Pub Date : 2022-09-01DOI: 10.1109/ICNISC57059.2022.00091
Wei Zhi, Yaowen Ye, Qian Xu, Tigang Jiang
This paper investigates the resource sharing strategy used by different cloud computing tenants, which allows tenants to borrow computing resources from one another as well as exchange high and low-speed data transmission links. We provide a theoretical model of the strategy as well as a resource borrowing and recycling scheme, as well as simulation results. The results show that using this resource borrowing scheme can reduce the business's denial of service rate, queuing time, and overall service time, which is especially beneficial for high-load businesses. This article also found that under this strategy, as the service arrival rate increases, the average time that high- and low-traffic services are directly served by the cloud computing center is not monotonously increasing or monotonically increasing, but presents a concave curve or a convex curve, gradually approaching the state of not using resource borrowing, this is of guiding significance for analyzing the resource borrowing and optimal threshold design of actual cloud computing centers.
{"title":"Cloud Computing Resource Allocation Considering Link Switching and Computing Resource Borrowing","authors":"Wei Zhi, Yaowen Ye, Qian Xu, Tigang Jiang","doi":"10.1109/ICNISC57059.2022.00091","DOIUrl":"https://doi.org/10.1109/ICNISC57059.2022.00091","url":null,"abstract":"This paper investigates the resource sharing strategy used by different cloud computing tenants, which allows tenants to borrow computing resources from one another as well as exchange high and low-speed data transmission links. We provide a theoretical model of the strategy as well as a resource borrowing and recycling scheme, as well as simulation results. The results show that using this resource borrowing scheme can reduce the business's denial of service rate, queuing time, and overall service time, which is especially beneficial for high-load businesses. This article also found that under this strategy, as the service arrival rate increases, the average time that high- and low-traffic services are directly served by the cloud computing center is not monotonously increasing or monotonically increasing, but presents a concave curve or a convex curve, gradually approaching the state of not using resource borrowing, this is of guiding significance for analyzing the resource borrowing and optimal threshold design of actual cloud computing centers.","PeriodicalId":286467,"journal":{"name":"2022 8th Annual International Conference on Network and Information Systems for Computers (ICNISC)","volume":"151 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134048973","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 : 2022-09-01DOI: 10.1109/icnisc57059.2022.00148
Q. Tan, Peng Wu, Wei Tang, Yu Zhang
Data centers have high energy consumption and large volume, and have great energy-saving potential. Through the transfer of data load among multiple data centers, the transfer of electric power between regional power grids can be realized. The latest progress of three typical application modes of current data center leasing and value-added services, edge content distribution and computing node joint deployment services, and edge-cloud computing collaborative services are analyzed. The feasibility and necessity of data center participating in demand-side resource scheduling are analyzed, and the preliminary work that needs to be completed in this stage to deeply excavate the adjustment potential of data center to participate in demand response is proposed.
{"title":"Data Center Participates in the Design of Typical Scenarios for Power Demand Response","authors":"Q. Tan, Peng Wu, Wei Tang, Yu Zhang","doi":"10.1109/icnisc57059.2022.00148","DOIUrl":"https://doi.org/10.1109/icnisc57059.2022.00148","url":null,"abstract":"Data centers have high energy consumption and large volume, and have great energy-saving potential. Through the transfer of data load among multiple data centers, the transfer of electric power between regional power grids can be realized. The latest progress of three typical application modes of current data center leasing and value-added services, edge content distribution and computing node joint deployment services, and edge-cloud computing collaborative services are analyzed. The feasibility and necessity of data center participating in demand-side resource scheduling are analyzed, and the preliminary work that needs to be completed in this stage to deeply excavate the adjustment potential of data center to participate in demand response is proposed.","PeriodicalId":286467,"journal":{"name":"2022 8th Annual International Conference on Network and Information Systems for Computers (ICNISC)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133945773","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 : 2022-09-01DOI: 10.1109/ICNISC57059.2022.00029
Yingjie Tan
Geological disasters cause great threat to people's life and property. Therefore, it is necessary to take close supervise and monitoring to geological disasters to take timely measures. To address this, communication needs to be established between the emergency operation center and the monitoring equipment. Traditional communication mode obviously cannot accomplish this task which is complex and dangerous. Hence, unmanned aerial vehicle (UAV) becomes an ideal choice given its high maneuverability and strong scalability. Considering the factors of cost and security, how to deploy UAVs is a key factor. In this paper, first of all, an optimization model for both minimizing cost and maximizing security is formulated. Moreover, a K-means and depth first search aided-artificial bee colony algorithm (KDFS-ABC) is proposed. Finally, extensive simulation results demonstrate that our proposed model outperforms the sate-of-the-art works in terms of computational complexity and the cost of UAV systems.
{"title":"Artificial Bee Colony-Aided UAV Deployment and Relay Communications for Geological Disasters","authors":"Yingjie Tan","doi":"10.1109/ICNISC57059.2022.00029","DOIUrl":"https://doi.org/10.1109/ICNISC57059.2022.00029","url":null,"abstract":"Geological disasters cause great threat to people's life and property. Therefore, it is necessary to take close supervise and monitoring to geological disasters to take timely measures. To address this, communication needs to be established between the emergency operation center and the monitoring equipment. Traditional communication mode obviously cannot accomplish this task which is complex and dangerous. Hence, unmanned aerial vehicle (UAV) becomes an ideal choice given its high maneuverability and strong scalability. Considering the factors of cost and security, how to deploy UAVs is a key factor. In this paper, first of all, an optimization model for both minimizing cost and maximizing security is formulated. Moreover, a K-means and depth first search aided-artificial bee colony algorithm (KDFS-ABC) is proposed. Finally, extensive simulation results demonstrate that our proposed model outperforms the sate-of-the-art works in terms of computational complexity and the cost of UAV systems.","PeriodicalId":286467,"journal":{"name":"2022 8th Annual International Conference on Network and Information Systems for Computers (ICNISC)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132937933","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 : 2022-09-01DOI: 10.1109/ICNISC57059.2022.00123
Jie Lin, Li Wan, Shaohong Fang, Hao Chen
Steel's performance is usually tested by a set of evaluation index system and the testing result is issued in formal reports. The reports are difficult to satisfy the steel quality analysis for long-term evaluation from different dimension. To evaluate the strength quality of steel, based on feature engineering method, we identify the data attributes and clean the raw data from steel strength test report first, and then construct the dynamic features of its mean, variance, and coefficient of variation using time window method for different dimension. Finally, integrate the multi-feature evaluation result. Experimental results show that the data definition is no redundancy and by time window dynamic feature the quality evaluation become more flexible for material control and achieve better result effectively.
{"title":"Evaluating Steel Quality via the Feature Engineering Method","authors":"Jie Lin, Li Wan, Shaohong Fang, Hao Chen","doi":"10.1109/ICNISC57059.2022.00123","DOIUrl":"https://doi.org/10.1109/ICNISC57059.2022.00123","url":null,"abstract":"Steel's performance is usually tested by a set of evaluation index system and the testing result is issued in formal reports. The reports are difficult to satisfy the steel quality analysis for long-term evaluation from different dimension. To evaluate the strength quality of steel, based on feature engineering method, we identify the data attributes and clean the raw data from steel strength test report first, and then construct the dynamic features of its mean, variance, and coefficient of variation using time window method for different dimension. Finally, integrate the multi-feature evaluation result. Experimental results show that the data definition is no redundancy and by time window dynamic feature the quality evaluation become more flexible for material control and achieve better result effectively.","PeriodicalId":286467,"journal":{"name":"2022 8th Annual International Conference on Network and Information Systems for Computers (ICNISC)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133484634","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 : 2022-09-01DOI: 10.1109/ICNISC57059.2022.00093
Xiao Zhang, Youhuai Wang, Yong Cai, Yuxiong He, Xiaoming Chen, Shi Jin
The Internet of Things has been integrated into every aspect of our modern life, intelligent IoT services and applications are booming, and massive amounts of data are generated every day, many of which contain private information. However, due to limited resources and limited computing power, IoT networks are vulnerable to various types of attacks. Therefore, it is crucial to protect the IoT network from adversarial attacks. In today's technology, applying deep learning to classify traffic is a very effective method. It also brings a problem. In a general cloud server architecture, training data needs to be transmitted to the cloud for processing and model training. The massive data transmission overhead will bring delays in transmission and response, as well as privacy leakage issues. Federated learning (FL) based on cloud-edge collaborative networks has received considerable attention, an emerging framework for training deep learning models from decentralized data. The system sends deep learning algorithms to all edges (data sources) at the same time, trains partial models at each edge, and aggregates these partial models into a learned overall model. User information is not uploaded to the cloud during the entire process. This paper adopts the federated learning framework to detect and classify network traffic attacks, and effectively protect user privacy data.
{"title":"Intrusion Detection Based on Data Privacy in Cloud-Edge Collaborative Computing Using Federated Learning","authors":"Xiao Zhang, Youhuai Wang, Yong Cai, Yuxiong He, Xiaoming Chen, Shi Jin","doi":"10.1109/ICNISC57059.2022.00093","DOIUrl":"https://doi.org/10.1109/ICNISC57059.2022.00093","url":null,"abstract":"The Internet of Things has been integrated into every aspect of our modern life, intelligent IoT services and applications are booming, and massive amounts of data are generated every day, many of which contain private information. However, due to limited resources and limited computing power, IoT networks are vulnerable to various types of attacks. Therefore, it is crucial to protect the IoT network from adversarial attacks. In today's technology, applying deep learning to classify traffic is a very effective method. It also brings a problem. In a general cloud server architecture, training data needs to be transmitted to the cloud for processing and model training. The massive data transmission overhead will bring delays in transmission and response, as well as privacy leakage issues. Federated learning (FL) based on cloud-edge collaborative networks has received considerable attention, an emerging framework for training deep learning models from decentralized data. The system sends deep learning algorithms to all edges (data sources) at the same time, trains partial models at each edge, and aggregates these partial models into a learned overall model. User information is not uploaded to the cloud during the entire process. This paper adopts the federated learning framework to detect and classify network traffic attacks, and effectively protect user privacy data.","PeriodicalId":286467,"journal":{"name":"2022 8th Annual International Conference on Network and Information Systems for Computers (ICNISC)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124948377","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 : 2022-09-01DOI: 10.1109/ICNISC57059.2022.00085
Yuan Kong, Lunbo Zou, Ling Zhu
In the context of big data, both the thinking and the methodology of auditing are undergoing huge changes. The auditing technology of big data provides new ideas and methods for modern auditing work, and makes it move toward a more predictable, intelligent and timely direction, free from traditional methods of data processing. On the other hand, the constant use and development of continuous auditing technology has adapted to the need for constant innovation in audit thinking in the context of big data. Conducting continuous auditing in the context of big data not only poses challenges to auditing, but also promotes changes in audit management and technology, and lays a solid foundation for conducting intelligent auditing in the future.
{"title":"Practice and Exploration of Conducting Continuous Auditing in the Context of Big Data","authors":"Yuan Kong, Lunbo Zou, Ling Zhu","doi":"10.1109/ICNISC57059.2022.00085","DOIUrl":"https://doi.org/10.1109/ICNISC57059.2022.00085","url":null,"abstract":"In the context of big data, both the thinking and the methodology of auditing are undergoing huge changes. The auditing technology of big data provides new ideas and methods for modern auditing work, and makes it move toward a more predictable, intelligent and timely direction, free from traditional methods of data processing. On the other hand, the constant use and development of continuous auditing technology has adapted to the need for constant innovation in audit thinking in the context of big data. Conducting continuous auditing in the context of big data not only poses challenges to auditing, but also promotes changes in audit management and technology, and lays a solid foundation for conducting intelligent auditing in the future.","PeriodicalId":286467,"journal":{"name":"2022 8th Annual International Conference on Network and Information Systems for Computers (ICNISC)","volume":"7 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126005034","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 : 2022-09-01DOI: 10.1109/ICNISC57059.2022.00156
Deqiang Kong, Baoping Yang, Fen Li
Controlling electromagnetic space has become an important support for the fight for comprehensive control over the battlefield. How to effectively use limited electromagnetic spectrum resources has become a major problem that restricts future operations. The GIS-based electromagnetic spectrum management and control prototype system can provide commanders with spectrum planning and frequency assignment suggestions, and give full play to the combat effectiveness of frequency equipment. First introduced the basic structure of the prototype system and the overview of the command and equipment side; then designed the system composition and the command side workflow of the prototype system; finally, in order to demonstrate the effectiveness of the prototype system, use the border conflict as the background to distinguish the pre-war spectrum The electromagnetic spectrum is managed and controlled in three situations: assignment, suffering from ground-based fixed interference and suffering from space-based mobile interference. Through teaching and training practice, it is helpful to effectively use electromagnetic spectrum resources and avoid intentional interference, and has certain promotion and application value
{"title":"Research on Prototype System for Electromagnetic Spectrum Management and Control Based on GIS","authors":"Deqiang Kong, Baoping Yang, Fen Li","doi":"10.1109/ICNISC57059.2022.00156","DOIUrl":"https://doi.org/10.1109/ICNISC57059.2022.00156","url":null,"abstract":"Controlling electromagnetic space has become an important support for the fight for comprehensive control over the battlefield. How to effectively use limited electromagnetic spectrum resources has become a major problem that restricts future operations. The GIS-based electromagnetic spectrum management and control prototype system can provide commanders with spectrum planning and frequency assignment suggestions, and give full play to the combat effectiveness of frequency equipment. First introduced the basic structure of the prototype system and the overview of the command and equipment side; then designed the system composition and the command side workflow of the prototype system; finally, in order to demonstrate the effectiveness of the prototype system, use the border conflict as the background to distinguish the pre-war spectrum The electromagnetic spectrum is managed and controlled in three situations: assignment, suffering from ground-based fixed interference and suffering from space-based mobile interference. Through teaching and training practice, it is helpful to effectively use electromagnetic spectrum resources and avoid intentional interference, and has certain promotion and application value","PeriodicalId":286467,"journal":{"name":"2022 8th Annual International Conference on Network and Information Systems for Computers (ICNISC)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127695253","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 : 2022-09-01DOI: 10.1109/ICNISC57059.2022.00058
Y. Peng, Chengzhang Qu
This paper aims to establish a distributed music comments mining system based on BGLL algorithm. With the massive music resource and users of NetEase Cloud Music, our system employs big data technology and machine learning technology to analyze data from the perspective of comments, discover users' attitudes towards the song or the music. The whole system is built based on the Hadoop ecosystem, and it includes four main modules: data acquisition, data storage, data analysis, and data visualization. A python based web crawler is used for data acquisition on NetEase Cloud Music resource, then the distributed HDFS system is built for data processing and analyzing. A refined mining algorithm based on BGLL is implemented for topic mining procedure. At last, a word cloud map is generated based on javaweb technology. Experiments show that our system can perfome well on the comment topic mining application, due to the distributed architecture, our system has a potential capability on dealing with large scale of data.
{"title":"Distributed Music Comments Mining System Based on BGLL Algorithm","authors":"Y. Peng, Chengzhang Qu","doi":"10.1109/ICNISC57059.2022.00058","DOIUrl":"https://doi.org/10.1109/ICNISC57059.2022.00058","url":null,"abstract":"This paper aims to establish a distributed music comments mining system based on BGLL algorithm. With the massive music resource and users of NetEase Cloud Music, our system employs big data technology and machine learning technology to analyze data from the perspective of comments, discover users' attitudes towards the song or the music. The whole system is built based on the Hadoop ecosystem, and it includes four main modules: data acquisition, data storage, data analysis, and data visualization. A python based web crawler is used for data acquisition on NetEase Cloud Music resource, then the distributed HDFS system is built for data processing and analyzing. A refined mining algorithm based on BGLL is implemented for topic mining procedure. At last, a word cloud map is generated based on javaweb technology. Experiments show that our system can perfome well on the comment topic mining application, due to the distributed architecture, our system has a potential capability on dealing with large scale of data.","PeriodicalId":286467,"journal":{"name":"2022 8th Annual International Conference on Network and Information Systems for Computers (ICNISC)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121069107","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 : 2022-09-01DOI: 10.1109/ICNISC57059.2022.00013
Yulin Zhou
In order to meet the needs of dual-channel high-resolution video encoding and decoding, as well as the need for long-term capture and recording of operating terminal screen information in important control scenarios such as shipborne, vehicle-mounted, and airborne, it is convenient for post-event technical analysis, service quality assessment, and exercises. Deduction and determination of responsibility for operation accidents. The hardware architecture of PowerPC+WW602 is researched, and a platform that supports dual-channel high-definition video encoding and decoding is designed and implemented. The compression algorithm of H.264 encoding standard is used to realize the encoding and decoding of video data, and advanced and mature technology is used to follow the generalization. The video codec platform design based on PowerPC+WW602 architecture can support single-channel or dual-channel video input of high-definition and standard-definition, and realize the codec transmission of two channels of video information. The delay of video capture and display is within 30ms, the picture is clear, and the video capture process is not lost.
{"title":"Design of Video Codec Platform Based on PowerPC+WW602 Architecture","authors":"Yulin Zhou","doi":"10.1109/ICNISC57059.2022.00013","DOIUrl":"https://doi.org/10.1109/ICNISC57059.2022.00013","url":null,"abstract":"In order to meet the needs of dual-channel high-resolution video encoding and decoding, as well as the need for long-term capture and recording of operating terminal screen information in important control scenarios such as shipborne, vehicle-mounted, and airborne, it is convenient for post-event technical analysis, service quality assessment, and exercises. Deduction and determination of responsibility for operation accidents. The hardware architecture of PowerPC+WW602 is researched, and a platform that supports dual-channel high-definition video encoding and decoding is designed and implemented. The compression algorithm of H.264 encoding standard is used to realize the encoding and decoding of video data, and advanced and mature technology is used to follow the generalization. The video codec platform design based on PowerPC+WW602 architecture can support single-channel or dual-channel video input of high-definition and standard-definition, and realize the codec transmission of two channels of video information. The delay of video capture and display is within 30ms, the picture is clear, and the video capture process is not lost.","PeriodicalId":286467,"journal":{"name":"2022 8th Annual International Conference on Network and Information Systems for Computers (ICNISC)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114262536","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}
With the development of the power industry, the number of two-way interactive power consumption units continues to increase, and the burden of power distribution on the grid continues to increase. The load aggregator is located between the power grid and the power consumption unit, and represents a certain range of users to request power from the power grid, and then performs power distribution and real-time scheduling to users, reducing the burden on the power grid. To better respond to the demand of electricity consumers, machine learning is used in electricity forecasting. However, the training data comes from power users, which will involve privacy protection issues. To this end, this paper proposes a load aggregator power prediction method that supports user privacy protection. This method can take into account the influence of user-related fixed factors and time-related variable factors on power consumption. The load aggregator is the aggregator. There is no need for power users to share their own data, and the necessary model parameters are passed to the load aggregator only when needed, and it can still be carried out for some participants without labels. Finally, the proposed method is evaluated through experiments, and the results show that the method in this paper can effectively protect user privacy, and has a considerable accuracy compared with the existing machine learning methods that do not protect privacy.
{"title":"A Load Aggregation Commercial Electricity Prediction Method Supporting User Privacy Protection","authors":"Hao Wu, Yiyun Wang, Weijian Wu, Ying Chen, Aoying Chen","doi":"10.1109/ICNISC57059.2022.00107","DOIUrl":"https://doi.org/10.1109/ICNISC57059.2022.00107","url":null,"abstract":"With the development of the power industry, the number of two-way interactive power consumption units continues to increase, and the burden of power distribution on the grid continues to increase. The load aggregator is located between the power grid and the power consumption unit, and represents a certain range of users to request power from the power grid, and then performs power distribution and real-time scheduling to users, reducing the burden on the power grid. To better respond to the demand of electricity consumers, machine learning is used in electricity forecasting. However, the training data comes from power users, which will involve privacy protection issues. To this end, this paper proposes a load aggregator power prediction method that supports user privacy protection. This method can take into account the influence of user-related fixed factors and time-related variable factors on power consumption. The load aggregator is the aggregator. There is no need for power users to share their own data, and the necessary model parameters are passed to the load aggregator only when needed, and it can still be carried out for some participants without labels. Finally, the proposed method is evaluated through experiments, and the results show that the method in this paper can effectively protect user privacy, and has a considerable accuracy compared with the existing machine learning methods that do not protect privacy.","PeriodicalId":286467,"journal":{"name":"2022 8th Annual International Conference on Network and Information Systems for Computers (ICNISC)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123109283","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：