A visual analytics system for optimizing the performance of large-scale networks in supercomputing systems

Fujiwara, Takanori; Li, Jianping Kelvin; Mubarak, Misbah; Ross, Caitlin; Carothers, Christopher D.; Ross, Robert; Ma, Kwan‐Liu

doi:10.1016/j.visinf.2018.04.010

Cited by 28 publications

(17 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Node or edge attributes of dynamic graphs can be introduced as time series. This kind of time series data helps understand different temporal patterns and evaluate the network dynamics in general [52]- [56]. The network view helps to visualize the connectivity of the sensors, which can enhance analysis, detection and exploration.…”

Section: ) Time Series Of Graph and Networkmentioning

confidence: 99%

“…From a data mining perspective, Aghabozorgi and Shirkhorshidi [12] state that Euclidean Distance and DTW are the most popular distance measures in time series data; however, Euclidian Distance is the most widely used distance measure in the surveyed visual analytics papers e.g. [34], [43], [44], [50], [52], [53], [56], [57], [59], [60], [66], [67], [69], [70], [75], [81], [85], [88]- [91], [93], [95], [96], [113]- [115] as it is the most straightforward distance measure compared to others. DTW has only been used in [48], [53], [56], [79] to calculate the similarity of time series data, and papers [34], [35], [61], [72], [83], [85], [86] use correlation and cross-correlation in their works.…”

Section: A Raw Data Similaritymentioning

confidence: 99%

“…Multidimensional Scaling (MDS) is a very popular non-linear dimensionality reduction technique that is useful for effectively representing high-dimensional data in lower dimensional space. This technique has been used in the surveyed papers [36], [48], [54], [56], [57], [63], [78], [81], [84]. MDS is a useful technique which effectively represents high-dimensional data in lower dimensional space; however, it struggles to separate k-Means clusters [84].…”

Section: B Feature Extractionmentioning

confidence: 99%

“…Partitioning has been adopted in some of the surveyed papers such as [41], [53], [54], [56], [59], [69], [70], [72], [81], [92], [96], [114], [115]. Even though fuzzy clustering methods such as Fuzzy c-Means (FCM) or Fuzzy c-Medoids have rarely been used in visual analytics, these methods have promising potential for the future of partitioning methods that can be used in visual analytics systems other than k-Means.…”

Section: K-meansmentioning

confidence: 99%

See 3 more Smart Citations

Clustering and Classification for Time Series Data in Visual Analytics: A Survey

et al. 2019

View full text Add to dashboard Cite

Visual analytics for time series data has received a considerable amount of attention. Different approaches have been developed to understand the characteristics of the data and obtain meaningful statistics in order to explore the underlying processes, identify and estimate trends, make decisions and predict the future. The machine learning and visualization areas share a focus on extracting information from data. In this paper, we consider not only automatic methods but also interactive exploration. The ability to embed efficient machine learning techniques (clustering and classification) in interactive visualization systems is highly desirable in order to gain the most from both humans and computers. We present a literature review of some of the most important publications in the field and classify over 60 published papers from six different perspectives. This review intends to clarify the major concepts with which clustering or classification algorithms are used in visual analytics for time series data and provide a valuable guide for both new researchers and experts in the emerging field of integrating machine learning techniques into visual analytics.

show abstract

Section: ) Time Series Of Graph and Networkmentioning

confidence: 99%

Section: A Raw Data Similaritymentioning

confidence: 99%

Section: B Feature Extractionmentioning

confidence: 99%

Section: K-meansmentioning

confidence: 99%

See 2 more Smart Citations

Clustering and Classification for Time Series Data in Visual Analytics: A Survey

et al. 2019

View full text Add to dashboard Cite

show abstract

“…At least 80% of the information about the external world is obtained and felt through vision and finally processed by the brain and perceived by humans [1]. e process of human beings converting the information obtained through vision into graphic images can be regarded as a simple visualization process [2]. e earliest "visualization technology" is mainly used in computer science and applications and formed a very important branch-scientific computing visualization.…”

Section: Introductionmentioning

confidence: 99%

Topology Optimization of Interactive Visual Communication Networks Based on the Non-Line-of-Sight Congestion Control Algorithm

Liu

Zhou

2020

Complexity

View full text Add to dashboard Cite

In this paper, an in-depth study of interactive visual communication of network topology through non-line-of-sight congestion control algorithms is conducted to address the real-time routing problem of adapting to dynamic topologies, and a delay-constrained stochastic routing algorithm is proposed to enable packets to reach GB within the delay threshold in the absence of end-to-end delay information while improving network throughput and reducing network resource consumption. The algorithm requires each sending node to select an available relay set based on the location of its neighbor nodes and channel state and computes transfer probabilities for each node in the relay set combining the remaining delay of the packet with the distance from the relay node to GB. Based on the obtained transfer probability and local channel state, the sending node passes the packet to the relay node. The convergence of the algorithm is proved and its performance is verified by simulation. The first part of the algorithm is based on the greedy algorithm to deploy and locate the network flying platform nodes with the goal of efficient coverage of the network flying platform nodes, considering the ground base station services. As the delay on each link varies due to the change of channel state, the source and relay nodes asynchronously update the data generation rate and the pairwise parameters based on the received local information and use the obtained optimal values to pass the packets to GB.

show abstract

Similarity Mining of Message Passing Delays in Supercomputer Networks Based on Peak and Step Detection

Salnikov

Begaev

Maysuradze

2020

Communications in Computer and Information Science

View full text Add to dashboard Cite

A visual analytics system for optimizing the performance of large-scale networks in supercomputing systems

Cited by 28 publications

References 28 publications

Clustering and Classification for Time Series Data in Visual Analytics: A Survey

Clustering and Classification for Time Series Data in Visual Analytics: A Survey

Topology Optimization of Interactive Visual Communication Networks Based on the Non-Line-of-Sight Congestion Control Algorithm

Similarity Mining of Message Passing Delays in Supercomputer Networks Based on Peak and Step Detection

Contact Info

Product

Resources

About