2) that can be used for generating training data and demonstrating of the proposed ML-AI frameworks.","PeriodicalId":437709,"journal":{"name":"2020 IEEE Green Energy and Smart Systems Conference (IGESSC)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126958203","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 : 2020-11-02DOI: 10.1109/IGESSC50231.2020.9285004
Héctor F. Chinchero, J. Marcos Alonso, Ortiz T. Hugo
This paper presents a review of Smart LED Lighting Systems applied to Smart Buildings. The study is focused on drivers, protocols, technologies, communication networks and applications. An extended overview of the methodologies used for LED Lighting Control in Smart Buildings is addressed. It also presents an integrated architecture in order to achieve the necessary services and control methodologies for Intelligent Building Energy Management System (IBEMS) for LED Lightings Systems in Smart Buildings.
{"title":"A Review on Smart LED Lighting Systems","authors":"Héctor F. Chinchero, J. Marcos Alonso, Ortiz T. Hugo","doi":"10.1109/IGESSC50231.2020.9285004","DOIUrl":"https://doi.org/10.1109/IGESSC50231.2020.9285004","url":null,"abstract":"This paper presents a review of Smart LED Lighting Systems applied to Smart Buildings. The study is focused on drivers, protocols, technologies, communication networks and applications. An extended overview of the methodologies used for LED Lighting Control in Smart Buildings is addressed. It also presents an integrated architecture in order to achieve the necessary services and control methodologies for Intelligent Building Energy Management System (IBEMS) for LED Lightings Systems in Smart Buildings.","PeriodicalId":437709,"journal":{"name":"2020 IEEE Green Energy and Smart Systems Conference (IGESSC)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114770555","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 : 2020-11-02DOI: 10.1109/IGESSC50231.2020.9285102
Yu-Jen Ku, Sandalika Sapra, S. Baidya, S. Dey
Renewable energy (RE) is a promising solution to save grid power in mobile edge computing (MEC) systems and thus reducing the carbon footprints. However, to effectively operate the RE-based MEC system, a method for predicting the state of energy (SoE) in the battery is essential, not only to prevent the battery from over-charging or over-discharging, but also allowing the MEC applications to adjust their loads in advance based on the energy availability. In this work, we consider RE-powered MEC systems at the Road-side Unit (RSU) and focus on predicting its battery's SoE by using machine learning technique. We developed a real-world RE-powered RSU testbed consisting of edge computing devices, small cell base station, and solar as well as wind power generators. By operating RE-powered RSU for serving real-world computation task offloading demands, we collect the corresponding data sequences of battery's SoE and other observable parameters of the MEC systems that impact the SoE. Using a variant of Long Short-term Memory (LSTM) model with additional convolutional layers, we form a CNN-LSTM model which can predict the SoE accurately with very low prediction error. Our results show that CNN-LSTM outperforms other Recurrent Neural Networks (RNN) based models for predicting intra-hour and hour-ahead SoE.
{"title":"State of Energy Prediction in Renewable Energy-driven Mobile Edge Computing using CNN-LSTM Networks","authors":"Yu-Jen Ku, Sandalika Sapra, S. Baidya, S. Dey","doi":"10.1109/IGESSC50231.2020.9285102","DOIUrl":"https://doi.org/10.1109/IGESSC50231.2020.9285102","url":null,"abstract":"Renewable energy (RE) is a promising solution to save grid power in mobile edge computing (MEC) systems and thus reducing the carbon footprints. However, to effectively operate the RE-based MEC system, a method for predicting the state of energy (SoE) in the battery is essential, not only to prevent the battery from over-charging or over-discharging, but also allowing the MEC applications to adjust their loads in advance based on the energy availability. In this work, we consider RE-powered MEC systems at the Road-side Unit (RSU) and focus on predicting its battery's SoE by using machine learning technique. We developed a real-world RE-powered RSU testbed consisting of edge computing devices, small cell base station, and solar as well as wind power generators. By operating RE-powered RSU for serving real-world computation task offloading demands, we collect the corresponding data sequences of battery's SoE and other observable parameters of the MEC systems that impact the SoE. Using a variant of Long Short-term Memory (LSTM) model with additional convolutional layers, we form a CNN-LSTM model which can predict the SoE accurately with very low prediction error. Our results show that CNN-LSTM outperforms other Recurrent Neural Networks (RNN) based models for predicting intra-hour and hour-ahead SoE.","PeriodicalId":437709,"journal":{"name":"2020 IEEE Green Energy and Smart Systems Conference (IGESSC)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126856304","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 : 2020-10-05DOI: 10.1109/IGESSC50231.2020.9285029
Seyed Mohammad Sajjadi Kalajahi, Sina Baghali, T. Khalili, B. Mohammadi-ivatloo, A. Bidram
In the recent years, due to the economic and environmental requirements, the use of distributed generations (DGs) has increased. If DGs have the optimal size and are located at the optimal locations, they are capable of enhancing the voltage profile and reducing the power loss. This paper proposes a new approach to obtain the optimal location and size of DGs. To this end, exchange market algorithm (EMA) is offered to find the optimal size and location of DGs subject to minimizing loss, increasing voltage profile, and improving voltage stability in the distribution systems. The effectiveness of the proposed approach is verified on both 33- and 69-bus IEEE standard systems.
{"title":"Multi-Objective Approach for Optimal Size and Location of DGs in Distribution Systems","authors":"Seyed Mohammad Sajjadi Kalajahi, Sina Baghali, T. Khalili, B. Mohammadi-ivatloo, A. Bidram","doi":"10.1109/IGESSC50231.2020.9285029","DOIUrl":"https://doi.org/10.1109/IGESSC50231.2020.9285029","url":null,"abstract":"In the recent years, due to the economic and environmental requirements, the use of distributed generations (DGs) has increased. If DGs have the optimal size and are located at the optimal locations, they are capable of enhancing the voltage profile and reducing the power loss. This paper proposes a new approach to obtain the optimal location and size of DGs. To this end, exchange market algorithm (EMA) is offered to find the optimal size and location of DGs subject to minimizing loss, increasing voltage profile, and improving voltage stability in the distribution systems. The effectiveness of the proposed approach is verified on both 33- and 69-bus IEEE standard systems.","PeriodicalId":437709,"journal":{"name":"2020 IEEE Green Energy and Smart Systems Conference (IGESSC)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122120604","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：