Pub Date : 2018-10-01DOI: 10.1109/CYBERC.2018.00083
Jiale Zhao, Shuangzhi Li, Daniel C. F. Ma, X. Mu
In this paper, we consider a single-cell spectrum sharing system, in which there exist multiple cognitive device-to-device (D2D) pairs and cellular users (CUs). For such a system, in order to improve the overall spectral efficiency, we propose a joint mode selection and resource allocation scheme. In detail, a mode selection criterion is firstly built by utilizing the knowledge of channel gain ratio; then, for different modes of D2D users, a resource allocation strategy based on greedy algorithm is derived. Finally, by exploiting the genetic algorithm, dichotomy and Lagrange multiplier method jointly, we further optimize the power allocation scheme. Simulation results demonstrate that the proposed scheme is able to enhance the spectral efficiency of the considered system.
{"title":"Research on Joint Mode Selection and Resource Allocation Scheme in D2D Networks","authors":"Jiale Zhao, Shuangzhi Li, Daniel C. F. Ma, X. Mu","doi":"10.1109/CYBERC.2018.00083","DOIUrl":"https://doi.org/10.1109/CYBERC.2018.00083","url":null,"abstract":"In this paper, we consider a single-cell spectrum sharing system, in which there exist multiple cognitive device-to-device (D2D) pairs and cellular users (CUs). For such a system, in order to improve the overall spectral efficiency, we propose a joint mode selection and resource allocation scheme. In detail, a mode selection criterion is firstly built by utilizing the knowledge of channel gain ratio; then, for different modes of D2D users, a resource allocation strategy based on greedy algorithm is derived. Finally, by exploiting the genetic algorithm, dichotomy and Lagrange multiplier method jointly, we further optimize the power allocation scheme. Simulation results demonstrate that the proposed scheme is able to enhance the spectral efficiency of the considered system.","PeriodicalId":282903,"journal":{"name":"2018 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121426144","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 : 2018-10-01DOI: 10.1109/CYBERC.2018.00086
Yang Gao, Yingzhou Zhang, Shurong Zhu, Yi Sun
With the development of the technology of unmanned aerial vehicle (UAV), the multi-UAV task allocation has become a hot topic in recent years. Recently, many classical intelligent optimization algorithms have been applied to this problem, because the multi-UAV task allocation problem can be formalized as a NP-hard issue. However, most research treat this problem as a single objective optimization problem. In view of this situation, we use an improved algorithm of multi-objective particle swarm optimization (MOPSO) to solve the task allocation problem of multiple UAVs. We will take two stages of SMC resampling to improve the disadvantages in the MOPSO algorithm. In the first stage, resampling is used to improve the slow convergence of the particle swarm optimization in the middle and late stages. In the second stage, resampling is used to expand the search area of the particle swarm optimization algorithm and to prevent the algorithm from falling into the local optimal solution. The simulation results show that the improved algorithm has a good performance in solving the task allocation problem of multiple UAVs.
{"title":"Multi-UAV Task Allocation Based on Improved Algorithm of Multi-objective Particle Swarm Optimization","authors":"Yang Gao, Yingzhou Zhang, Shurong Zhu, Yi Sun","doi":"10.1109/CYBERC.2018.00086","DOIUrl":"https://doi.org/10.1109/CYBERC.2018.00086","url":null,"abstract":"With the development of the technology of unmanned aerial vehicle (UAV), the multi-UAV task allocation has become a hot topic in recent years. Recently, many classical intelligent optimization algorithms have been applied to this problem, because the multi-UAV task allocation problem can be formalized as a NP-hard issue. However, most research treat this problem as a single objective optimization problem. In view of this situation, we use an improved algorithm of multi-objective particle swarm optimization (MOPSO) to solve the task allocation problem of multiple UAVs. We will take two stages of SMC resampling to improve the disadvantages in the MOPSO algorithm. In the first stage, resampling is used to improve the slow convergence of the particle swarm optimization in the middle and late stages. In the second stage, resampling is used to expand the search area of the particle swarm optimization algorithm and to prevent the algorithm from falling into the local optimal solution. The simulation results show that the improved algorithm has a good performance in solving the task allocation problem of multiple UAVs.","PeriodicalId":282903,"journal":{"name":"2018 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125680957","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 : 2018-10-01DOI: 10.1109/CYBERC.2018.00102
E. Basan, A. Basan, O. Makarevich
In this paper we consider the problem of the need for deep traffic analysis to detect attacks on a network of mobile robots, as well as to assess their effectiveness. The object of the study is a group of mobile robots. It provide a means to analyze the security of mobile robot networks. It analyzes the anomalous activity of robots in a mobile network, based on analysis of traffic at the network and transport layers. To carry out such an analysis, a mathematical approach based on mathematical statistics and probability theory is used. It allows detecting attacks distributed denial of service and Sibyl attack. In addition, this technique allows us to determine what metrics are affected by this or that attack. In addition, it is possible to assess under what conditions the attack has the greatest impact on the network. In this paper, an experimental study was carried out and statistical data collected, the analysis of which allowed us to confirm theoretical assumptions.
{"title":"Evaluating and Detecting Internal Attacks in a Mobile Robotic Network","authors":"E. Basan, A. Basan, O. Makarevich","doi":"10.1109/CYBERC.2018.00102","DOIUrl":"https://doi.org/10.1109/CYBERC.2018.00102","url":null,"abstract":"In this paper we consider the problem of the need for deep traffic analysis to detect attacks on a network of mobile robots, as well as to assess their effectiveness. The object of the study is a group of mobile robots. It provide a means to analyze the security of mobile robot networks. It analyzes the anomalous activity of robots in a mobile network, based on analysis of traffic at the network and transport layers. To carry out such an analysis, a mathematical approach based on mathematical statistics and probability theory is used. It allows detecting attacks distributed denial of service and Sibyl attack. In addition, this technique allows us to determine what metrics are affected by this or that attack. In addition, it is possible to assess under what conditions the attack has the greatest impact on the network. In this paper, an experimental study was carried out and statistical data collected, the analysis of which allowed us to confirm theoretical assumptions.","PeriodicalId":282903,"journal":{"name":"2018 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126507784","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}
Answer selection is a one of the critical tasks in natural lan-guage processing area and it is helpful in many practical applications. To better tackle this problem, the first challenge is to effectively extract the sentence information. In this research, we propose an advanced Re-Read-CNN model which can learn a deep sentence representation and meanwhile combine the local feature representation. The experiment results on commonly used datasets have shown its effectiveness and potential for answer selection.
{"title":"A Hybrid of Deep Sentence Representation and Local Feature Representation Model for Question Answer Selection","authors":"Dongge Tang, Wenge Rong, Libin Shi, Haodong Yang, Zhang Xiong","doi":"10.1109/CYBERC.2018.00057","DOIUrl":"https://doi.org/10.1109/CYBERC.2018.00057","url":null,"abstract":"Answer selection is a one of the critical tasks in natural lan-guage processing area and it is helpful in many practical applications. To better tackle this problem, the first challenge is to effectively extract the sentence information. In this research, we propose an advanced Re-Read-CNN model which can learn a deep sentence representation and meanwhile combine the local feature representation. The experiment results on commonly used datasets have shown its effectiveness and potential for answer selection.","PeriodicalId":282903,"journal":{"name":"2018 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117291699","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}
L-band digital aeronautical communication system (L-DACS) based on orthogonal Frequency Division Multiplexing (OFDM) technology is the best candidate for the future communication infrastructure of the air-to-ground (AG) communication system. How does the receiver can correctly and timely determine the channel change becomes the basis for ensuring the stable transmission of information in the aeronautical communication network. In this paper, we propose a channel parameter estimation algorithm using the statistical multipath delay information of takeoff and landing near the airport as a priori information in the navigation system and fixed aircraft scene. Simulation results have demonstra-ted that the proposed algorithm significantly improves the estimated performance on the basis of reducing the parameters to be estimated.
{"title":"Prior-Information Associated Channel Parameter Estimation for Aeronautical Communications","authors":"Youyou Zhao, Xingxuan Zuo, Yingbo Shang, X. Mu, Jiankang Zhang","doi":"10.1109/CYBERC.2018.00078","DOIUrl":"https://doi.org/10.1109/CYBERC.2018.00078","url":null,"abstract":"L-band digital aeronautical communication system (L-DACS) based on orthogonal Frequency Division Multiplexing (OFDM) technology is the best candidate for the future communication infrastructure of the air-to-ground (AG) communication system. How does the receiver can correctly and timely determine the channel change becomes the basis for ensuring the stable transmission of information in the aeronautical communication network. In this paper, we propose a channel parameter estimation algorithm using the statistical multipath delay information of takeoff and landing near the airport as a priori information in the navigation system and fixed aircraft scene. Simulation results have demonstra-ted that the proposed algorithm significantly improves the estimated performance on the basis of reducing the parameters to be estimated.","PeriodicalId":282903,"journal":{"name":"2018 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128873976","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 : 2018-10-01DOI: 10.1109/CYBERC.2018.00048
Zehong Zhou, Chenxi Zhang, Zhenyu A. Liao, Jian Xu, Jiangfeng Li
An intermittently connected mobile social network (ICMSN) is a special kind of delay tolerant network (DTN). Compared with the stable routing path in conventional networks, there is not a stable routing path from source to destination in ICMSNs. In order to deal with the challenging routing issue in ICMSNs, numerous opportunistic routing algorithms have been proposed. However, the existed approaches cannot achieve the optimal performance in file sharing because most of them focus on the general routing but ignore the social characteristic. In addition, the needed resources passively waited until a request has been received by the nodes in the traditional file sharing schemes. In this paper, a field intensity based model is proposed to solve the passive file sharing problem in ICMSNs. This model exploits the field intensity generated from the inherent features of mobile users to decide a better orientation for messages forwarding. Furthermore, a container which be used to store the information of field is designed to reduce overhead. We also propose a field intensity based redundancy control strategy to maintain the number of copies within a reasonable range. Finally, we realize a initiative file sharing system according to the model. The simulation results show that our method has advantages in performance against other methods.
{"title":"A Field Intensity Based Model for Initiative File Sharing in Mobile Social Networks","authors":"Zehong Zhou, Chenxi Zhang, Zhenyu A. Liao, Jian Xu, Jiangfeng Li","doi":"10.1109/CYBERC.2018.00048","DOIUrl":"https://doi.org/10.1109/CYBERC.2018.00048","url":null,"abstract":"An intermittently connected mobile social network (ICMSN) is a special kind of delay tolerant network (DTN). Compared with the stable routing path in conventional networks, there is not a stable routing path from source to destination in ICMSNs. In order to deal with the challenging routing issue in ICMSNs, numerous opportunistic routing algorithms have been proposed. However, the existed approaches cannot achieve the optimal performance in file sharing because most of them focus on the general routing but ignore the social characteristic. In addition, the needed resources passively waited until a request has been received by the nodes in the traditional file sharing schemes. In this paper, a field intensity based model is proposed to solve the passive file sharing problem in ICMSNs. This model exploits the field intensity generated from the inherent features of mobile users to decide a better orientation for messages forwarding. Furthermore, a container which be used to store the information of field is designed to reduce overhead. We also propose a field intensity based redundancy control strategy to maintain the number of copies within a reasonable range. Finally, we realize a initiative file sharing system according to the model. The simulation results show that our method has advantages in performance against other methods.","PeriodicalId":282903,"journal":{"name":"2018 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125293112","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 : 2018-10-01DOI: 10.1109/CYBERC.2018.00093
Mahesh Singh
This technique of mesh generation is based on advance and researched quad tree approach which makes use of mathematical technique of variance for selecting quad size and further triangulate the quad for final mesh of image and later filtering of vertices is done as per mapping based on robotic model. Object identification based on Bayesian statistical and probability theorem is used to estimate the foreground object for getting selective object within image for mesh generation. This paper explains estimation algorithms for object identification by detecting background and foreground objects in image obtained from raw video frame@30fps supporting sampling format 4:2:0. This algorithm is implemented tested/verified on and written for android based ARM system and x86 for demo and quality propose.Video frame is live captured in .mp4 file format using aac/avc (H264) audio and video codec. Video is decoded and sub sampled and scaled using ffmeg framework to desired frame size and frame format for Video processing using Open source based framework integrated into propriety applications. This algorithm can be applied for various application including application in defense/artificial intelligence and medical imaging
{"title":"Mesh Generation Technique and Object Identification for Robotic/Artificial Intelligence","authors":"Mahesh Singh","doi":"10.1109/CYBERC.2018.00093","DOIUrl":"https://doi.org/10.1109/CYBERC.2018.00093","url":null,"abstract":"This technique of mesh generation is based on advance and researched quad tree approach which makes use of mathematical technique of variance for selecting quad size and further triangulate the quad for final mesh of image and later filtering of vertices is done as per mapping based on robotic model. Object identification based on Bayesian statistical and probability theorem is used to estimate the foreground object for getting selective object within image for mesh generation. This paper explains estimation algorithms for object identification by detecting background and foreground objects in image obtained from raw video frame@30fps supporting sampling format 4:2:0. This algorithm is implemented tested/verified on and written for android based ARM system and x86 for demo and quality propose.Video frame is live captured in .mp4 file format using aac/avc (H264) audio and video codec. Video is decoded and sub sampled and scaled using ffmeg framework to desired frame size and frame format for Video processing using Open source based framework integrated into propriety applications. This algorithm can be applied for various application including application in defense/artificial intelligence and medical imaging","PeriodicalId":282903,"journal":{"name":"2018 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129973611","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 : 2018-10-01DOI: 10.1109/CYBERC.2018.00070
N. S. A. G. Yari, Varus Mbembo Loundou, Dong Doan Van
With growing of wireless systems integration, the role that plays green communication platforms are becoming more essential for reducing energy consumption. By proposing a based sub-optimal green energy-efficient algorithm to solve issue of low computational, this paper investigates the effect of users scheduling and power allocation scheme for MIMO-OFDMA green cognitive radio network The problem is formulated as a mixed-integer non-convex optimization problem, in which the objective is to maximize the energy efficiency, enabling Green Communication, under the constraints of the per-user power budget and primary system’s QoS requirements. Taking account of the mixed-integer and non-convexity nature of the problem, we propose a sub-optimal energy-efficient algorithm through two successive steps. The first step schedules the subcarriers among the SUs based on IA while the second step iteratively allocates the power based on Dinkelbach’s method. Through numerical result, the proposed algorithm is revealed to achieve significant improvement in the energy efficiency compared to the traditional spectrum-efficient algorithm.
{"title":"Users Scheduling and Power Allocation Algorithm for MIMO-OFDMA Green Cognitive Radio Systems","authors":"N. S. A. G. Yari, Varus Mbembo Loundou, Dong Doan Van","doi":"10.1109/CYBERC.2018.00070","DOIUrl":"https://doi.org/10.1109/CYBERC.2018.00070","url":null,"abstract":"With growing of wireless systems integration, the role that plays green communication platforms are becoming more essential for reducing energy consumption. By proposing a based sub-optimal green energy-efficient algorithm to solve issue of low computational, this paper investigates the effect of users scheduling and power allocation scheme for MIMO-OFDMA green cognitive radio network The problem is formulated as a mixed-integer non-convex optimization problem, in which the objective is to maximize the energy efficiency, enabling Green Communication, under the constraints of the per-user power budget and primary system’s QoS requirements. Taking account of the mixed-integer and non-convexity nature of the problem, we propose a sub-optimal energy-efficient algorithm through two successive steps. The first step schedules the subcarriers among the SUs based on IA while the second step iteratively allocates the power based on Dinkelbach’s method. Through numerical result, the proposed algorithm is revealed to achieve significant improvement in the energy efficiency compared to the traditional spectrum-efficient algorithm.","PeriodicalId":282903,"journal":{"name":"2018 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130177607","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 : 2018-10-01DOI: 10.1109/CYBERC.2018.00087
Yongliang Sun, Yu He, Yang Yang
In recent years, Location-Based Services (LBS) have been widely applied in people's life with various localization technologies. Because outdoor localization methods are not suitable for indoor environments, various indoor localization methods have been developed. Among the existing indoor localization methods, Wi-Fi fingerprinting localization has attracted great concerns because of its wide applicability, simple deployment, and comparable performance. This paper proposed an interpolation method for radio map establishment based on RSS clustering and propagation model optimization. Fuzzy C-Means (FCM) clustering algorithm is used to cluster the Received Signal Strength (RSS) samples collected at Reference Points (RPs). In each cluster, propagation model parameters are optimized. Then RSS samples are estimated at select locations for radio map establishment. With the radio map after interpolation, more accurate localization results can be computed using K Nearest Neighbors (KNN) fingerprinting algorithm.
{"title":"Interpolation Method for Radio Map Establishment Based on RSS Clustering and Propagation Model Optimization","authors":"Yongliang Sun, Yu He, Yang Yang","doi":"10.1109/CYBERC.2018.00087","DOIUrl":"https://doi.org/10.1109/CYBERC.2018.00087","url":null,"abstract":"In recent years, Location-Based Services (LBS) have been widely applied in people's life with various localization technologies. Because outdoor localization methods are not suitable for indoor environments, various indoor localization methods have been developed. Among the existing indoor localization methods, Wi-Fi fingerprinting localization has attracted great concerns because of its wide applicability, simple deployment, and comparable performance. This paper proposed an interpolation method for radio map establishment based on RSS clustering and propagation model optimization. Fuzzy C-Means (FCM) clustering algorithm is used to cluster the Received Signal Strength (RSS) samples collected at Reference Points (RPs). In each cluster, propagation model parameters are optimized. Then RSS samples are estimated at select locations for radio map establishment. With the radio map after interpolation, more accurate localization results can be computed using K Nearest Neighbors (KNN) fingerprinting algorithm.","PeriodicalId":282903,"journal":{"name":"2018 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116457881","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 : 2018-10-01DOI: 10.1109/CYBERC.2018.00042
Lijuan Hu, Ke-yan Liu, Zhi Lin, Yinglong Diao, W. Sheng
This paper focuses on using big data technology to solve the abnormal state detection problem in power distribution system. With the increasingly more widespread use of digitalization technology, various related systems have been embedded extensively in power system, resulting in a large number of interconnected observations. In order to discover more complex deep-seated rules and provide more effective decision support for power system decision-making, it is necessary to study data mining and analysis methods that are suitable for massive data under current situation. This paper studies the method to identify abnormal data from multi-temporal and multi-spatial data in distribution networks and propose a method to detective abnormal operation state using likelihood-ratio test for three-dimensional spatiotemporal data. In order to speed up the data processing rate, an anomaly detection method based on multi-threading and Hadoop parallelization methods and techniques is proposed.
{"title":"An Abnormal State Detection Method for Power Distribution Network Based on Big Data Technology","authors":"Lijuan Hu, Ke-yan Liu, Zhi Lin, Yinglong Diao, W. Sheng","doi":"10.1109/CYBERC.2018.00042","DOIUrl":"https://doi.org/10.1109/CYBERC.2018.00042","url":null,"abstract":"This paper focuses on using big data technology to solve the abnormal state detection problem in power distribution system. With the increasingly more widespread use of digitalization technology, various related systems have been embedded extensively in power system, resulting in a large number of interconnected observations. In order to discover more complex deep-seated rules and provide more effective decision support for power system decision-making, it is necessary to study data mining and analysis methods that are suitable for massive data under current situation. This paper studies the method to identify abnormal data from multi-temporal and multi-spatial data in distribution networks and propose a method to detective abnormal operation state using likelihood-ratio test for three-dimensional spatiotemporal data. In order to speed up the data processing rate, an anomaly detection method based on multi-threading and Hadoop parallelization methods and techniques is proposed.","PeriodicalId":282903,"journal":{"name":"2018 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123812031","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：