Proceedings of the 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation最新文献

筛选
英文 中文
FATEsys 2021: the first ACM SIGEnergy workshop on fair, accountable, transparent, and ethical (FATE) AI for smart environments and energy systems FATEsys 2021:首届ACM SIGEnergy研讨会,主题为智能环境和能源系统的公平、负责、透明和道德(FATE)人工智能
Milan Jain, P. Arjunan
{"title":"FATEsys 2021: the first ACM SIGEnergy workshop on fair, accountable, transparent, and ethical (FATE) AI for smart environments and energy systems","authors":"Milan Jain, P. Arjunan","doi":"10.1145/3486611.3492408","DOIUrl":"https://doi.org/10.1145/3486611.3492408","url":null,"abstract":"The advent of IoT, ubiquitous and smart sensing, and high performance computing has resulted in a big shift in the adoption of data-driven black-box modeling (also referred to as machine/deep learning) to make our environments smarter and energy systems efficient. Several studies have shown that these AI-enabled solutions for smart buildings, smart cities, smart grids, electric transportation, among others are much more accurate and efficient. However, these data-driven black-box solutions are rarely held accountable for the impact of their actions on the human in the loop which significantly impacts their real-world adoption. To truly conceptualize the idea of smart systems for everyone, it is critical to study these AI-enabled smart environments and energy systems for not just efficiency, but also for affordability and accessibility for all. The first ACM SIGEnergy workshop on Fair, Accountable, Transparent, and Ethical AI for Smart Environments and Energy Systems intends to bring together researchers from diverse backgrounds and discuss key issues, challenges, breakthroughs, and socio-economic impact in developing fair, accountable, transparent and ethical AI techniques for smart environments and energy systems.","PeriodicalId":412282,"journal":{"name":"Proceedings of the 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114689739","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
Marble: collaborative scheduling of batteryless sensors with meta reinforcement learning Marble:基于元强化学习的无电池传感器协同调度
Francesco Fraternali, Bharathan Balaji, Dezhi Hong, Yuvraj Agarwal, Rajesh K. Gupta
{"title":"Marble: collaborative scheduling of batteryless sensors with meta reinforcement learning","authors":"Francesco Fraternali, Bharathan Balaji, Dezhi Hong, Yuvraj Agarwal, Rajesh K. Gupta","doi":"10.1145/3486611.3486670","DOIUrl":"https://doi.org/10.1145/3486611.3486670","url":null,"abstract":"Batteryless energy-harvesting sensing systems are attractive for low maintenance but face challenges in real-world applications due to low quality of service from sporadic and unpredictable energy availability. To overcome this challenge, recent data-driven energy management techniques optimize energy usage to maximize application performance even in low harvested energy scenarios by learning energy availability patterns in the environment. These techniques require prior knowledge of the environment in which the sensor nodes are deployed to work correctly. In the absence of historical data, the application performance deteriorates. To overcome this challenge, we describe here the use of meta reinforcement learning to increase the application performance of newly deployed batteryless sensor nodes without historical data. Our system, called Marble, exploits information from other sensor node locations to expedite the learning of newly deployed sensor nodes, and improves application performance in the initial period of deployment. Our evaluation using real-world data traces shows that Marble detects up to 66% more events in low lighting conditions, and up to 25.6% more events on average on the first 3 days of deployment compared to the state-of-the-art.1","PeriodicalId":412282,"journal":{"name":"Proceedings of the 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121664166","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: 4
Towards equity in energy efficiency analyses 实现能源效率分析的公平性
John Wamburu, Emma Grazier, David E. Irwin, Christine Crago, P. Shenoy
{"title":"Towards equity in energy efficiency analyses","authors":"John Wamburu, Emma Grazier, David E. Irwin, Christine Crago, P. Shenoy","doi":"10.1145/3486611.3492411","DOIUrl":"https://doi.org/10.1145/3486611.3492411","url":null,"abstract":"The electric grid has begun a profound transition from primarily using carbon-intensive energy to instead using carbon-free renewable energy. In parallel, smart meters and other sensors are now providing us unparalleled visibility into the energy-efficiency of building and grid operations. Researchers are actively using building and grid energy data from these sensors to develop analytics techniques, e.g., using machine learning, that can improve energy-efficiency and facilitate the energy transition. Unfortunately, much of this research ignores the impact of these analytics on equity. That is, while current data analytics techniques may accurately identify energy-inefficiencies, they generally do not contextualize the underlying reasons for these inefficiencies. For example, data analytics that identify the most energy-inefficient homes might motivate new programs that target these homes for subsidies to improve energy-efficiency. However, the most energy-inefficient homes might also correlate with those with the highest income that have less need for subsidies, and engage in the most energy wasteful behavior. In contrast, the most energy-efficient homes might be the homes that can least afford to waste (or even use) energy. In this paper, we use an example from recent research to illustrate the inequity of state-of-the-art energy analytics, and argue that energy analytics research should elevate equity to a first-class concern.","PeriodicalId":412282,"journal":{"name":"Proceedings of the 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114606790","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: 3
Application of occupant behavior prediction model on residential big data analysis 居住者行为预测模型在住宅大数据分析中的应用
Yunjeong Mo, Dong Zhao
{"title":"Application of occupant behavior prediction model on residential big data analysis","authors":"Yunjeong Mo, Dong Zhao","doi":"10.1145/3486611.3491121","DOIUrl":"https://doi.org/10.1145/3486611.3491121","url":null,"abstract":"Occupant behavior is multifaceted, and a systematic approach is required to understand occupant behavior comprehensively. This research aims to define a structure of the relationship between energy consumption, building technology, and occupant behavior, using the Occupant Behavior Prediction Model. The model can predict and explain occupant energy usage-related activities. A machine learning approach is used to develop the model, and datasets from the American Time Use Survey (ATUS) are used to verify the model. The results show that the energy use activities with higher predictive performances are more stable and habitual compared to the ones with lower predictive performances. The prediction accuracy achieved by this model for these habitual activities reached as high as 99%. The findings imply that the building systems and control strategies need to be adjusted to accommodate habitual energy use behaviors, rather than changing the behaviors. In addition, educational interventions seem more effective on the less habitual behaviors, which often change.","PeriodicalId":412282,"journal":{"name":"Proceedings of the 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129350356","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: 1
SCHMEAR: scalable construction of holistic models for energy analysis from rooftops SCHMEAR:用于屋顶能源分析的可扩展整体模型的构建
Thomas R. Dougherty, Tianyuan Huang, Yirong Chen, Rishee K. Jain, R. Rajagopal
{"title":"SCHMEAR: scalable construction of holistic models for energy analysis from rooftops","authors":"Thomas R. Dougherty, Tianyuan Huang, Yirong Chen, Rishee K. Jain, R. Rajagopal","doi":"10.1145/3486611.3486666","DOIUrl":"https://doi.org/10.1145/3486611.3486666","url":null,"abstract":"As the world moves to decarbonize, the built environment commands attention for its intensity of energy consumption. Potential pathways for decarbonizing the built environment can be discovered through the aid of building energy modeling, which helps identify potential retrofit strategies and simulate integration with renewable energy sources. Energy modeling is complicated however, due to compound interactions between building materials, structural design, and urban form. Significant domain knowledge, modeling expertise, and extensive time investment are required for accurate modeling to accommodate this complexity. In this work, we explore the potential of accurately modeling building energy consumption at scale through the application of modern computer vision algorithms. We demonstrate that our computer vision system can accurately predict energy consumption through the extraction of meaningful features contained in satellite imagery. To accomplish this, we introduce a data-collection pipeline and a computer vision architecture to process satellite photos and contextual information from the urban texture. We also demonstrate a method of comparing the relative significance of the automatically extracted features in informing building decarbonization decision making and policy. Our results indicate that this approach reveals valuable insights into the dynamics of building energy consumption on the city scale and enables the rapid analysis of urban energy dynamics with readily available data.","PeriodicalId":412282,"journal":{"name":"Proceedings of the 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130387222","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: 5
Deep Q-network boosted with external knowledge for HVAC control 深度q -网络增强了外部知识的暖通空调控制
Khoder Jneid, S. Ploix, P. Reignier, P. Jallon
{"title":"Deep Q-network boosted with external knowledge for HVAC control","authors":"Khoder Jneid, S. Ploix, P. Reignier, P. Jallon","doi":"10.1145/3486611.3488731","DOIUrl":"https://doi.org/10.1145/3486611.3488731","url":null,"abstract":"Heating, ventilation, and air conditioning (HVAC) systems consume nearly 40% of the total energy consumption in developed countries. Traditional techniques such as rule based control (RBC) fail to control these systems in an optimal way. Model predictive control (MPC) has been widely explored in literature as well but it doesn't represent a practical solution due to the complexity of buildings' dynamics that it relies on. Recently, deep reinforcement learning (DRL) has shown great success in the domain of optimal control such as robotics and gaming. In this paper, we develop two model-free DRL approaches to optimize the energy consumption of an office while maintaining thermal comfort and good indoor air quality through controlling the radiator and the opening/closing of a window and a door existing in the office. The two DRL approaches belong to deep-Q network (DQN): the first approach represents a DQN agent with no knowledge of the environment and the second approach represents a DQN agent with initial knowledge of the environment: A hybrid approach DQN+RBC. The goal of having external knowledge in DQN agent is to boost convergence by exploiting the RBC rules. We evaluate the performance of these two approaches against an RBC approach through simulations using a physical model of the office's dynamics. Experiments show that the two DRL approaches succeeded to maintain better thermal comfort and better indoor air quality compared with RBC approach while consuming nearly the same energy. In addition, experiments demonstrate that the DQN with knowledge outperforms the DQN with no knowledge in the beginning and converges faster to the optimal value.","PeriodicalId":412282,"journal":{"name":"Proceedings of the 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126137567","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: 2
Toward explainable and interpretable building energy modelling: an explainable artificial intelligence approach 迈向可解释和可解释的建筑能源模型:可解释的人工智能方法
Wei Zhang, F. Liu, Yonggang Wen, B. Nee
{"title":"Toward explainable and interpretable building energy modelling: an explainable artificial intelligence approach","authors":"Wei Zhang, F. Liu, Yonggang Wen, B. Nee","doi":"10.1145/3486611.3491127","DOIUrl":"https://doi.org/10.1145/3486611.3491127","url":null,"abstract":"Building energy modelling is essential for the operation and optimization of energy systems. Existing efforts have focused on the model fidelity, which however should not be the only concern. Due to the lack of adequate understanding and trust in the model, many accurate energy models have not been deployed in the real world. In this article, we introduce explainability and interpretability into the building energy model. We first use partial dependence plots to explain and quantify the importance of features at a fine-grained level and reveal different importance change patterns with different feature values. We also use a surrogate-based approach to interpret the internal mechanism and decision-making process of the model. We show that the local mechanism interpretation is feasible when the surrogate is both accurate and explainable. Explanation and interpretation are visualized, to provide system users with intuitive and informative insights with multi-disciplinary discussions. Our research promotes the operation and optimization of building energy systems and supports the widespread adoption of energy systems based on machine learning.","PeriodicalId":412282,"journal":{"name":"Proceedings of the 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127473203","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: 3
Activity-aware privacy protection for smart water meters 智能水表的活动感知隐私保护
R. Cardell-Oliver, Harrison Carter-Turner
{"title":"Activity-aware privacy protection for smart water meters","authors":"R. Cardell-Oliver, Harrison Carter-Turner","doi":"10.1145/3486611.3486650","DOIUrl":"https://doi.org/10.1145/3486611.3486650","url":null,"abstract":"Identifying water end-uses from household meter readings yields valuable insights of commercial and environmental value for both customers and water providers. But smart water meter data may expose sensitive information about the activities of metered households. This paper considers the case where a water provider wishes to publish a database of household water meter traces to be used by water analysts for research and planning purposes. We consider the risks to privacy should an adversary gain access to this database, with the threat of uniquely identifying a household of interest and exposing their water use activities. Previous work shows that the effectiveness of privacy protection techniques is strongly domain and application dependent, but few privacy studies have considered smart water metering. This paper introduces a framework for activity-aware privacy protection for databases of household smart water meters and evaluates its effectiveness using real-world and synthetic datasets. We found that privacy-protection is strongly dependent on the type of activity. Aggregating readings protects households from disclosure of small scale and common activities. For individualistic, infrequent activities such as garden watering or clothes washing, we found that data-aware sampling of households and seasons offers the best protection.","PeriodicalId":412282,"journal":{"name":"Proceedings of the 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","volume":"705 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122987740","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: 3
Open set anomaly classification 开集异常分类
Marcel Dix, Reuben Borrison
{"title":"Open set anomaly classification","authors":"Marcel Dix, Reuben Borrison","doi":"10.1145/3486611.3491118","DOIUrl":"https://doi.org/10.1145/3486611.3491118","url":null,"abstract":"Anomaly classification can provide a discrimination of the type of anomaly at hand, that can help the user to narrow down the search space during troubleshooting. A limitation of most machine learning (ML) classification models is being under the closed set assumption and thereby failing to recognize unknown data. Literature refers to this issue as the Opens Set Recognition (OSR) problem. In this paper, the given use case is the detection of technical faults in HVAC systems in commercial buildings. Here, the OSR problem is of high relevance, because it is very unrealistic that all possible faults are already known beforehand. This paper proposes an ML pipeline for open set anomaly classification. To address the OSR problem, the pipeline makes use of three common neural network architecture models that successively build on each other, namely two autoencoders and one ANN classifier. The advantage of using common well-known models is the ease of implementation for solution developers. The validation is made against an HVAC dataset published by LBNL that contains 7 fault cases, where we assume 3 of them as unknown. Our validation results show that the proposed pipeline can significantly reduce the risk of false class predictions in the presence of unknown data.","PeriodicalId":412282,"journal":{"name":"Proceedings of the 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116833360","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: 2
Towards utility-aware privacy-preserving sensor data anonymization in distributed IoT 分布式物联网中公用事业感知隐私保护传感器数据匿名化
Xin Yang
{"title":"Towards utility-aware privacy-preserving sensor data anonymization in distributed IoT","authors":"Xin Yang","doi":"10.1145/3486611.3492389","DOIUrl":"https://doi.org/10.1145/3486611.3492389","url":null,"abstract":"With the increased deployment of Internet of Things (IoT) systems, there come multiple privacy concerns regarding how the sensor data is stored and processed. Our research aims to protect user privacy by developing distributed data anonymization techniques that obscure sensitive information in the raw sensor data before it is used by third-party applications. Since users may have different privacy requirements, we propose to leverage meta-learning to allow our model to adapt to various privacy-utility trade-offs. We will assess the efficacy of the proposed techniques on real-world datasets and design defense mechanisms against various adversaries.","PeriodicalId":412282,"journal":{"name":"Proceedings of the 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125851661","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: 2
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书