Pub Date : 2020-07-15DOI: 10.1109/IISA50023.2020.9284415
Apostolos Glenis
Time series classification is an important problem since data from sensors become more prevalent over time. In addition most of the data arrive in the form of a stream and thus have to be handled with the limitation that apply to streaming environments (low latency,low memory footprint). In this paper we address the problem of scalable time series classification on both Batch and Streaming environments. More specifically we implemented two state-of-the-art time series classification on top of Apache Spark and we adapted one of them for streaming applications. We evaluated our algorithms against two open datasets on a 10-node cluster. The algorithms we implemented scaled gracefully both in the batch and streaming environment.
{"title":"Scalable Time Series Classification in streaming and batch environments on Apache Spark","authors":"Apostolos Glenis","doi":"10.1109/IISA50023.2020.9284415","DOIUrl":"https://doi.org/10.1109/IISA50023.2020.9284415","url":null,"abstract":"Time series classification is an important problem since data from sensors become more prevalent over time. In addition most of the data arrive in the form of a stream and thus have to be handled with the limitation that apply to streaming environments (low latency,low memory footprint). In this paper we address the problem of scalable time series classification on both Batch and Streaming environments. More specifically we implemented two state-of-the-art time series classification on top of Apache Spark and we adapted one of them for streaming applications. We evaluated our algorithms against two open datasets on a 10-node cluster. The algorithms we implemented scaled gracefully both in the batch and streaming environment.","PeriodicalId":109238,"journal":{"name":"2020 11th International Conference on Information, Intelligence, Systems and Applications (IISA","volume":"158 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133622276","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 : 2020-07-15DOI: 10.1109/IISA50023.2020.9284337
Ioannis Daramouskas, I. Perikos, I. Hatzilygeroudis, V. Lappas, Vasilios Kostopoulos
Over the last decade, drones and UAVs have attracted great research interest mainly due to their abilities and their potential to be used in various applications and domains. One of the most important operations that Drones must perform efficiently concerns the navigation in real-world environments. This typically includes the ability of path planning and obstacle avoidance. It is crucial that drones have the ability to perform automatically and efficiently procedures related to the avoidance of objects while navigating in environments. In this work, we present a methodology for assisting a drone to navigate in unknown environments and avoid obstacles. The methodology is based on a training-by-human concept where the drone learns how to avoid obstacles by example cases that are provided to it and it is trained on them. The results are quite interesting and indicate that the methodology is efficient and can assist drones and robotics systems to learn how to navigate and avoid obstacles in environments.
{"title":"A Methodology For Drones to Learn How to Navigate And Avoid Obstacles Using Decision Trees","authors":"Ioannis Daramouskas, I. Perikos, I. Hatzilygeroudis, V. Lappas, Vasilios Kostopoulos","doi":"10.1109/IISA50023.2020.9284337","DOIUrl":"https://doi.org/10.1109/IISA50023.2020.9284337","url":null,"abstract":"Over the last decade, drones and UAVs have attracted great research interest mainly due to their abilities and their potential to be used in various applications and domains. One of the most important operations that Drones must perform efficiently concerns the navigation in real-world environments. This typically includes the ability of path planning and obstacle avoidance. It is crucial that drones have the ability to perform automatically and efficiently procedures related to the avoidance of objects while navigating in environments. In this work, we present a methodology for assisting a drone to navigate in unknown environments and avoid obstacles. The methodology is based on a training-by-human concept where the drone learns how to avoid obstacles by example cases that are provided to it and it is trained on them. The results are quite interesting and indicate that the methodology is efficient and can assist drones and robotics systems to learn how to navigate and avoid obstacles in environments.","PeriodicalId":109238,"journal":{"name":"2020 11th International Conference on Information, Intelligence, Systems and Applications (IISA","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127044093","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 : 2020-07-15DOI: 10.1109/IISA50023.2020.9284385
Dimitrios Ntardas, Alexandros Tzanetos, G. Dounias
Optimal resource allocation is a challenging problem which is faced by Project Managers. In large projects, where multiple resources have to be properly allocated taking into consideration the total cost of project and the time needed to be completed, the optimization problem becomes even more difficult. Therefore, intelligent techniques have been widely used to cope with such demanding problems. This study applies a nature-inspired intelligent algorithm, i.e. Sonar Inspired Optimization (SIO), to face the Resource Leveling problem of a real world project, i.e. a High Voltage Alternating Current Submarine Link Terminal Station. The specific application domain is a NP-hard optimization problem as it can receive a very large number of possible solutions. Furthermore, a hybrid scheme of this algorithm with Simulated Annealing (SIO-SA) is used to improve the performance of SIO. Comparative results show that both approaches (SIO and SIO-SA) perform almost equally well.
{"title":"Intelligent Nature-Inspired Approaches for Optimal Resource Levelling in a High Voltage Alternating Current Submarine Link Terminal Station Project","authors":"Dimitrios Ntardas, Alexandros Tzanetos, G. Dounias","doi":"10.1109/IISA50023.2020.9284385","DOIUrl":"https://doi.org/10.1109/IISA50023.2020.9284385","url":null,"abstract":"Optimal resource allocation is a challenging problem which is faced by Project Managers. In large projects, where multiple resources have to be properly allocated taking into consideration the total cost of project and the time needed to be completed, the optimization problem becomes even more difficult. Therefore, intelligent techniques have been widely used to cope with such demanding problems. This study applies a nature-inspired intelligent algorithm, i.e. Sonar Inspired Optimization (SIO), to face the Resource Leveling problem of a real world project, i.e. a High Voltage Alternating Current Submarine Link Terminal Station. The specific application domain is a NP-hard optimization problem as it can receive a very large number of possible solutions. Furthermore, a hybrid scheme of this algorithm with Simulated Annealing (SIO-SA) is used to improve the performance of SIO. Comparative results show that both approaches (SIO and SIO-SA) perform almost equally well.","PeriodicalId":109238,"journal":{"name":"2020 11th International Conference on Information, Intelligence, Systems and Applications (IISA","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127362677","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 : 2020-07-15DOI: 10.1109/IISA50023.2020.9284349
A. Ebada, Samir Abdelrazek, I. El-Henawy
The healthcare big data including medical history, Physician reports, prescription, parents and family historical diseases, laboratories, and scan reports can help in disease detection and prediction process. The article presents an overview of the recent technologies and methods in the medical area to get the benefits of cloud systems, data science, and machine algorithms. The paper presents also how can current technologies like Spark can be used to employ streaming data for healthcare applications. Big medical data analysis is a big area of research and the article shows some advanced analysis impact on disease detection and predictions. The proposed system employed an optimized Support Vector Machine classifier with performing the parameter tuning to increase the accuracy of the classification, and efficiency. The proposed system uses wearable devices and sensors to get the data of heart rate, diabetes, and blood pressure of the users to analyze and predict heart diseases with the help of the user healthcare profile on the cloud system.
{"title":"Applying Cloud Based Machine Learning on Biosensors Streaming Data for Health Status Prediction","authors":"A. Ebada, Samir Abdelrazek, I. El-Henawy","doi":"10.1109/IISA50023.2020.9284349","DOIUrl":"https://doi.org/10.1109/IISA50023.2020.9284349","url":null,"abstract":"The healthcare big data including medical history, Physician reports, prescription, parents and family historical diseases, laboratories, and scan reports can help in disease detection and prediction process. The article presents an overview of the recent technologies and methods in the medical area to get the benefits of cloud systems, data science, and machine algorithms. The paper presents also how can current technologies like Spark can be used to employ streaming data for healthcare applications. Big medical data analysis is a big area of research and the article shows some advanced analysis impact on disease detection and predictions. The proposed system employed an optimized Support Vector Machine classifier with performing the parameter tuning to increase the accuracy of the classification, and efficiency. The proposed system uses wearable devices and sensors to get the data of heart rate, diabetes, and blood pressure of the users to analyze and predict heart diseases with the help of the user healthcare profile on the cloud system.","PeriodicalId":109238,"journal":{"name":"2020 11th International Conference on Information, Intelligence, Systems and Applications (IISA","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129041023","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 : 2020-07-15DOI: 10.1109/IISA50023.2020.9284361
Michail Katsivelakis, D. Bargiotas, Aspassia Daskalopulu
Renewable energy systems, especially wind turbines and farms are nowadays integrated rapidly into power systems and smart grids. Several technical challenges arise due to penetration of wind energy into power networks and systems. In order for system stability and steady state operation to be ensured in power systems and electric networks, steady and dynamic analysis are necessary. We study a standard IEEE 9 bus test system, which is integrated with a Doubly-Fed Induction Generator wind farm, aiming to examine its behaviour during disturbances. Steady state and transient stability configurations are proposed in order to analyze the system described. A threephase fault is suddenly applied to a load bus. Moreover, critical fault clearing time is identified for the corresponding three-phase fault and results show the maximum time for system stability during a disturbance. The influence of transient stability, including voltage stability, angle stability, active power and reactive power is discussed and research results become important for the smooth integration of wind farms into networks. This study is conducted with the help of PSS/E 34 software simulation tool by Siemens.
{"title":"Transient Stability Analysis in Power Systems Integrated with a Doubly-Fed Induction Generator Wind Farm","authors":"Michail Katsivelakis, D. Bargiotas, Aspassia Daskalopulu","doi":"10.1109/IISA50023.2020.9284361","DOIUrl":"https://doi.org/10.1109/IISA50023.2020.9284361","url":null,"abstract":"Renewable energy systems, especially wind turbines and farms are nowadays integrated rapidly into power systems and smart grids. Several technical challenges arise due to penetration of wind energy into power networks and systems. In order for system stability and steady state operation to be ensured in power systems and electric networks, steady and dynamic analysis are necessary. We study a standard IEEE 9 bus test system, which is integrated with a Doubly-Fed Induction Generator wind farm, aiming to examine its behaviour during disturbances. Steady state and transient stability configurations are proposed in order to analyze the system described. A threephase fault is suddenly applied to a load bus. Moreover, critical fault clearing time is identified for the corresponding three-phase fault and results show the maximum time for system stability during a disturbance. The influence of transient stability, including voltage stability, angle stability, active power and reactive power is discussed and research results become important for the smooth integration of wind farms into networks. This study is conducted with the help of PSS/E 34 software simulation tool by Siemens.","PeriodicalId":109238,"journal":{"name":"2020 11th International Conference on Information, Intelligence, Systems and Applications (IISA","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127918999","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 : 2020-07-15DOI: 10.1109/IISA50023.2020.9284342
Styliani Pantopoulou, P. Lagari, C. H. Townsend, L. Tsoukalas
Cybersecurity of digital critical systems, such as nuclear reactors, is a research area of great interest at present. As a result, novel methods of attack resiliency are being explored to support diverse and redundant Cyber Physical Systems. By exploiting the time dependent nature of common control units, the physical operability of the overall structure is enhanced, resulting in greater security and reliability. An important concern is the stability and integrity of the system through cyber support. This stability is created through the introduction of the proposed architecture, which places a premium on the continuation of known quality signal.
{"title":"Critical Systems under Cyber Threats","authors":"Styliani Pantopoulou, P. Lagari, C. H. Townsend, L. Tsoukalas","doi":"10.1109/IISA50023.2020.9284342","DOIUrl":"https://doi.org/10.1109/IISA50023.2020.9284342","url":null,"abstract":"Cybersecurity of digital critical systems, such as nuclear reactors, is a research area of great interest at present. As a result, novel methods of attack resiliency are being explored to support diverse and redundant Cyber Physical Systems. By exploiting the time dependent nature of common control units, the physical operability of the overall structure is enhanced, resulting in greater security and reliability. An important concern is the stability and integrity of the system through cyber support. This stability is created through the introduction of the proposed architecture, which places a premium on the continuation of known quality signal.","PeriodicalId":109238,"journal":{"name":"2020 11th International Conference on Information, Intelligence, Systems and Applications (IISA","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132389878","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 : 2020-07-15DOI: 10.1109/IISA50023.2020.9284400
Ilias Theodorakopoulos, F. Fotopoulou, G. Economou
In this work we present a method for local manifold-based regularization, as a mechanism for knowledge transfer during training of Convolutional Neural Networks. The proposed method aims at regularizing local features produced in intermediate layers of a “student” CNN through an appropriate loss function that encourages the model to adapt such that the local features to exhibit similar geometrical characteristics to those of an “instructor” model, at corresponding layers. To that purpose we formulate a computationally efficient function, loosely encoding the neighboring information in the feature space of the involved feature sets. Experimental evaluation demonstrates the effectiveness of the proposed scheme under various scenarios involving knowledge-transfer, even for difficult tasks where it proves more efficient than the established technique of knowledge distillation. We demonstrate that the presented regularization scheme, utilized in combination with distillation improves the performance of both techniques in most tested configurations. Furthermore, experiments on training with limited data, demonstrate that a combined regularization scheme can achieve the same generalization as an un-regularized training with 50% of the data.
{"title":"Local Manifold Regularization for Knowledge Transfer in Convolutional Neural Networks","authors":"Ilias Theodorakopoulos, F. Fotopoulou, G. Economou","doi":"10.1109/IISA50023.2020.9284400","DOIUrl":"https://doi.org/10.1109/IISA50023.2020.9284400","url":null,"abstract":"In this work we present a method for local manifold-based regularization, as a mechanism for knowledge transfer during training of Convolutional Neural Networks. The proposed method aims at regularizing local features produced in intermediate layers of a “student” CNN through an appropriate loss function that encourages the model to adapt such that the local features to exhibit similar geometrical characteristics to those of an “instructor” model, at corresponding layers. To that purpose we formulate a computationally efficient function, loosely encoding the neighboring information in the feature space of the involved feature sets. Experimental evaluation demonstrates the effectiveness of the proposed scheme under various scenarios involving knowledge-transfer, even for difficult tasks where it proves more efficient than the established technique of knowledge distillation. We demonstrate that the presented regularization scheme, utilized in combination with distillation improves the performance of both techniques in most tested configurations. Furthermore, experiments on training with limited data, demonstrate that a combined regularization scheme can achieve the same generalization as an un-regularized training with 50% of the data.","PeriodicalId":109238,"journal":{"name":"2020 11th International Conference on Information, Intelligence, Systems and Applications (IISA","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129942263","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 : 2020-07-15DOI: 10.1109/IISA50023.2020.9284336
P. Groumpos, Vassiliki Mpelogianni, Dimitris Tsipianitis, Aimilia Papagiannaki, John Gionas, Elan Roy, Amit Aflalo
Buildings consume a significant percentage of the world’s energy resources. The rapid depletion of energy resources, has imparted researchers to focus on energy conservation and wastage. The next generation of intelligent buildings is becoming a trend to cope with the needs of energy and environmental ease in buildings. This advances the intelligent control of building to fulfill the occupants’ need. Intelligent system control for sustainable buildings is dynamic and highly complex.
{"title":"Building Energy Management Methods based on Fuzzy Logic and Expert Intelligence","authors":"P. Groumpos, Vassiliki Mpelogianni, Dimitris Tsipianitis, Aimilia Papagiannaki, John Gionas, Elan Roy, Amit Aflalo","doi":"10.1109/IISA50023.2020.9284336","DOIUrl":"https://doi.org/10.1109/IISA50023.2020.9284336","url":null,"abstract":"Buildings consume a significant percentage of the world’s energy resources. The rapid depletion of energy resources, has imparted researchers to focus on energy conservation and wastage. The next generation of intelligent buildings is becoming a trend to cope with the needs of energy and environmental ease in buildings. This advances the intelligent control of building to fulfill the occupants’ need. Intelligent system control for sustainable buildings is dynamic and highly complex.","PeriodicalId":109238,"journal":{"name":"2020 11th International Conference on Information, Intelligence, Systems and Applications (IISA","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133755396","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 : 2020-07-15DOI: 10.1109/IISA50023.2020.9284378
P. Groumpos
The novel Coronavirus outbreak late in 2019 and early 2020, known today as COVID-19 or SARS-CoV-2. is with us. The WHO has accepted COVID-19 as a pandemic disease. The outbreak of COVID-19 has gained ground in many countries, leading towards a global health emergency. Increased national and international measures are being taken to contain the outbreak leading to total “lockdown” of many countries directly affecting urban economies on a multi-lateral level.. This is a perspective paper, written from a classical engineering point of view only four months after detecting the COVID-19 pandemic. All known studies for COVID-19 are done based on statistical models. These statistical approaches depend solely on correlation factors. The factor of causality has not been considered due to the luck of sufficient mathematical models based on causality. Correlation does not imply causality while causality always implies correlation. The approach of Fuzzy Cognitive Maps (FCM) that is considering the causality factors is proposed, for the first time, to investigate the whole spectrum of COVID-19. An FCM model is proposed and referred as the classical FCM methods. Early theoretical simulation studies using a COVID-19 FCM are very promising. Simulations were performed and results were compared with the classical FCM approach. Useful conclusions and future research directions are provided
{"title":"A new Mathematical Modell for COVID-19: A Fuzzy Cognitive Map Approach for Coronavirus Diseases","authors":"P. Groumpos","doi":"10.1109/IISA50023.2020.9284378","DOIUrl":"https://doi.org/10.1109/IISA50023.2020.9284378","url":null,"abstract":"The novel Coronavirus outbreak late in 2019 and early 2020, known today as COVID-19 or SARS-CoV-2. is with us. The WHO has accepted COVID-19 as a pandemic disease. The outbreak of COVID-19 has gained ground in many countries, leading towards a global health emergency. Increased national and international measures are being taken to contain the outbreak leading to total “lockdown” of many countries directly affecting urban economies on a multi-lateral level.. This is a perspective paper, written from a classical engineering point of view only four months after detecting the COVID-19 pandemic. All known studies for COVID-19 are done based on statistical models. These statistical approaches depend solely on correlation factors. The factor of causality has not been considered due to the luck of sufficient mathematical models based on causality. Correlation does not imply causality while causality always implies correlation. The approach of Fuzzy Cognitive Maps (FCM) that is considering the causality factors is proposed, for the first time, to investigate the whole spectrum of COVID-19. An FCM model is proposed and referred as the classical FCM methods. Early theoretical simulation studies using a COVID-19 FCM are very promising. Simulations were performed and results were compared with the classical FCM approach. Useful conclusions and future research directions are provided","PeriodicalId":109238,"journal":{"name":"2020 11th International Conference on Information, Intelligence, Systems and Applications (IISA","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130664719","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 : 2020-07-15DOI: 10.1109/IISA50023.2020.9284364
Kristen Jaskie, Dominique Smith, A. Spanias
Smart energy meters allow individual residential, commercial, and industrial energy load usage to be monitored continuously with high granularity. Accurate short-term energy forecasting is essential for improving energy efficiency, reducing blackouts, and enabling smart grid control and analytics. In this paper, we survey commonly used non-linear deep learning timeseries forecasting methods for this task including long short-term memory recurrent neural networks and nonlinear autoregressive models, nonlinear autoregressive exogenous networks that also include weather data, and for completeness, MATLAB’s nonlinear input-output model that only uses weather. These models look at every combination of load sequence data and weather information to identify which factors and methods are most effective at predicting short-term residential load. In this paper, the traditional nonlinear autoregressive model predicted short term load values most accurately using only energy load information with a mean square error of 7.53E-5 and a correlation coefficient of 0.995.
{"title":"Deep Learning Networks for Vectorized Energy Load Forecasting","authors":"Kristen Jaskie, Dominique Smith, A. Spanias","doi":"10.1109/IISA50023.2020.9284364","DOIUrl":"https://doi.org/10.1109/IISA50023.2020.9284364","url":null,"abstract":"Smart energy meters allow individual residential, commercial, and industrial energy load usage to be monitored continuously with high granularity. Accurate short-term energy forecasting is essential for improving energy efficiency, reducing blackouts, and enabling smart grid control and analytics. In this paper, we survey commonly used non-linear deep learning timeseries forecasting methods for this task including long short-term memory recurrent neural networks and nonlinear autoregressive models, nonlinear autoregressive exogenous networks that also include weather data, and for completeness, MATLAB’s nonlinear input-output model that only uses weather. These models look at every combination of load sequence data and weather information to identify which factors and methods are most effective at predicting short-term residential load. In this paper, the traditional nonlinear autoregressive model predicted short term load values most accurately using only energy load information with a mean square error of 7.53E-5 and a correlation coefficient of 0.995.","PeriodicalId":109238,"journal":{"name":"2020 11th International Conference on Information, Intelligence, Systems and Applications (IISA","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114357413","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：