2022 IEEE Conference on Technologies for Sustainability (SusTech)最新文献_第3页

Anomaly detection at the apiary: predicting state and swarming preparation activity of honey bee colonies using low-cost sensor technology 蜂房异常检测:利用低成本传感器技术预测蜂群状态和蜂群准备活动

2022 IEEE Conference on Technologies for Sustainability (SusTech) Pub Date : 2022-04-21 DOI: 10.1109/SusTech53338.2022.9794223

Diren Senger, Carolin Johannsen, Thorsten Kluss

引用次数: 1

Architecture of an Innovative Route Planning System for Sustainable Commercial Vehicle Fleets 可持续商用车车队创新路线规划系统架构

2022 IEEE Conference on Technologies for Sustainability (SusTech) Pub Date : 2022-04-21 DOI: 10.1109/SusTech53338.2022.9794217

Florian Anghelache, D. Mitrea, N. Goga, A. Vasilățeanu, Vladut Radulescu, Diana Scurtu, D. Musat

引用次数: 1

Enhancing the Performance of Multi-Agent Reinforcement Learning for Controlling HVAC Systems 提高多智能体强化学习在暖通空调系统控制中的性能

2022 IEEE Conference on Technologies for Sustainability (SusTech) Pub Date : 2022-04-21 DOI: 10.1109/SusTech53338.2022.9794179

D. Bayer, M. Pruckner

{"title":"Enhancing the Performance of Multi-Agent Reinforcement Learning for Controlling HVAC Systems","authors":"D. Bayer, M. Pruckner","doi":"10.1109/SusTech53338.2022.9794179","DOIUrl":"https://doi.org/10.1109/SusTech53338.2022.9794179","url":null,"abstract":"Systems for heating, ventilation and air-conditioning (HVAC) of buildings are traditionally controlled by a rule-based approach. In order to reduce the energy consumption and the environmental impact of HVAC systems more advanced control methods such as reinforcement learning are promising. Reinforcement learning (RL) strategies offer a good alternative, as user feedback can be integrated more easily and presence can also be incorporated. Moreover, multi-agent RL approaches scale well and can be generalized. In this paper, we propose a multi-agent RL framework based on existing work that learns reducing on one hand energy consumption by optimizing HVAC control and on the other hand user feedback by occupants about uncomfortable room temperatures. Second, we show how to reduce training time required for proper RL-agent-training by using parameter sharing between the multiple agents and apply different pretraining techniques. Results show that our framework is capable of reducing the energy by around 6% when controlling a complete building or 8% for a single room zone. The occupants complaints are acceptable or even better compared to a rule-based baseline. Additionally, our performance analysis show that the training time can be drastically reduced by using parameter sharing.","PeriodicalId":434652,"journal":{"name":"2022 IEEE Conference on Technologies for Sustainability (SusTech)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127686989","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

Automated Identification of Used Beverage Cans for Deposit Return using Deep Learning Methods 基于深度学习方法的废旧饮料罐自动识别及押金返还

2022 IEEE Conference on Technologies for Sustainability (SusTech) Pub Date : 2022-04-21 DOI: 10.1109/SusTech53338.2022.9794235

Spencer Ploeger, Matthew Bolan, Lucas Dasovic

{"title":"Automated Identification of Used Beverage Cans for Deposit Return using Deep Learning Methods","authors":"Spencer Ploeger, Matthew Bolan, Lucas Dasovic","doi":"10.1109/SusTech53338.2022.9794235","DOIUrl":"https://doi.org/10.1109/SusTech53338.2022.9794235","url":null,"abstract":"Accurate sorting of recyclable materials, especially aluminum, is an important process within municipal Material Recovery Facilities (MRFs) as it has a high scrap value and is easily recycled, keeping it out of landfills. Additionally, in jurisdictions that have deposit return programs, MRF operators may return permitted cans and collect the higher deposit value, thus increasing profits. This interest in accurate sorting creates an ideal environment for computer vision and deep learning applications, specifically, the classification and sorting of cans with higher accuracy than human sorters, which are often central to this process. In this work, a can classification dataset was created following deposit return program definitions used in Ontario, Canada. The dataset contains images of returnable and non- returnable cans. Neural networks based on Mask R-CNN are then trained to classify can images as returnable or non-returnable. The neural networks achieve excellent results, with over 99% class accuracy on the testing dataset. Lastly, recommendations for future work and recommendations for system installation and integration are discussed.","PeriodicalId":434652,"journal":{"name":"2022 IEEE Conference on Technologies for Sustainability (SusTech)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116333108","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

Feasibility of achieving net-zero water usage through rainwater harvesting at big-box retailers 大型零售商通过收集雨水实现净零用水的可行性

2022 IEEE Conference on Technologies for Sustainability (SusTech) Pub Date : 2022-04-21 DOI: 10.1109/sustech53338.2022.9794224

Kurt Wurthmann

引用次数: 0

A Complete State Transition-Based Traffic Signal Control Using Deep Reinforcement Learning 基于深度强化学习的完全状态转换交通信号控制

2022 IEEE Conference on Technologies for Sustainability (SusTech) Pub Date : 2022-04-21 DOI: 10.1109/SusTech53338.2022.9794168

Shangru Liu, Guoyuan Wu, M. Barth

{"title":"A Complete State Transition-Based Traffic Signal Control Using Deep Reinforcement Learning","authors":"Shangru Liu, Guoyuan Wu, M. Barth","doi":"10.1109/SusTech53338.2022.9794168","DOIUrl":"https://doi.org/10.1109/SusTech53338.2022.9794168","url":null,"abstract":"Traffic signal control is a fundamental but challenging real-world problem that manages traffic at roadway intersections by adjusting signal timing and phases sequences. With the advances in emerging transportation technologies (e.g., Connected and Automated Vehicles, roadside sensing, drones), richer information (e.g., vehicle position, speed, type) has now become available in real-time, which can be utilized to reduce congestion. This paper introduces a deep reinforcement learning (DRL)-based traffic signal control (TSC) method for isolated intersections, where vehicles’ positions and speeds (available via V2I, roadside sensing, or drone-based surveillance) are processed by a convolution neural network (CNN) and fed into the RL system as inputs. In addition, a complete state transition process using a dual-ring mechanism is introduced to enable flexible traffic signal control. Using a traffic simulator (SUMO: Simulation of Urban Mobility), the proposed algorithm is compared with both fixed-time and actuated TSC under different traffic conditions. Results show that the DRL-based strategy can reduce average delay and pollutant emissions by 34.7% and 18.5%, respectively.","PeriodicalId":434652,"journal":{"name":"2022 IEEE Conference on Technologies for Sustainability (SusTech)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133991066","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

Resilience Metrics for Building-Level Electrical Distribution Systems with Energy Storage 具有储能的建筑级配电系统的弹性度量

2022 IEEE Conference on Technologies for Sustainability (SusTech) Pub Date : 2022-04-21 DOI: 10.1109/SusTech53338.2022.9794261

Spencer Hutchinson, Willy Bernal Heredia, Omkar A. Ghatpande

引用次数: 2

Analysis of Rainwater Harvesting Methods Considering the Impacts of Climate Change 考虑气候变化影响的雨水收集方法分析

2022 IEEE Conference on Technologies for Sustainability (SusTech) Pub Date : 2022-04-21 DOI: 10.1109/SusTech53338.2022.9794241

C. Monjardin, Anne Louie B. Ente, Gladys Mae G. Lorenzo

{"title":"Analysis of Rainwater Harvesting Methods Considering the Impacts of Climate Change","authors":"C. Monjardin, Anne Louie B. Ente, Gladys Mae G. Lorenzo","doi":"10.1109/SusTech53338.2022.9794241","DOIUrl":"https://doi.org/10.1109/SusTech53338.2022.9794241","url":null,"abstract":"Rainwater harvesting (RWH) has been practiced for a long time but only 4% of the total rainfall amount experienced in the Philippines is utilized. This study then explored on the impacts of climate change and the forecasted rainfall it could generate in a span of 30 years from 2020 – 2050. A local climate model was developed to forecast the annual rainfall for the next 30 years utilizing Representative Concentration Pathway Scenarios 2.6, 4.5, and 8.5. Extracting the minimum and maximum annual rainfall from the projected rainfall, the estimated net runoff was determined which is the study’s sole parameter along with a limited catchment area of 40 – 100 m2 in analyzing a RWH method in Barangay San Jose, Antipolo, Rizal. A range of estimated net runoff through the critical scenario of RCP 8.5 was known to be between 60.042 m3 – 234.409 m3 that could be harvested annually. The study has gathered the most common materials and usual capacities of the set collection devices (i.e. rain barrels/drums, tanks and cisterns) and their possible placements available and manufactured in the Philippines. Through the minimum net runoff, a 55-gallon Polyethylene (P.E) rain barrel/drum is suggested and at most, a 12,000-liter P.E/Stainless tank is suggested for the maximum net runoff. The study recommends that parameters like water demand, economy and reliability factors be taken into consideration for better analysis of appropriate RWH methods to be applied in a specific study area.","PeriodicalId":434652,"journal":{"name":"2022 IEEE Conference on Technologies for Sustainability (SusTech)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123529039","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

Incentivizing Distributed Energy Resource Participation in Grid Services 激励分布式能源参与电网服务

2022 IEEE Conference on Technologies for Sustainability (SusTech) Pub Date : 2022-04-21 DOI: 10.1109/SusTech53338.2022.9794228

Tylor E. Slay, J. Acken, R. Bass

{"title":"Incentivizing Distributed Energy Resource Participation in Grid Services","authors":"Tylor E. Slay, J. Acken, R. Bass","doi":"10.1109/SusTech53338.2022.9794228","DOIUrl":"https://doi.org/10.1109/SusTech53338.2022.9794228","url":null,"abstract":"The bulk power system is experiencing a dramatic shift as renewable generation growth continues to accelerate. Large-scale renewables adoption will help societies transition to a low-carbon, low-cost, and environmental-friendly electrical power system. However, the transition from a paradigm of generation following load to one where load follows generation will require large-scale interconnection and coordinated operation of Distributed Energy Resources (DERs), supported by open communication protocols. In this future grid scenario, DER aggregations will provide critical grid services that enable high penetration levels of renewable generation. This position paper presents an Energy Service Interface (ESI) that defines scope for ensuring secure, trustworthy information exchange between grid service providers and DERs. The goal of the ESI is to encourage large-scale participation of DERs in order to provide grid services through dispatch of DER aggregations. This position paper also presents an open smart energy communications protocol that allows DERs to advertise their characteristics and participate in grid services, within constraints established by the ESI. The paper presents several monetization incentives that grid service providers could use to encourage large-scale DER participation.","PeriodicalId":434652,"journal":{"name":"2022 IEEE Conference on Technologies for Sustainability (SusTech)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127300222","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: 6

Risk Index Spatial Clustering (RISC): Identifying High Risk Counties Using Local Moran’s I and Spatial Statistics for Natural Disaster Risk Management : Leveraging Spatial Tools for Dynamic Risk Assessment, Resilience Planning And Resource Management Across Spatial Scales 风险指数空间聚类(RISC):利用当地Moran 's I和自然灾害风险管理的空间统计识别高风险县:利用空间工具进行动态风险评估、弹性规划和跨空间尺度的资源管理

2022 IEEE Conference on Technologies for Sustainability (SusTech) Pub Date : 2022-04-21 DOI: 10.1109/SusTech53338.2022.9794200

Suraj Sheth

引用次数: 2