Pub Date : 2018-04-01DOI: 10.1109/IoTDI.2018.00029
Fanxin Kong, Xue Liu, Insup Lee
Charging stations have become indispensable infrastructure to support the rapid proliferation of electric vehicles (EVs). The operational scheme of charging stations is crucial to satisfy the stability of the power grid and the quality of service (QoS) to EV users. Most existing schemes target either of the two major operations: charging rate control and demand balancing. This partial focus overlooks the coupling relation between the two operations and thus causes the degradation on the grid stability or customer QoS. A thoughtful scheme should manage both operations together. A big challenge to design such a scheme is the aggregated uncertainty caused by their coupling relation. This uncertainty accumulates from three aspects: the renewable generators co-located with charging stations, the power load of other (or non-EV) consumers, and the charging demand arriving in the future. To handle this aggregated uncertainty, we propose a stochastic optimization based operational scheme. The scheme jointly manages charging rate control and demand balancing to satisfy both the grid stability and user QoS. Further, our scheme consists of two algorithms that we design for managing the two operations respectively. An appealing feature of our algorithms is that they have robust performance guarantees in terms of the prediction errors on these three aspects. Simulation results demonstrate the efficacy of the proposed operational scheme and also validate our theoretical results.
{"title":"Joint Rate Control and Demand Balancing for Electric Vehicle Charging","authors":"Fanxin Kong, Xue Liu, Insup Lee","doi":"10.1109/IoTDI.2018.00029","DOIUrl":"https://doi.org/10.1109/IoTDI.2018.00029","url":null,"abstract":"Charging stations have become indispensable infrastructure to support the rapid proliferation of electric vehicles (EVs). The operational scheme of charging stations is crucial to satisfy the stability of the power grid and the quality of service (QoS) to EV users. Most existing schemes target either of the two major operations: charging rate control and demand balancing. This partial focus overlooks the coupling relation between the two operations and thus causes the degradation on the grid stability or customer QoS. A thoughtful scheme should manage both operations together. A big challenge to design such a scheme is the aggregated uncertainty caused by their coupling relation. This uncertainty accumulates from three aspects: the renewable generators co-located with charging stations, the power load of other (or non-EV) consumers, and the charging demand arriving in the future. To handle this aggregated uncertainty, we propose a stochastic optimization based operational scheme. The scheme jointly manages charging rate control and demand balancing to satisfy both the grid stability and user QoS. Further, our scheme consists of two algorithms that we design for managing the two operations respectively. An appealing feature of our algorithms is that they have robust performance guarantees in terms of the prediction errors on these three aspects. Simulation results demonstrate the efficacy of the proposed operational scheme and also validate our theoretical results.","PeriodicalId":149725,"journal":{"name":"2018 IEEE/ACM Third International Conference on Internet-of-Things Design and Implementation (IoTDI)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123344421","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 : 2017-10-18DOI: 10.1109/IoTDI.2018.00025
M. Malekzadeh, R. Clegg, H. Haddadi
An increasing number of sensors on mobile, Internet of things (IoT), and wearable devices generate time-series measurements of physical activities. Though access to the sensory data is critical to the success of many beneficial applications such as health monitoring or activity recognition, a wide range of potentially sensitive information about the individuals can also be discovered through access to sensory data and this cannot easily be protected using traditional privacy approaches. In this paper, we propose a privacy-preserving sensing framework for managing access to time-series data in order to provide utility while protecting individuals' privacy. We introduce Replacement AutoEncoder, a novel feature-learning algorithm which learns how to transform discriminative features of multi-variate time-series that correspond to sensitive inferences, into some features that have been more observed in non-sensitive inferences, to protect users' privacy. This efficiency is achieved by defining a user-customized objective function for deep autoencoders. Replacement will not only eliminate the possibility of recognition sensitive inferences, it also eliminates the possibility of detecting the occurrence of them, that is the main weakness of other approaches such as filtering or randomization. We evaluate the efficacy of the algorithm with an activity recognition task in a multi-sensing environment using extensive experiments on three benchmark datasets. We show that it can retain the recognition accuracy of state-of-the-art techniques while simultaneously preserving the privacy of sensitive information. Finally, we utilize the GANs for detecting the occurrence of replacement, after releasing data, and show that this can be done only if the adversarial network is trained on the users' original data.
{"title":"Replacement AutoEncoder: A Privacy-Preserving Algorithm for Sensory Data Analysis","authors":"M. Malekzadeh, R. Clegg, H. Haddadi","doi":"10.1109/IoTDI.2018.00025","DOIUrl":"https://doi.org/10.1109/IoTDI.2018.00025","url":null,"abstract":"An increasing number of sensors on mobile, Internet of things (IoT), and wearable devices generate time-series measurements of physical activities. Though access to the sensory data is critical to the success of many beneficial applications such as health monitoring or activity recognition, a wide range of potentially sensitive information about the individuals can also be discovered through access to sensory data and this cannot easily be protected using traditional privacy approaches. In this paper, we propose a privacy-preserving sensing framework for managing access to time-series data in order to provide utility while protecting individuals' privacy. We introduce Replacement AutoEncoder, a novel feature-learning algorithm which learns how to transform discriminative features of multi-variate time-series that correspond to sensitive inferences, into some features that have been more observed in non-sensitive inferences, to protect users' privacy. This efficiency is achieved by defining a user-customized objective function for deep autoencoders. Replacement will not only eliminate the possibility of recognition sensitive inferences, it also eliminates the possibility of detecting the occurrence of them, that is the main weakness of other approaches such as filtering or randomization. We evaluate the efficacy of the algorithm with an activity recognition task in a multi-sensing environment using extensive experiments on three benchmark datasets. We show that it can retain the recognition accuracy of state-of-the-art techniques while simultaneously preserving the privacy of sensitive information. Finally, we utilize the GANs for detecting the occurrence of replacement, after releasing data, and show that this can be done only if the adversarial network is trained on the users' original data.","PeriodicalId":149725,"journal":{"name":"2018 IEEE/ACM Third International Conference on Internet-of-Things Design and Implementation (IoTDI)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116554688","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 : 2017-03-01DOI: 10.1109/IoTDI.2018.00024
S. S. Rodríguez, Liang Wang, Jianxin R. Zhao, R. Mortier, H. Haddadi
Many current Internet services rely on inferences from models trained on user data. Commonly, both the training and inference tasks are carried out using cloud resources fed by personal data collected at scale from users. Holding and using such large collections of personal data in the cloud creates privacy risks to the data subjects, but is currently required for users to benefit from such services. We explore how to provide for model training and inference in a system where computation is pushed to the data in preference to moving data to the cloud, obviating many current privacy risks. Specifically, we take an initial model learnt from a small set of users and retrain it locally using data from a single user. We evaluate on two tasks: one supervised learning task, using a neural network to recognise users' current activity from accelerometer traces; and one unsupervised learning task, identifying topics in a large set of documents. In both cases the accuracy is improved. We also analyse the robustness of our approach against adversarial attacks, as well as its feasibility by presenting a performance evaluation on a representative resource-constrained device (a Raspberry Pi).
{"title":"Privacy-Preserving Personal Model Training","authors":"S. S. Rodríguez, Liang Wang, Jianxin R. Zhao, R. Mortier, H. Haddadi","doi":"10.1109/IoTDI.2018.00024","DOIUrl":"https://doi.org/10.1109/IoTDI.2018.00024","url":null,"abstract":"Many current Internet services rely on inferences from models trained on user data. Commonly, both the training and inference tasks are carried out using cloud resources fed by personal data collected at scale from users. Holding and using such large collections of personal data in the cloud creates privacy risks to the data subjects, but is currently required for users to benefit from such services. We explore how to provide for model training and inference in a system where computation is pushed to the data in preference to moving data to the cloud, obviating many current privacy risks. Specifically, we take an initial model learnt from a small set of users and retrain it locally using data from a single user. We evaluate on two tasks: one supervised learning task, using a neural network to recognise users' current activity from accelerometer traces; and one unsupervised learning task, identifying topics in a large set of documents. In both cases the accuracy is improved. We also analyse the robustness of our approach against adversarial attacks, as well as its feasibility by presenting a performance evaluation on a representative resource-constrained device (a Raspberry Pi).","PeriodicalId":149725,"journal":{"name":"2018 IEEE/ACM Third International Conference on Internet-of-Things Design and Implementation (IoTDI)","volume":"20 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130960117","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 : 1900-01-01DOI: 10.1109/IoTDI.2018.00015
Hang Qiu, Xiaochen Liu, S. Rallapalli, Archith J. Bency, Kevin Chan, Rahul Urgaonkar, B. S. Manjunath, R. Govindan
In the future, the video-enabled camera will be the most pervasive type of sensor in the Internet of Things. Such cameras will enable continuous surveillance through heterogeneous camera networks consisting of fixed camera systems as well as cameras on mobile devices. The challenge in these networks is to enable efficient video analytics: the ability to process videos cheaply and quickly to enable searching for specific events or sequences of events. In this paper, we discuss the design and implementation of Kestrel, a video analytics system that tracks the path of vehicles across a heterogeneous camera network. In Kestrel, fixed camera feeds are processed on the cloud, and mobile devices are invoked only to resolve ambiguities in vehicle tracks. Kestrel's mobile device pipeline detects objects using a deep neural network, extracts attributes using cheap visual features, and resolves path ambiguities by careful association of vehicle visual descriptors, while using several optimizations to conserve energy and reduce latency. Our evaluations show that Kestrel can achieve precision and recall comparable to a fixed camera network of the same size and topology, while reducing energy usage on mobile devices by more than an order of magnitude.
{"title":"Kestrel: Video Analytics for Augmented Multi-Camera Vehicle Tracking","authors":"Hang Qiu, Xiaochen Liu, S. Rallapalli, Archith J. Bency, Kevin Chan, Rahul Urgaonkar, B. S. Manjunath, R. Govindan","doi":"10.1109/IoTDI.2018.00015","DOIUrl":"https://doi.org/10.1109/IoTDI.2018.00015","url":null,"abstract":"In the future, the video-enabled camera will be the most pervasive type of sensor in the Internet of Things. Such cameras will enable continuous surveillance through heterogeneous camera networks consisting of fixed camera systems as well as cameras on mobile devices. The challenge in these networks is to enable efficient video analytics: the ability to process videos cheaply and quickly to enable searching for specific events or sequences of events. In this paper, we discuss the design and implementation of Kestrel, a video analytics system that tracks the path of vehicles across a heterogeneous camera network. In Kestrel, fixed camera feeds are processed on the cloud, and mobile devices are invoked only to resolve ambiguities in vehicle tracks. Kestrel's mobile device pipeline detects objects using a deep neural network, extracts attributes using cheap visual features, and resolves path ambiguities by careful association of vehicle visual descriptors, while using several optimizations to conserve energy and reduce latency. Our evaluations show that Kestrel can achieve precision and recall comparable to a fixed camera network of the same size and topology, while reducing energy usage on mobile devices by more than an order of magnitude.","PeriodicalId":149725,"journal":{"name":"2018 IEEE/ACM Third International Conference on Internet-of-Things Design and Implementation (IoTDI)","volume":"278 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120894005","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：