Pub Date : 2023-10-19DOI: 10.1007/s10606-023-09481-8
Silja Martikainen, Laura Kohonen-Aho, Niina Seittenranta, Emilia Makkonen, Mari Falcon, Valtteri Wikström, Katri Saarikivi
Abstract Empathic responding matters in face-to-face medical consultations. We have previously shown that patients' perceptions of doctor empathy also support positive experiences at an online clinic. However, there is still little knowledge about what types of communication influence patients’ online experiences of empathy. In this study we investigated text-based patient-doctor discourse at an online clinic using an adaptation of the Roter Interaction Analysis System (RIAS). Our aims were 1) to assess the reliability of the adapted RIAS 2) to investigate what characteristics are common during the text-based consultations and 3) to examine how the doctor’s discourse relates to the patients’ experience of empathy online. Based on the inter-rater reliability analyses the conversational clusters of Social ( ρ = 0.950), Biomedical ( ρ = 0.939), and Technology related talk ( ρ = 0.833), Procedural statements ( ρ = 0.693) and Agreement ( ρ = 0.687) were rated with acceptable reliability. Biomedical topics were most common in both patients’ and doctors’ communication. Patients’ experience of doctors’ empathy was positively correlated with the amount of doctor’s psychosocial talk and procedural statements although the effect sizes were small ( ρ < 0.30 for all models). These results encourage the use of personal talk and giving clear instructions to patients about the care process at a text-based online clinic focusing on brief consultations.
{"title":"Text-based Patient – Doctor Discourse Online And Patients’ Experiences of Empathy","authors":"Silja Martikainen, Laura Kohonen-Aho, Niina Seittenranta, Emilia Makkonen, Mari Falcon, Valtteri Wikström, Katri Saarikivi","doi":"10.1007/s10606-023-09481-8","DOIUrl":"https://doi.org/10.1007/s10606-023-09481-8","url":null,"abstract":"Abstract Empathic responding matters in face-to-face medical consultations. We have previously shown that patients' perceptions of doctor empathy also support positive experiences at an online clinic. However, there is still little knowledge about what types of communication influence patients’ online experiences of empathy. In this study we investigated text-based patient-doctor discourse at an online clinic using an adaptation of the Roter Interaction Analysis System (RIAS). Our aims were 1) to assess the reliability of the adapted RIAS 2) to investigate what characteristics are common during the text-based consultations and 3) to examine how the doctor’s discourse relates to the patients’ experience of empathy online. Based on the inter-rater reliability analyses the conversational clusters of Social ( ρ = 0.950), Biomedical ( ρ = 0.939), and Technology related talk ( ρ = 0.833), Procedural statements ( ρ = 0.693) and Agreement ( ρ = 0.687) were rated with acceptable reliability. Biomedical topics were most common in both patients’ and doctors’ communication. Patients’ experience of doctors’ empathy was positively correlated with the amount of doctor’s psychosocial talk and procedural statements although the effect sizes were small ( ρ < 0.30 for all models). These results encourage the use of personal talk and giving clear instructions to patients about the care process at a text-based online clinic focusing on brief consultations.","PeriodicalId":51008,"journal":{"name":"Computer Supported Cooperative Work-The Journal of Collaborative Computing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135730924","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-07DOI: 10.1007/s10606-023-09482-7
Maria Murray, Nadia Pantidi, John McCarthy
{"title":"Agency, Power and Confrontation: the Role for Socially Engaged Art in CSCW with Rurban Communities in Support of Inclusion","authors":"Maria Murray, Nadia Pantidi, John McCarthy","doi":"10.1007/s10606-023-09482-7","DOIUrl":"https://doi.org/10.1007/s10606-023-09482-7","url":null,"abstract":"","PeriodicalId":51008,"journal":{"name":"Computer Supported Cooperative Work-The Journal of Collaborative Computing","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135253583","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-30DOI: 10.1007/s10606-023-09480-9
Brit Ross Winthereik
Abstract This paper examines how the intense focus on data in political digitalization strategies takes effect in practice in a Danish municipality. Building on an ethnographic study of data-driven management, the paper argues that one of the effects of making data a driver for organizational decision-making is uncertainty as to what data are and can be taken to mean. While in political discourse and strategies, data are considered as a resource for collaboration across organizational units as well as for optimization of their performance, in practice, data are not this straightforward entity. The paper presents a kind of data work that identifies data as part of different worlds (ontologies). The management task that results from this is nurturing organizational spaces that articulate data as relational. The paper argues that being attentive to the troublesome experiences public sector employees have when encountering data may help mitigate some of the risks of seeing data merely as a resource. The paper concludes that as public sector managers learn to nurture spaces where differences in data can be articulated, they also protect core values of welfare bureaucracies. Acknowledging that data work is about what we take to be real and what not (ontological work) is a first step in this direction.
{"title":"Data as Relation: Ontological Trouble in the Data-Driven Public Administration","authors":"Brit Ross Winthereik","doi":"10.1007/s10606-023-09480-9","DOIUrl":"https://doi.org/10.1007/s10606-023-09480-9","url":null,"abstract":"Abstract This paper examines how the intense focus on data in political digitalization strategies takes effect in practice in a Danish municipality. Building on an ethnographic study of data-driven management, the paper argues that one of the effects of making data a driver for organizational decision-making is uncertainty as to what data are and can be taken to mean. While in political discourse and strategies, data are considered as a resource for collaboration across organizational units as well as for optimization of their performance, in practice, data are not this straightforward entity. The paper presents a kind of data work that identifies data as part of different worlds (ontologies). The management task that results from this is nurturing organizational spaces that articulate data as relational. The paper argues that being attentive to the troublesome experiences public sector employees have when encountering data may help mitigate some of the risks of seeing data merely as a resource. The paper concludes that as public sector managers learn to nurture spaces where differences in data can be articulated, they also protect core values of welfare bureaucracies. Acknowledging that data work is about what we take to be real and what not (ontological work) is a first step in this direction.","PeriodicalId":51008,"journal":{"name":"Computer Supported Cooperative Work-The Journal of Collaborative Computing","volume":"219 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136341682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-24DOI: 10.1109/CSCWD57460.2023.10152735
Jifan Shen, Yuling Sun
With the fast growth of aging population and the spread of various chronic diseases such as heart disease and arthritis among older adults, elderly care has become an urgent topic facing today’s society. Consequently, technologies mediated remote care has become a widely-used method, with the significant promise of reducing cost and improving the efficiency and quality of healthcare. Yet, most remote-caring technologies, especially surveillance video based remote care, face the challenge of privacy issues. For addressing this issue, this paper proposes a privacy- preserved remote care method. Specially, we use ROMP to extract the 3D human model of the elderly in the surveillance video, and use KNN pose estimation algorithm to detect the potential abnormal behaviors. Compared to existing methods, which mainly replace the privacy information with totally different contents, our method not only protects the personal privacy information of the elderly, but also provides clear and identifiable posture information which could better support remote care.
{"title":"Privacy-Preserved Video Monitoring Method with 3D Human Pose Estimation","authors":"Jifan Shen, Yuling Sun","doi":"10.1109/CSCWD57460.2023.10152735","DOIUrl":"https://doi.org/10.1109/CSCWD57460.2023.10152735","url":null,"abstract":"With the fast growth of aging population and the spread of various chronic diseases such as heart disease and arthritis among older adults, elderly care has become an urgent topic facing today’s society. Consequently, technologies mediated remote care has become a widely-used method, with the significant promise of reducing cost and improving the efficiency and quality of healthcare. Yet, most remote-caring technologies, especially surveillance video based remote care, face the challenge of privacy issues. For addressing this issue, this paper proposes a privacy- preserved remote care method. Specially, we use ROMP to extract the 3D human model of the elderly in the surveillance video, and use KNN pose estimation algorithm to detect the potential abnormal behaviors. Compared to existing methods, which mainly replace the privacy information with totally different contents, our method not only protects the personal privacy information of the elderly, but also provides clear and identifiable posture information which could better support remote care.","PeriodicalId":51008,"journal":{"name":"Computer Supported Cooperative Work-The Journal of Collaborative Computing","volume":"98 1","pages":"1502-1507"},"PeriodicalIF":2.4,"publicationDate":"2023-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90307105","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-24DOI: 10.1109/CSCWD57460.2023.10152807
Yuzhang Wu, Beilun Wang
Nowadays, with the popularity of the federated learning, it becomes crucial for us to tackle the challenges, communication cost and model robustness. And targeting at the communication bottleneck, data compression is widely used to solve the problem. Besides, the usage of variance reduction for achieving robustness and communication compression for reducing costs has been studied. The Byz-VR-MARINA pro- posed before uses random-sparsification. In this paper, we adopt the absolute compressors hard-threshold and propose a robust compressed framework Byz-VR-BARRY. Experimental results on w8a and a9a datasets have shown the effectiveness of our method, which can decrease the optimality gap obviously.
{"title":"A Framework Using Absolute Compression Hard-Threshold for Improving The Robustness of Federated Learning Model","authors":"Yuzhang Wu, Beilun Wang","doi":"10.1109/CSCWD57460.2023.10152807","DOIUrl":"https://doi.org/10.1109/CSCWD57460.2023.10152807","url":null,"abstract":"Nowadays, with the popularity of the federated learning, it becomes crucial for us to tackle the challenges, communication cost and model robustness. And targeting at the communication bottleneck, data compression is widely used to solve the problem. Besides, the usage of variance reduction for achieving robustness and communication compression for reducing costs has been studied. The Byz-VR-MARINA pro- posed before uses random-sparsification. In this paper, we adopt the absolute compressors hard-threshold and propose a robust compressed framework Byz-VR-BARRY. Experimental results on w8a and a9a datasets have shown the effectiveness of our method, which can decrease the optimality gap obviously.","PeriodicalId":51008,"journal":{"name":"Computer Supported Cooperative Work-The Journal of Collaborative Computing","volume":"22 1","pages":"1106-1111"},"PeriodicalIF":2.4,"publicationDate":"2023-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90192671","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-24DOI: 10.1109/CSCWD57460.2023.10152769
Yang Wang, Jiayan Xiang, Hangyu Cheng, Wanjun Chen, Yong Xiao, Guosheng Kang
With the wide adoption of Web APIs released on Internet, users tend to reuse them for business requirements or software development. Mashup is a useful technology for composing Web APIs into a new and value-added application. With the increasing number of Web APIs and Mashups, the API-Mashup ecosystem has emerged based on the invocation relationship between Mashups and Web APIs. In this paper, we take ProgrammableWeb, a typical API-Mashup ecosystem, as an example to investigate its dynamic evolutionary analysis. Although there have been some works on the API-Mashup ecosystem, they mainly focus on static analysis, i.e., the static characteristics of the API- Mashup ecosystem on a fixed time point. This paper conducts a comprehensive study on the dynamic evolutionary analysis of the API-Mashup ecosystem with a long time range from 2005 to 2021. First, we conduct a dynamic statistical analysis based on the API-Mashup ecosystem dataset. Next, we construct two cooperation networks, one between Web APIs, and the other between their categories. And the general characteristics of the two cooperation networks are presented. Finally, we investigate the derived cooperation networks from four perspectives: dynamic characteristics, degree distribution, betweenness centrality, and assortative mixing. Meanwhile, the corresponding insights are uncovered. Our work provides a foundation for visualization and understanding of the API-Mashup ecosystem from the timeline.
{"title":"Towards Dynamic Evolutionary Analysis of ProgrammableWeb for API-Mashup Ecosystem","authors":"Yang Wang, Jiayan Xiang, Hangyu Cheng, Wanjun Chen, Yong Xiao, Guosheng Kang","doi":"10.1109/CSCWD57460.2023.10152769","DOIUrl":"https://doi.org/10.1109/CSCWD57460.2023.10152769","url":null,"abstract":"With the wide adoption of Web APIs released on Internet, users tend to reuse them for business requirements or software development. Mashup is a useful technology for composing Web APIs into a new and value-added application. With the increasing number of Web APIs and Mashups, the API-Mashup ecosystem has emerged based on the invocation relationship between Mashups and Web APIs. In this paper, we take ProgrammableWeb, a typical API-Mashup ecosystem, as an example to investigate its dynamic evolutionary analysis. Although there have been some works on the API-Mashup ecosystem, they mainly focus on static analysis, i.e., the static characteristics of the API- Mashup ecosystem on a fixed time point. This paper conducts a comprehensive study on the dynamic evolutionary analysis of the API-Mashup ecosystem with a long time range from 2005 to 2021. First, we conduct a dynamic statistical analysis based on the API-Mashup ecosystem dataset. Next, we construct two cooperation networks, one between Web APIs, and the other between their categories. And the general characteristics of the two cooperation networks are presented. Finally, we investigate the derived cooperation networks from four perspectives: dynamic characteristics, degree distribution, betweenness centrality, and assortative mixing. Meanwhile, the corresponding insights are uncovered. Our work provides a foundation for visualization and understanding of the API-Mashup ecosystem from the timeline.","PeriodicalId":51008,"journal":{"name":"Computer Supported Cooperative Work-The Journal of Collaborative Computing","volume":"104 1","pages":"1716-1721"},"PeriodicalIF":2.4,"publicationDate":"2023-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73368830","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-24DOI: 10.1109/CSCWD57460.2023.10152753
Bing Shi, Wenan Tan, Pengfei Yu
Contrastive self-supervised learning (SSL) based Sequential Recommendations (SR) have recently achieved significant performance improvements in addressing the data sparsity problem, which hinders learning high-quality user representations. However, current contrastive SSL based models ignore the importance of consistency between sample pairs. Consistency means the similarity degree between the feature representation of encoded sample pairs, and the higher the consistency, the better the feature learning. To figure out the benefits of consistency and utilize it effectively, Momentum Contrastive Learning for Sequential Recommendation (MCL4SRec) is designed. Existing experiments on four public datasets demonstrate the superiority of MCL4SRec, which achieves state-of-the-art performance over existing baselines.
{"title":"Momentum Contrastive Learning for Sequential Recommendation","authors":"Bing Shi, Wenan Tan, Pengfei Yu","doi":"10.1109/CSCWD57460.2023.10152753","DOIUrl":"https://doi.org/10.1109/CSCWD57460.2023.10152753","url":null,"abstract":"Contrastive self-supervised learning (SSL) based Sequential Recommendations (SR) have recently achieved significant performance improvements in addressing the data sparsity problem, which hinders learning high-quality user representations. However, current contrastive SSL based models ignore the importance of consistency between sample pairs. Consistency means the similarity degree between the feature representation of encoded sample pairs, and the higher the consistency, the better the feature learning. To figure out the benefits of consistency and utilize it effectively, Momentum Contrastive Learning for Sequential Recommendation (MCL4SRec) is designed. Existing experiments on four public datasets demonstrate the superiority of MCL4SRec, which achieves state-of-the-art performance over existing baselines.","PeriodicalId":51008,"journal":{"name":"Computer Supported Cooperative Work-The Journal of Collaborative Computing","volume":"44 1","pages":"107-112"},"PeriodicalIF":2.4,"publicationDate":"2023-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73789280","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-24DOI: 10.1109/CSCWD57460.2023.10152614
Xiaolong Xu, Qun Ding, Lichen Lin
With the increase of car ownership in China, the problem of difficult parking in cities has become more and more serious. In large parking garage, finding an ideal parking space has become a daily problem for people; especially during the peak usage period of parking garage, a large number of vehicles will be driven into the parking garage, which will bring congestion, and at the same time, the demand of a large number of users in the area will lead to network congestion under 4G network, and users cannot access the network to check and find parking spaces. Therefore, this paper proposes a global optimal navigation mechanism with 5G network based on the above mentioned problems by analyzing the congestion situation during the peak usage of the parking garage. This mechanism uses an optimal parking space selection model and a global optimal scheduling model that can avoid congestion. Based on the model proposed in this paper, we construct a navigation planning system based on mobile, front-end and back-end. With the ultra-low latency, ultrahigh transmission efficiency and reliability of 5G network, the mobile port can select the optimal parking space according to the user's preference, and the back-end can show the parking space and congestion in the parking garage in real time according to the actual situation of the parking garage. Finally, the performance of the model and system proposed in this paper is verified through experiments.
{"title":"Indoor Navigation Mechanism based on 5G network for Large Parking Garage","authors":"Xiaolong Xu, Qun Ding, Lichen Lin","doi":"10.1109/CSCWD57460.2023.10152614","DOIUrl":"https://doi.org/10.1109/CSCWD57460.2023.10152614","url":null,"abstract":"With the increase of car ownership in China, the problem of difficult parking in cities has become more and more serious. In large parking garage, finding an ideal parking space has become a daily problem for people; especially during the peak usage period of parking garage, a large number of vehicles will be driven into the parking garage, which will bring congestion, and at the same time, the demand of a large number of users in the area will lead to network congestion under 4G network, and users cannot access the network to check and find parking spaces. Therefore, this paper proposes a global optimal navigation mechanism with 5G network based on the above mentioned problems by analyzing the congestion situation during the peak usage of the parking garage. This mechanism uses an optimal parking space selection model and a global optimal scheduling model that can avoid congestion. Based on the model proposed in this paper, we construct a navigation planning system based on mobile, front-end and back-end. With the ultra-low latency, ultrahigh transmission efficiency and reliability of 5G network, the mobile port can select the optimal parking space according to the user's preference, and the back-end can show the parking space and congestion in the parking garage in real time according to the actual situation of the parking garage. Finally, the performance of the model and system proposed in this paper is verified through experiments.","PeriodicalId":51008,"journal":{"name":"Computer Supported Cooperative Work-The Journal of Collaborative Computing","volume":"13 1","pages":"588-593"},"PeriodicalIF":2.4,"publicationDate":"2023-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80012432","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-24DOI: 10.1109/CSCWD57460.2023.10152762
Emilly Marques Da Silva, António Correia, Claudio Miceli, D. Schneider
In this scoping review, we aim to summarize and analyze the latest persuasive design research developments for smart bins. This study initially collected data from 551 scientific papers, and later, based on a selection process, 13 papers that mainly focused on handling smart bins through persuasive designs were included in the final analysis. These 13 papers were rated by four characteristics: research specifications, methodologies, persuasive strategies, and adopted technologies. We argue that, to understand how to design cyber-physical systems for waste management that involve the cooperation of civil society, a promising path includes unraveling how persuasive smart bins designs are being developed and identifying the challenges and opportunities that exist for waste management in cyber-physical collaborative environments, at the intersection of person, place, and technology.
{"title":"Understanding the Support of IoT and Persuasive Technology for Smart Bin Design: A Scoping Review","authors":"Emilly Marques Da Silva, António Correia, Claudio Miceli, D. Schneider","doi":"10.1109/CSCWD57460.2023.10152762","DOIUrl":"https://doi.org/10.1109/CSCWD57460.2023.10152762","url":null,"abstract":"In this scoping review, we aim to summarize and analyze the latest persuasive design research developments for smart bins. This study initially collected data from 551 scientific papers, and later, based on a selection process, 13 papers that mainly focused on handling smart bins through persuasive designs were included in the final analysis. These 13 papers were rated by four characteristics: research specifications, methodologies, persuasive strategies, and adopted technologies. We argue that, to understand how to design cyber-physical systems for waste management that involve the cooperation of civil society, a promising path includes unraveling how persuasive smart bins designs are being developed and identifying the challenges and opportunities that exist for waste management in cyber-physical collaborative environments, at the intersection of person, place, and technology.","PeriodicalId":51008,"journal":{"name":"Computer Supported Cooperative Work-The Journal of Collaborative Computing","volume":"96 1","pages":"193-198"},"PeriodicalIF":2.4,"publicationDate":"2023-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80208409","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-24DOI: 10.1109/CSCWD57460.2023.10152783
Yunsong Xiang, Xuemei Yang, Y. Sun, Hong Luo
With the promotion of cloud computing, a large number of hardware and software systems in the cloud bring massive and complex operation and maintenance (O&M) work. To ensure the O&M efficiency of IT infrastructures, it is necessary to implement automatic and reliable scheduling for the directed acyclic graph (DAG) workflow which is composed of multiple O&M tasks. Considering the changing status of networks and machines in the cloud and the position constraints that some tasks must be executed on the specified machines in some O&M scenarios, we propose a novel workflow scheduling approach based on Deep Reinforcement Learning (DRL) to minimize the workflow execution makespan and implement the fault tolerance with the position constraints of tasks execution. In our proposal, we first design a fault-tolerant mechanism according to the reliability requirement and the probability distributions of the machine failure parameters with consideration of different failure rates in the heterogeneous environment. Then, we employ proximal policy optimization (PPO) to optimize the task scheduling strategy and ensure the strategy to satisfy the position constraints of tasks execution by action masking in proximal policy optimization. The experimental results show that our proposal can effectively reduce the makespan of the fault-tolerant workflow on the premise of 99.9% reliability.
{"title":"A Fault-tolerant and Cost-efficient Workflow Scheduling Approach Based on Deep Reinforcement Learning for IT Operation and Maintenance","authors":"Yunsong Xiang, Xuemei Yang, Y. Sun, Hong Luo","doi":"10.1109/CSCWD57460.2023.10152783","DOIUrl":"https://doi.org/10.1109/CSCWD57460.2023.10152783","url":null,"abstract":"With the promotion of cloud computing, a large number of hardware and software systems in the cloud bring massive and complex operation and maintenance (O&M) work. To ensure the O&M efficiency of IT infrastructures, it is necessary to implement automatic and reliable scheduling for the directed acyclic graph (DAG) workflow which is composed of multiple O&M tasks. Considering the changing status of networks and machines in the cloud and the position constraints that some tasks must be executed on the specified machines in some O&M scenarios, we propose a novel workflow scheduling approach based on Deep Reinforcement Learning (DRL) to minimize the workflow execution makespan and implement the fault tolerance with the position constraints of tasks execution. In our proposal, we first design a fault-tolerant mechanism according to the reliability requirement and the probability distributions of the machine failure parameters with consideration of different failure rates in the heterogeneous environment. Then, we employ proximal policy optimization (PPO) to optimize the task scheduling strategy and ensure the strategy to satisfy the position constraints of tasks execution by action masking in proximal policy optimization. The experimental results show that our proposal can effectively reduce the makespan of the fault-tolerant workflow on the premise of 99.9% reliability.","PeriodicalId":51008,"journal":{"name":"Computer Supported Cooperative Work-The Journal of Collaborative Computing","volume":"6 1","pages":"411-416"},"PeriodicalIF":2.4,"publicationDate":"2023-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80352842","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","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：