检索结果-内蒙古大学图书馆

Online Learning in Blockchain-based Energy Trading systems 24

Online Learning in Blockchain-based Energy Trading Systems

2024 International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile networks and Mobile Computing, MobiHoc 2024

作者： Liu, Yunshu Cheung, Man Hon Huang, Jianwei Pillar of Engineering Systems and Design Singapore University of Technology and Design Singapore Singapore Department of Computer Science City University of Hong Kong Hong Kong School of Science and Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen Key Laboratory of Crowd Intelligence Empowered Low-Carbon Energy Network CSIJRI Joint Research Centre on Smart Energy Storage The Chinese University of HongKong Guangdong Shenzhen518172 China

ISBN: (纸本)9798400705212

In this paper, we consider a blockchain-based energy trading (BBET) system with the proof-of-stake (PoS) protocol. The system designer aims to minimize system cost by considering the prosumers’ strategic token allocation between blockchain staking and energy purchase for their applications. This is challenging as the system designer does not know prosumers’ private information of impatience levels towards different applications. To this end, we propose an online learning mechanism (OLM), which includes incentive mechanisms to guide both prosumers’ private information reporting and staking decisions in two phases. In the exploration phase, we design a randomized staking reward to encourage prosumers’ truthful reporting of their private information for the learning of impatience level distributions. Based on the threshold structure of the prosumers’ equilibrium staking strategies, in the exploitation phase, we propose a learning-error-based reward to minimize the system cost considering the finite-sample bias. By characterizing the optimal exploration duration, we prove that OLM achieves an asymptotic zero-regret against the complete information benchmark, with the regret bounded by O(3√lnT/T) when operating for T time slots. We implement the corresponding smart contract in Ethereum to demonstrate the feasibility of our approach. Experiment results show that our mechanism reduces regret by an average of 74% compared to the state-of-art mechanism. © 2024 Copyright held by the owner/author(s).

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Necessary and Sufficient Conditions for Satisfying Linear Temporal Logic Constraints Using Control Barrier Certificates

Necessary and Sufficient Conditions for Satisfying Linear Te...

引用

IEEE Conference on Decision and Control

作者： Luyao Niu Andrew Clark Radha Poovendran Department of Electrical and Computer Engineering Network Security Lab University of Washington Seattle WA Electrical and Systems Engineering Department McKelvey School of Engineering Washington University in St. Louis St. Louis MO

Temporal logic specifications have been used to express complex tasks for control systems. Discretization-free approaches, which do not require discretizing the state and input spaces of the system, have been proposed for control synthesis under temporal logic specifications. Among these approaches, control barrier certificate (CBC)-based solutions have attracted increasing attention. The existing CBC-based approaches, however, have no guarantee on always finding control laws to satisfy the specification, and hence are sound but not complete. In this paper, we derive the necessary and sufficient conditions for a control law to satisfy a temporal logic specification over finite traces using CBCs. By leveraging the equivalence between satisfying the specification and violating the negated specification, we first negate the specification and construct the deterministic finite automaton (DFA) as a representation. We then decompose the DFA into a set of safety problems, where each decomposed problem corresponds to a transition in the DFA. We derive the necessary and sufficient conditions for a control law to solve each safety problem via CBC-based approach. We further develop the necessary and sufficient conditions to verify whether the control laws associated with different safety problems are composable or not. The composability captures whether a sequence of transitions in the DFA can be realized by the system or not. If the set of composable control laws does not render an accepting run on the DFA, then the system can satisfy the specification. We illustrate the proposed approach using a numerical case study on a multi-agent system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Android Malware Detection Approach Based on Static Feature Analysis Using Machine Learning Algorithms

引用

Procedia computer Science 2022年 201卷 653-658页

作者： Ahmed S. Shatnawi Qussai Yassen Abdulrahman Yateem Department of Computer Information Systems Jordan University of Since and Technology Irbid Jordan Department of Network and Security Engineering Jordan University of Since and Technology Irbid Jordan

In the past decade, mobile devices became necessary for modern civilization and contributed directly to its development stages in defining mobile information access. Nonetheless, along with these rapid developments in modern mobile devices, security issues rise dramatically, and malware is the most concerning of all. Therefore, many studies and research are still trending in this spectrum, using Machine Learning approaches to prevent and reduce malware’s impact. This paper seeks to add to what is already a foundation of various malware detection efforts by presenting a static base classification approach for malware detection based on android permissions and API calls. This approach is based on three well-known Machine Learning algorithms, Support Vector Machines (SVM), K-nearest neighbors (KNN), and Naive Bayes (NB) against a comprehensive new Android malware dataset (CICInvesAndMal2019), in pursuit of achieving high malware detection rates and contribution to the efforts and studies in protecting the development of mobile information. access.

关键词： Mobile Information Access Android Malware Malware Detection Machine Learning SVM KNN Naive Bayes CICInves Mal2019 Dataset

来源：评论

学校读者我要写书评

暂无评论

MEAT: MEDIAN-ENSEMBLE ADVERSARIAL TRAINING FOR IMPROVING ROBUSTNESS AND GENERALIZATION

arXiv

引用

arXiv 2024年

作者： Hu, Zhaozhe Yin, Jia-Li Chen, Bin Lin, Luojun Chen, Bo-Hao Liu, Ximeng Fujian Province Key Laboratory of Information Security and Network Systems Fuzhou350108 China College of Computer Science and Big Data Fuzhou University Fuzhou350108 China Department of Computer Science and Engineering Yuan Ze University Taiwan

Self-ensemble adversarial training methods improve model robustness by ensembling models at different training epochs, such as model weight averaging (WA). However, previous research has shown that self-ensemble defense methods in adversarial training (AT) still suffer from robust overfitting, which severely affects the generalization performance. Empirically, in the late phases of training, the AT becomes more overfitting to the extent that the individuals for weight averaging also suffer from overfitting and produce anomalous weight values, which causes the self-ensemble model to continue to undergo robust overfitting due to the failure in removing the weight anomalies. To solve this problem, we aim to tackle the influence of outliers in the weight space in this work and propose an easy-to-operate and effective Median-Ensemble Adversarial Training (MEAT) method to solve the robust overfitting phenomenon existing in self-ensemble defense from the source by searching for the median of the historical model weights. Experimental results show that MEAT achieves the best robustness against the powerful AutoAttack and can effectively allievate the robust overfitting. We further demonstrate that most defense methods can improve robust generalization and robustness by combining with MEAT. Copyright © 2024, The Authors. All rights reserved.

关键词： network security

来源：评论

学校读者我要写书评

暂无评论

A Submodular Energy Function Approach to Controlled Islanding with Provable Stability

A Submodular Energy Function Approach to Controlled Islandin...

引用

IEEE Conference on Decision and Control

作者： Shiyu Cheng Luyao Niu Andrew Clark Radha Poovendran Department of Electrical and Systems Engineering Washington University in St. Louis St. Louis MO USA Department of Electrical and Computer Engineering Network Security Lab University of Washington Seattle WA

Cascading failures occur when failures of one or more nodes in a network lead to failures in neighboring nodes that propagate through the remainder of the network. One approach to mitigate cascading failures is through controlled islanding, in which a subset of edges is deliberately removed in order to partition the network into disjoint and stable islands. In this paper, we propose a submodular optimization algorithm for selecting edges to remove in order to create islands with provable stability. In contrast to existing approaches that optimize over stability-related metrics such as network coherence, our approach maps standard Lyapunov stability conditions to the objective function of an optimization problem. We prove that this optimization problem is equivalent to minimizing a supermodular function subject to a matroid basis constraint. We propose a local search algorithm for selecting the islands with provable optimality bounds, and discuss special cases including signed linear consensus and nonlinear synchronization dynamics. We simulate our approach using linear consensus dynamics with negative edges and find that our proposed algorithms partition the network into a stable island and an unstable island.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning based Spectral Efficiency Maximization in STAR-RIS-Assisted Indoor Outdoor Communication

Deep Reinforcement Learning based Spectral Efficiency Maximi...

引用

IEEE Symposium on network Operations and Management

作者： Pyae Sone Aung Loc X. Nguyen Yan Kyaw Tun Zhu Han Choong Seon Hong Department of Computer Science and Engineering Kyung Hee University Yongin-si Republic of Korea Division of Network and Systems Engineering School of Electrical Engineering and Computer Science (EECS) KTH Royal Institute of Technology Brinellvägen 8 Stockholm Sweden Department of Electrical and Computer Engineering University of Houston Houston TX USA

The significant growth in data consumption among mobile users necessitates the development of new architecture to meet the increasing demand. On the other hand, reconfigurable intelligent surface (RIS) has grown in popularity in 6G due to its improved spectral efficiency, simplicity of deployment, and low cost. However, with the constrained limitation of the coverage by conventional RIS, the research direction has turned towards simultaneously transmitting and reflecting RIS (STAR-RIS) to provide 360° coverage alongside the benefits of RIS. In this paper, a STAR-RIS-assisted downlink communication system for both indoor and outdoor users is investigated. Then, the optimization problem to maximize the spectral efficiency while jointly controlling the beamforming power for each user and phase shift values of the STAR-RIS is formulated. Since the formulated problem is NP-hard and challenging to solve in polynomial time, a policy gradient method for reinforcement learning named proximal policy optimization (PPO) is implemented to solve the problem. To demonstrate the effectiveness of our proposed algorithm, extensive simulation results are executed. Numerical results prove that our proposed algorithm outperforms several benchmark schemes in the literature.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fault Tolerant Neural Control Barrier Functions for Robotic systems under Sensor Faults and Attacks

arXiv

引用

arXiv 2024年

作者： Zhang, Hongchao Niu, Luyao Clark, Andrew Poovendran, Radha The Electrical and Systems Engineering Department McKelvey School of Engineering Washington University in St. Louis St. LouisMO63130 United States The Network Security Lab Department of Electrical and Computer Engineering University of Washington SeattleWA98195-2500 United States

Safety is a fundamental requirement of many robotic systems. Control barrier function (CBF)-based approaches have been proposed to guarantee the safety of robotic systems. However, the effectiveness of these approaches highly relies on the choice of CBFs. Inspired by the universal approximation power of neural networks, there is a growing trend toward representing CBFs using neural networks, leading to the notion of neural CBFs (NCBFs). Current NCBFs, however, are trained and deployed in benign environments, making them ineffective for scenarios where robotic systems experience sensor faults and attacks. In this paper, we study safety-critical control synthesis for robotic systems under sensor faults and attacks. Our main contribution is the development and synthesis of a new class of CBFs that we term fault tolerant neural control barrier function (FT-NCBF). We derive the necessary and sufficient conditions for FT-NCBFs to guarantee safety, and develop a data-driven method to learn FT-NCBFs by minimizing a loss function constructed using the derived conditions. Using the learned FT-NCBF, we synthesize a control input and formally prove the safety guarantee provided by our approach. We demonstrate our proposed approach using two case studies: obstacle avoidance problem for an autonomous mobile robot and spacecraft rendezvous problem, with code available via https://***/HongchaoZhang-HZ/FTNCBF. © 2024, CC BY.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Supervised reinforcement learning based trajectory tracking control for autonomous vehicles ⁎

引用

IFAC-PapersOnLine 2024年第10期58卷 140-145页

作者： András Mihály Van Tan Vu Trong Tu Do Péter Gáspár Systems and Control Laboratory Institute for Computer Science and Control (SZTAKI) Hungarian Research Network Kende u. 13-17 H-1111 Budapest Hungary Department of Automotive Mechanical Engineering Faculty of Mechanical Engineering University of Transport and Communications Hanoi Vietnam Mechanical and Power Engineering Faculty Electric Power University Hanoi Vietnam

Recent developments in autonomous vehicle technologies and applications gain a lot of interest by the public, as the popularity of both driver assistance and automated driving systems increase. One of the most promising aspect of the autonomous vehicle compared to conventional human driven vehicle is the increased level of safety. Machine learning techniques enables to achieve fast and efficient control actions compared to model based techniques. However, the advantages of a more conservative model based controller are their better robustness properties. In this paper a synergy of the two control philosophy is presented through a trajectory tracking control design for autonomous vehicles. A supervised reinforcement learning (RL) control method is introduced, where a robust Linear Parameter Varying (LPV) controller supervises the operation of the trained RL agent. Thus, in case sensor noise is detected, the guaranteed stability LPV controller takes over the steering control action. In order to demonstrate the operation of the proposed method, three different simulations have been evaluated and compared in CarSim simulation environment.

关键词： autonomous vehicle control supervised reinforcement learning trajectory tracking

来源：评论

学校读者我要写书评

暂无评论

EDGAR: An Autonomous Driving Research Platform – From Feature Development to Real-World Application

arXiv

引用

arXiv 2023年

作者： Karle, Phillip Betz, Tobias Bosk, Marcin Fent, Felix Gehrke, Nils Geisslinger, Maximilian Gressenbuch, Luis Hafemann, Philipp Huber, Sebastian Hübner, Maximilian Huch, Sebastian Kaljavesi, Gemb Kerbl, Tobias Kulmer, Dominik Maierhofer, Sebastian Mascetta, Tobias Pfab, Florian Rezabek, Filip Rivera, Esteban Sagmeister, Simon Seidlitz, Leander Sauerbeck, Florian Tahiraj, Ilir Trauth, Rainer Uhlemann, Nico Würsching, Gerald Zarrouki, Baha Althoff, Matthias Betz, Johannes Bengler, Klaus Carle, Georg Diermeyer, Frank Ott, Jörg Lienkamp, Markus Germany School of Computation Information and Technology Department of Computer Engineering Germany School of Computation Information and Technology Department of Computer Engineering Professorship Cyber-Physical Systems Cyprus School of Engineering and Design Department of Mechanical Engineering Germany School of Computation Information and Technology Department of Computer Engineering Chair of Network Architectures and Services Germany Germany Technical University of Munich Garching Germany

While current research and development of autonomous driving primarily focuses on developing new features and algorithms, the transfer from isolated software components into an entire software stack has been covered sparsely. Besides that, due to the complexity of autonomous software stacks and public road traffic, the optimal validation of entire stacks is an open research problem. Our paper focuses on these two aspects. We present our autonomous research vehicle EDGAR and its digital twin, a detailed virtual duplication of the vehicle. While the vehicle’s setup is closely related to the state of the art, its virtual duplication is a valuable contribution as it is crucial for a consistent validation process from simulation to real-world tests. In addition, different development teams can work with the same model, making integration and testing of software stacks much easier, significantly accelerating the development process. The real and virtual vehicles are embedded in a comprehensive development environment, which is also introduced. All parameters of the digital twin are provided open-source at https://***/TUMFTM/edgar_digital_twin. © 2023, CC BY.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

High Performance of Smart Refrigerator System Based on IoT Technique

High Performance of Smart Refrigerator System Based on IoT T...

引用

International Conference on Developments in esystems engineering (DESE)

作者： Hamid R. Alsanad Mohanad A. Al-Askari Khaldoon A. Omar Yousif Almashhadany Sameer Algburi Taisir A. Yaseen Department of Electrical Engineering University of Anbar Anbar Iraq Information Systems Department University of Anbar Anbar Iraq College of Engineering Al-Kitab University Kurkuk Iraq Computer Network Department University of Anbar Anbar Iraq

The Internet of Things (IoT) has made a significant impact on improving human life in the modern era, offering convenience and ease. Smart appliances, which are connected to the Internet, have become increasingly popular due to their improved efficiency, robustness, power consumption, and connectivity. The main objective of this paper is to convert a conventional refrigerator into an intelligent appliance by integrating computational intelligence using a microcontroller and a range of sensors. The proposed approach aims to improve food management capabilities by introducing automated techniques and cost-effective intelligence to the refrigerator. The resulting smart refrigerator is designed to be user-friendly and improve the overall quality of life. The system includes a mobile or web application that acts as a bridge between the refrigerator and the user, allowing for remote control and monitoring. The smart refrigerator employs sensors to detect shortages of items and can automatically place orders online or send messages to grocery stores for item delivery. Additionally, the smart module continuously monitors temperature and humidity levels, uploading real-time updates to a cloud platform for user access. The integration of IoT technology into refrigerators offers numerous features and benefits, ultimately enhancing convenience and efficiency in managing food storage and consumption.

关键词：

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：