检索结果-内蒙古大学图书馆

DSTL:A dual-step transfer learning-based prediction model for next-generation intelligent cellular networks

Intelligent and Converged Networks 2025年第1期6卷 82-101页

作者： Waqar A.Aziz Iacovos I.Ioannou Marios Lestas Vasos Vassiliou Department of Computer Science University of CyprusNicosia 2109Cyprusand also with CYENS Centre of ExcellenceNicosia 1076Cyprus Department of Electrical Engineering Frederick UniversityNicosia 1036Cyprus

Traffic modeling and prediction are indispensable to future extensive data-driven automated intelligent cellular *** contributes to proactive and autonomic network control operations within cellular *** methodologies typically rely on established prediction models designed for univariate and multivariate time series ***,these approaches often demand a substantial volume of training data and extensive computational resources for prediction model *** this study,we introduce a dual-step transfer learning(DSTL)-based prediction model specifically designed for the prediction of multivariate spatio-temporal cellular *** technique involves the categorization of gNodeBs(gNBs)into distinct clusters based on their traffic pattern *** of training the prediction model individually on each gNB,a base model is trained on the aggregated dataset of all the gNBs within a base cluster using a combination of recurrent neural network(RNN)and bidirectional long-short term memory(RNN-BLSTM)*** the first-step transfer learning(TL),the base model is provided to the gNBs within the base cluster and to the other clusters,where it undergoes the process of fine-tuning the intra-cluster aggregated *** the model is trained on the aggregated dataset within each cluster,it is provided to the gNBs within the respective cluster in the second-step *** model received by each gNB through the proposed DSTL technique either necessitates minimal fine-tuning or,in some cases,requires no further *** conduct extensive experiments on a real-world Telecom Italia cellular traffic *** results demonstrate that the proposed DSTL-based prediction model achieves a mean absolute percentage error of 2.97%,9.85%,and 9.73%in predicting spatio-temporal Internet,calling,and messaging traffic,respectively,while utilizing less computational resources and requiring less training time than traditional model training and

关键词： dual-step transfer learning(DSTL) multivariate spatio-temporal cellular traffic prediction bidirectional long-short term memory(RNN-BLSTM)

来源：评论

学校读者我要写书评

暂无评论

Offloading Using Traditional Optimization and Machine Learning in Federated Cloud-Edge-Fog Systems: A Survey

引用

IEEE Communications Surveys and Tutorials 2023年第2期25卷 1199-1226页

作者： Kar, Binayak Yahya, Widhi Lin, Ying-Dar Ali, Asad National Taiwan University of Science and Technology Department of Computer Science and Information Engineering Taipei106 Taiwan National Yang Ming Chiao Tung University Department of Electrical Engineering and Computer Science Hsinchu300 Taiwan University of Brawijaya Department of Computer Science Malang65145 Indonesia National Yang Ming Chiao Tung University Department of Computer Science Hsinchu300 Taiwan

The huge amount of data generated by the Internet of Things (IoT) devices needs the computational power and storage capacity provided by cloud, edge, and fog computing paradigms. Each of these computing paradigms has its own pros and cons. Cloud computing provides enhanced data storage and computing power but causes high communication latency. Edge and fog computing provide similar services with lower latency but limited capacity, capability, and coverage. A single computing paradigm cannot fulfill all the requirements of IoT devices and a federation between them is needed to extend their capacity, capability, and services. This federation is beneficial to both subscribers and providers and also reveals research issues in traffic offloading between clouds, edges, and fogs. Optimization has traditionally been used to solve the problem of traffic offloading. However, in such a complex federated system, traditional optimization cannot keep up with the strict latency requirements of decision-making, ranging from milliseconds to sub-seconds. Machine learning approaches, especially reinforcement learning, are consequently becoming popular because they could quickly solve offloading problems in dynamic environments with some unknown information. This study provides a novel federal classification between cloud, edge, and fog and presents a comprehensive research roadmap on offloading for different federated scenarios. We survey the relevant literature on the various optimization approaches used to solve this offloading problem and compare their salient features. We then provide a comprehensive survey on offloading in federated systems with machine learning approaches and the lessons learned as a result of these surveys. Finally, we outline several directions for future research and challenges that have to be faced in order to achieve such a federation. © 1998-2012 IEEE.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Detection of Data Falsification Cyber-Attacks in Distributed Generation

Data-Driven Detection of Data Falsification Cyber-Attacks in...

引用

2024 IEEE Middle East Conference on Communications and Networking, MECOM 2024

作者： Anin, Johnson Abdelsalam, Omar Nabil, Mahmoud Hu, Fei Alsharif, Ahmad University of Alabama Department of Electrical and Computer Engineering AL35487 United States Tennessee Tech University Department of Computer Science TN35405 United States University of North Carolina A&T Electrical and Computer Engineering NC27411 United States University of Alabama Department of Computer Science AL35487 United States Benha University Faculty of Engineering at Shoubra Department of Electrical Engineering Egypt

ISBN: (纸本)9798350376715

The advancement of smart grid technology has enabled consumers to become active participants in electricity generation, particularly using renewable-based distributed energy resources. While this evolution offers economic benefits by allowing consumers to sell excess energy back to the grid, it has also opened the door to fraudulent activities. Generation theft, a malicious act where consumers report falsified higher energy generation readings for financial gain, has emerged as a significant challenge, leading to estimated annual losses of approximately $6 billion in the United States alone. In response to this issue, our paper introduces a novel approach to the detection of fraudulent electricity generation within the grid. Our primary contribution is the creation of a benchmark dataset, based on actual power usage and generation data from the Ausgrid dataset, which now includes simulated fraudulent activities alongside normal usage patterns. Our investigation further explores the statistical properties of power consumption patterns among fraudulent users, revealing a distinct lack of periodicity and predictability. By employing the day-to-day correlation matrix as an input to a 2D Convolutional Neural Network (CNN), our detection system significantly improves its ability to distinguish between legitimate and fraudulent electricity use. Additionally, we propose a hybrid deep learning model that merges the strengths of 2D CNNs with the sequential pattern recognition capabilities of Long Short-Term Memory (LSTM) networks. This approach effectively captures both spatial and temporal dynamics within the dataset, leading to a remarkable performance with a detection rate of 97.04%, a false alarm rate of 0.67%, and an overall accuracy of 99.70%. © 2024 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Intelligent Predetermination of Generator Tripping Scheme: Knowledge Fusion-based Deep Reinforcement Learning Framework

引用

CSEE Journal of Power and Energy Systems 2024年第1期10卷 66-75页

作者： Lingkang Zeng Wei Yao Ze Hu Hang Shuai Zhouping Li Jinyu Wen Shijie Cheng State Key Laboratory of Advanced Electromagnetic Engineering and Technology School of Electrical and Electronics EngineeringHuazhong University of Science and TechnologyWuhan 430074China Dispatching and Control Center Central China Branch of State Grid Corporation of ChinaWuhan 430077China. Department of Electrical Engineering and Computer Science University of TennesseeKnoxvilleTN 37996USA

Generator tripping scheme(GTS)is the most commonly used scheme to prevent power systems from losing safety and ***,GTS is composed of offline predetermination and real-time scenario ***,it is extremely time-consuming and labor-intensive for manual predetermination for a large-scale modern power *** improve efficiency of predetermination,this paper proposes a framework of knowledge fusion-based deep reinforcement learning(KF-DRL)for intelligent predetermination of ***,the Markov Decision Process(MDP)for GTS problem is formulated based on transient instability ***,linear action space is developed to reduce dimensionality of action space for multiple controllable ***,KF-DRL leverages domain knowledge about GTS to mask invalid actions during the decision-making *** can enhance the efficiency and learning ***,the graph convolutional network(GCN)is introduced to the policy network for enhanced learning *** simulation results obtained on New England power system demonstrate superiority of the proposed KF-DRL framework for GTS over the purely data-driven DRL method.

关键词： Deep reinforcement learning generator tripping scheme graph convolutional network invalid action masking knowledgefusion

来源：评论

学校读者我要写书评

暂无评论

A TREE STRUCTURE FOR STORAGE, ACCESS AND COLLISION DETECTION OF DISKS

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: electrical engineering and computer science 2023年第1期85卷 53-64页

作者： Sohrabi, S. Moradinejad, A. Asgharian, A. Department of Mathematics Faculty of Science Urmia University Urmia57561-51818 Iran Faculty of Engineering Urmia University Urmia Iran Department of Computer Engineering Faculty of Electrical and Computer Engineering Urmia University Urmia57561-51818 Iran

This paper presents a new and efficient tree data structure for sorting and collision detection of disks in 2D based on a new tree-based data structure, called hexatree, which is introduced for the first time in this paper. The data structure relies on mapping the objects to a space 1 dimension higher and then doing an appropriate range query in that range which is 3D range queries with circular cones of fixed direction and opening angle. Once the tree is constructed in O(n log n) time, disk collision detection queries can be answered in time O(n0.61). The proposed algorithm, in principle, is a dynamic structure;that is, it’s a structure that can be modified once it’s built. The proposed algorithm can be used for designing CAD softwares and other issues that require searching for a disk among a multitude of 2D disks. © 2023, Politechnica University of Bucharest. All rights reserved.

关键词： computer aided design

来源：评论

学校读者我要写书评

暂无评论

iSummary: Workload-Based, Personalized Summaries for Knowledge Graphs 20th

iSummary: Workload-Based, Personalized Summaries for Knowled...

引用

20th International Conference on The Semantic Web, ESWC 2023

作者： Vassiliou, Giannis Alevizakis, Fanouris Papadakis, Nikolaos Kondylakis, Haridimos Department of Electrical and Computer Engineering HMU Heraklion Greece Computer Science Department UOC Heraklion Greece Institute of Computer Science FORTH Heraklion Greece

ISBN: (纸本)9783031334542

The explosion in the size and the complexity of the available Knowledge Graphs on the web has led to the need for efficient and effective methods for their understanding and exploration. Semantic summaries have recently emerged as methods to quickly explore and understand the contents of various sources. However, in most cases, they are static, not incorporating user needs and preferences, and cannot scale. In this paper, we present iSummary, a novel, scalable approach for constructing personalized summaries. As the size and the complexity of the Knowledge Graphs for constructing personalized summaries prohibit efficient summary construction, in our approach we exploit query logs. The main idea behind our approach is to exploit knowledge captured in existing user queries for identifying the most interesting resources and linking them, constructing as such high-quality, personalized summaries. We present an algorithm with theoretical guarantees on the summary’s quality, linear in the number of queries available in the query log. We evaluate our approach using three real-world datasets and several baselines, showing that our approach dominates other methods in terms of both quality and efficiency. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Optimization with a Simplified Helper Task for High-Dimensional Expensive Multiobjective Problems

引用

ACM Transactions on Evolutionary Learning and Optimization 2024年第4期4卷 1-32页

作者： Wu, Xunfeng Lin, Qiuzhen Zhou, Junwei Liu, Songbai Coello Coello, Carlos A. Leung, Victor C. M. College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan430070 China Mexico City07300 Mexico Department of Electrical and Computer Engineering University of British Columbia VancouverBCV6T 1Z4 Canada

In recent years, surrogate-Assisted evolutionary algorithms (SAEAs) have been sufficiently studied for tackling computationally expensive multiobjective optimization problems (EMOPs), as they can quickly estimate the qualities of solutions by using surrogate models to substitute for expensive evaluations. However, most existing SAEAs only show promising performance for solving EMOPs with no more than 10 dimensions, and become less efficient for tackling EMOPs with higher dimensionality. Thus, this article proposes a new SAEA with a simplified helper task for tackling high-dimensional EMOPs. In each generation, one simplified task will be generated artificially by using random dimension reduction on the target task (i.e., the target EMOPs). Then, two surrogate models are trained for the helper task and the target task, respectively. Based on the trained surrogate models, evolutionary multitasking optimization is run to solve these two tasks so that the experiences of solving the helper task can be transferred to speed up the convergence of tackling the target task. Moreover, an effective model management strategy is designed to select new promising samples for training the surrogate models. When compared to five competitive SAEAs on four well-known benchmark suites, the experiments validate the advantages of the proposed algorithm on most test cases. © 2024 held by the owner/author(s).

关键词： Multitasking

来源：评论

学校读者我要写书评

暂无评论

Analysis on unit maximum capacity of orthogonal multiple watermarking for multimedia signals in B5G wireless communications

引用

Digital Communications and Networks 2024年第1期10卷 38-44页

作者： Mianjie Li Senfeng Lai Jiao Wang Zhihong Tian Nadra Guizani Xiaojiang Du Chun Shan School of Electronics and Information Guangdong Polytechnic Normal UniversityGuangzhou510665China Cyberspace Institute of Advanced Technology Guangzhou UniversityGuangzhou510006China Schoolof Electrical Engineering and Computer Science Washington State UniversityPullmanWA99164USA Department of Computer and Information Science Temple UniversityPhiladelphiaPA19122USA

Beyond-5G(B5G)aims to meet the growing demands of mobile traffic and expand the communication *** that intelligent applications to B5G wireless communications will involve security issues regarding user data and operational data,this paper analyzes the maximum capacity of the multi-watermarking method for multimedia signal hiding as a means of alleviating the information security problem of *** multiwatermarking process employs spread transform dither *** the watermarking procedure,Gram-Schmidt orthogonalization is used to obtain the multiple spreading ***,multiple watermarks can be simultaneously embedded into the same position of a multimedia ***,the multiple watermarks can be extracted without affecting one another during the extraction *** analyze the effect of the size of the spreading vector on the unit maximum capacity,and consequently derive the theoretical relationship between the size of the spreading vector and the unit maximum capacity.A number of experiments are conducted to determine the optimal parameter values for maximum robustness on the premise of high capacity and good imperceptibility.

关键词： B5G Multimedia information security Spread transform dither modulation Spreading vector measurement Unit maximum capacity

来源：评论

学校读者我要写书评

暂无评论

Backup subscription scheme for differential protection using IEC61850-9-2 sampled values

引用

Energy Informatics 2024年第1期7卷 110页

作者： Katoulaei, Mohammad Khalili Rahmani, Aamir Høidalen, Hans Kristian Oleinikova, Irina Mork, Bruce Department of energy systems Norwegian University of Science and Technology Trondheim Norway Department of electrical power system Michigan Technical University Michigan United States Department of Electrical Power Engineering Norwegian University of Science and Technology Trondheim Norway Department of Electrical and Computer Engineering Michigan Technological University HoughtonMI49931 United States

In IEC-61850-based digital substations, the protection IED’s performance is dependent on merging unit’s vendor implementation, communication networks, and measurement circuit’s health conditions. As the process bus Sampled Value(SV) enables the availability of all sensor data on a communication network, this paper proposes a Backup Subscription scheme (BSS) for a transformer differential protection (87T, PDIF) function. BSS utilizes sensor data in digital substations to achieve a flexible protection scheme using a dynamic subscription feature. Thus, in case of failure of one sensor, differential protection would be maintained. The paper presents the implementation and verification of a prototyped scheme using a Hardware-in-the-loop simulation test bed. The main result is that BSS integration into differential protection ensures its dependability and security. Moreover, delay compensation and seamless switching feature increases the availability of differential protection. © The Author(s) 2024.

关键词： Hardware-in-the-loop simulation

来源：评论

学校读者我要写书评

暂无评论

FedRME: Federated Learning for Enhanced Distributed Radiomap Estimation 100

FedRME: Federated Learning for Enhanced Distributed Radiomap...

引用

100th IEEE Vehicular Technology Conference, VTC 2024-Fall

作者： Zhang, Weishan Wang, Yue Liu, Lingjia Tian, Zhi George Mason University Department of Electrical and Computer Engineering FairfaxVA United States Georgia State University Department of Computer Science AtlantaGA United States Virginia Tech Department of Electrical and Computer Engineering BlacksburgVA United States

ISBN: (纸本)9798331517786

For future intelligent communication systems, radiomap estimation (RME) is essential for acquiring panoramic awareness of spectrum spatial distribution in wireless environments. Recently, deep learning-based RME methods have been developed to reconstruct radiomaps from spectrum measurements collected at distributed sensors. However, these methods rely on gathering all input data at a central fusion center, resulting in large communication overheads, high computation costs, and privacy leakage concerns. To address these challenges, this work proposes a FedRME approach that makes federated learning applicable for distributed RME over a large-scale network, accommodating geographically heterogeneous transmitter locations and propagation environments. Specifically, we partition the large area into smaller regions to reduce the model complexity required for learning the radiomap in each region. Meanwhile, we incorporate the landscape map as an auxiliary input to induce a common learning model that adheres to the same propagation physics across all these heterogeneous regions. In doing so, fusion centers in all regions can collaborate through federated learning to enhance the overall RME performance. Simulation results indicate that our proposed method outperforms existing benchmarks, particularly under limited data, achieving higher learning accuracy with reduced model complexity and lower computational cost. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：