2023 57th Annual Conference on Information Sciences and Systems (CISS)最新文献_第7页

ACRE: Actor Critic Reinforcement Learning for Failure-Aware Edge Computing Migrations 基于故障感知边缘计算迁移的Actor批评家强化学习

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089694

Marie Siew, Shikhar Sharma, Carlee Joe-Wong

{"title":"ACRE: Actor Critic Reinforcement Learning for Failure-Aware Edge Computing Migrations","authors":"Marie Siew, Shikhar Sharma, Carlee Joe-Wong","doi":"10.1109/CISS56502.2023.10089694","DOIUrl":"https://doi.org/10.1109/CISS56502.2023.10089694","url":null,"abstract":"In edge computing, users' service profiles are migrated in response to user mobility, to minimize the user-experienced delay, balanced against the migration cost. Due to imperfect information on transition probabilities and costs, reinforcement learning (RL) is often used to optimize service migration. Nevertheless, current works do not optimize service migration in light of occasional server failures. While server failures are rare, they impact the smooth and safe functioning of latency sensitive edge computing applications like autonomous driving and real-time obstacle detection, because users can no longer complete their computing jobs. As these failures occur at a low probability, it is difficult for RL algorithms, which are data and experience driven, to learn an optimal service migration policy for both the usual and rare event scenarios. Therefore, we propose an algorithm ImACRE, which integrates importance sampling into actor critic reinforcement learning, to learn the optimal service profile and backup placement policy. Our algorithm uses importance sampling to sample rare events in a simulator, at a rate proportional to their contribution to system costs, while balancing service migration trade-offs between delay and migration costs, with failure costs, backup placement and migration costs. We use trace driven experiments to show that our algorithm gives cost reductions in the event of failures.","PeriodicalId":243775,"journal":{"name":"2023 57th Annual Conference on Information Sciences and Systems (CISS)","volume":"141 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117042058","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}

引用次数: 0

A Decision Making Model Where the Cell Exhibits Maximum Detection Probability: Statistical Signal Detection Theory and Molecular Experimental Data 细胞显示最大检测概率的决策模型:统计信号检测理论和分子实验数据

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089677

A. Emadi, T. Lipniacki, A. Levchenko, A. Abdi

{"title":"A Decision Making Model Where the Cell Exhibits Maximum Detection Probability: Statistical Signal Detection Theory and Molecular Experimental Data","authors":"A. Emadi, T. Lipniacki, A. Levchenko, A. Abdi","doi":"10.1109/CISS56502.2023.10089677","DOIUrl":"https://doi.org/10.1109/CISS56502.2023.10089677","url":null,"abstract":"Molecular noise and signaling abnormalities in biochemical signaling systems in cells affect signaling events and consequently may alter cellular decision making results. Since unexpected and altered cellular decisions may contribute to the development of many pathological conditions and diseases, it is of interest to develop proper models to characterize and measure molecular signal detection parameters and cellular decisions. In this paper and using the Neyman-Pearson signal detection theorem, we propose a signal detection model in which the cell maximizes its signal detection probability in the presence of noise. To evaluate the usefulness of the proposed model, we use measured molecular experimental data of the important TNF-NF- $kappa mathbf{B}$ cell signaling system. Our results demonstrate that the proposed model provides biologically relevant findings. The introduced Neyman-Pearson-based molecular signal detection framework allows to systematically model and quantify the signal detection behavior and failure of molecular signaling systems, and compute their key decision making parameters such as detection and false alarm probabilities. With regard to the specific TNF-NF- $kappamathbf{B}$ system case study in this paper and given the high involvement of the transcription factor NF- $kappa mathbf{B}$ in cell survival, programmed cell death, immune signaling and stress response, the developed signal detection framework can serve as a useful tool to model the associated cell decision making processes.","PeriodicalId":243775,"journal":{"name":"2023 57th Annual Conference on Information Sciences and Systems (CISS)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131556100","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}

引用次数: 0

Secret Key Generation from MIMO Channel With or Without Reciprocity 有无互易的MIMO信道密钥生成

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089738

Y. Hua, Ahmed Maksud

引用次数: 1

Towards Equalization of Mixed Multi-user OFDM Signals Over a Doubly-Dispersive Channel 双色散信道中混合多用户OFDM信号的均衡研究

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089639

Kirsten Toland, Peter O. Taiwo, A. Cole-Rhodes

{"title":"Towards Equalization of Mixed Multi-user OFDM Signals Over a Doubly-Dispersive Channel","authors":"Kirsten Toland, Peter O. Taiwo, A. Cole-Rhodes","doi":"10.1109/CISS56502.2023.10089639","DOIUrl":"https://doi.org/10.1109/CISS56502.2023.10089639","url":null,"abstract":"This work explores the recovery of mixed signals, which have been transmitted by multiple users over a doubly-dispersive channel using OFDM modulation, and received by a multi-antenna system. We consider multiple users transmitting QPSK signal blocks over a shared OFDM frequency band and consider two cases, with respect to the location of signal data sources. The first case will involve collocated users transmitting blocks of QPSK signals to be received by the multi-antenna system, and the second case will involve non-collocated mobile users transmitting QPSK signal blocks to the multi-antenna system. On each OFDM subcarrier, transmitted symbols from multiple users are mixed thereby providing a low probability of interception (LPI) scenario. A modified OFDM receiver architecture is proposed and used to separate and recover these user signals at the base station. A Least square equalizer is applied to the signal data blocks at the receiver. These received signal blocks have also been corrupted by additive white Gaussian noise (AWGN) and inter-symbol interference (ISI) after transmission through a Rayleigh fading Doppler channel. The channel state information is estimated using pilots, and this gives a baseline performance of the proposed multi-user OFDM receiver.","PeriodicalId":243775,"journal":{"name":"2023 57th Annual Conference on Information Sciences and Systems (CISS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132049322","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}

引用次数: 0

Net Load Forecast based on Behind-the-Meter Disaggregation of Smart Meter Data 基于智能电表数据背后分解的净负荷预测

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089621

Mian Jia, Kang Pu, Yue Zhao

{"title":"Net Load Forecast based on Behind-the-Meter Disaggregation of Smart Meter Data","authors":"Mian Jia, Kang Pu, Yue Zhao","doi":"10.1109/CISS56502.2023.10089621","DOIUrl":"https://doi.org/10.1109/CISS56502.2023.10089621","url":null,"abstract":"As the penetration of behind-the-meter (BTM) rooftop solar energies continues to increase in power distribution systems, it is of paramount importance for load serving entities and system operators to forecast net loads in the system. In this paper, novel algorithms for training high-performance predictors for day-ahead net load forecasting are developed. Importantly, the overall method only utilizes metered net load data and does not require any monitoring data of solar generation. Methodologically, the net load data trace is disaggregated into estimated BTM solar and load traces, based on which separate predictors are then trained for solar generation and load forecasting exploiting their distinct natures, respectively. For solar generation forecasting, time data, weather forecast, and potentially solar irradiance forecast are used as input features of the predictor. For load forecasting, time data, weather forecast, and judiciously chosen load data in the recent past are used as input features of the predictor. The two predictors' outputs are combined to produce the final net load forecast. The developed method is comprehensively evaluated based on two real-world smart meter data sets from Ithaca, NY and Clifton park, NY, respectively. High accuracy of day-ahead net load forecast is demonstrated.","PeriodicalId":243775,"journal":{"name":"2023 57th Annual Conference on Information Sciences and Systems (CISS)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122329072","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}

引用次数: 0

Error Detection Strategies for CRC-Concatenated Polar Codes under Successive Cancellation List Decoding 逐次取消表译码下crc级联极化码的错误检测策略

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089769

Alexander Sauter, B. Matuz, G. Liva

引用次数: 2

SPSA-Based Switch Updating Algorithm for Constrained Stochastic Optimization 基于spsa的约束随机优化开关更新算法

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089743

Zhichao Jia, Ziyi Wei

引用次数: 0

An Overview of Quantum-Safe Approaches: Quantum Key Distribution and Post-Quantum Cryptography 量子安全方法综述:量子密钥分发和后量子密码学

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089619

Guobin Xu, Jianzhou Mao, Eric Sakk, S. Wang

引用次数: 4

Game and Prospect Theoretic Hardware Trojan Testing 博弈论与展望论硬件木马测试

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089630

Satyaki Nan, L. Njilla, Swastik Brahma, C. Kamhoua

引用次数: 0

Multi-Objective Design Optimization for Image Classification Using Elastic Neural Networks 基于弹性神经网络的图像分类多目标设计优化

2023 57th Annual Conference on Information Sciences and Systems (CISS) Pub Date : 2023-03-22 DOI: 10.1109/CISS56502.2023.10089753

Lei Pan, Yan Zhang, Yi Zhou, H. Huttunen, S. Bhattacharyya

{"title":"Multi-Objective Design Optimization for Image Classification Using Elastic Neural Networks","authors":"Lei Pan, Yan Zhang, Yi Zhou, H. Huttunen, S. Bhattacharyya","doi":"10.1109/CISS56502.2023.10089753","DOIUrl":"https://doi.org/10.1109/CISS56502.2023.10089753","url":null,"abstract":"Image classification is an essential challenge for many types of autonomous and smart systems. With advances in Convolutional Neural Networks (CNNs), the accuracy of image classification systems has been dramatically improved. However, due to the escalating complexity of state-of-the-art CNN solutions, significant challenges arise in implementing real-time image classification applications on resource-constrained platforms. The framework of elastic neural networks has been proposed to address trade-offs between classification accuracy and real-time performance by leveraging intermediate early-exits placed in deep CNNs and allowing systems to switch among multiple candidate outputs, while switching off inference layers that are not used by the selected output. In this paper, we propose a novel approach for configuring early-exit points when converting a deep CNN into an elastic neural network. The proposed approach is designed to systematically optimize the quality and diversity of the alternative CNN operating points that are provided by the derived elastic networks. We demonstrate the utility of the proposed elastic neural network approach on the CIFAR-100 dataset.","PeriodicalId":243775,"journal":{"name":"2023 57th Annual Conference on Information Sciences and Systems (CISS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134033560","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}

引用次数: 0