Q-Learning based SFC deployment on Edge Computing Environment

Suman Pandey,James Won-Ki Hong,Jae-Hyoung Yoo 한국통신학회 2020 한국통신학회 APNOMS Vol.2020 No.09

Reinforcement learning (RL) has been used in various path finding applications including games, robotics and autonomous systems. Deploying Service Function Chain (SFC) with optimal path and resource utilization in edge computing environment is an important and challenging problem to solve in Software Defined Network (SDN) paradigm. In this paper we used RL based Q-Learning algorithm to find an optimal SFC deployment path in edge computing environment with limited computing and storage resources. To achieve this, our deployment scenario uses a hierarchical network structure with local, neighbor and datacenter servers. Our Q-Learning algorithm uses an intuitive reward function which does not only depend on the optimal path but also considers edge computing resource utilization and SFC length. We defined regret and empirical standard deviation as evaluation parameters. We evaluated our results by making 1200 test cases with varying SFC-length, edge resources and Virtual Network Function’s (VNF) resource demand. The computation time of our algorithm varies between 0.03~0.6 seconds depending on the SFC length and resource requirement.

Community Model for Smart TV over the Top Services

( Suman Pandey ),( Young Joon Won ),( Mi-jung Choi ),( Joon-min Gil ) 한국정보처리학회 2016 Journal of information processing systems Vol.12 No.4

We studied the current state-of-the-art of Smart TV, the challenges and the drawbacks. Mainly we discussed the lack of end-to-end solution. We then illustrated the differences between Smart TV and IPTV from network service provider point of view. Unlike IPTV, viewer of Smart TV`s over-the-top (OTT) services could be global, such as foreign nationals in a country or viewers having special viewing preferences. Those viewers are sparsely distributed. The existing TV service deployment models over Internet are not suitable for such viewers as they are based on content popularity, hence we propose a community based service deployment methodology with proactive content caching on rendezvous points (RPs). In our proposal, RPs are intermediate nodes responsible for caching routing and decision making. The viewer`s community formation is based on geographical locations and similarity of their interests. The idea of using context information to do proactive caching is itself not new, but we combined this with “in network caching” mechanism of content centric network (CCN) architecture. We gauge the performance improvement achieved by a community model. The result shows that when the total numbers of requests are same; our model can have significantly better performance, especially for sparsely distributed communities.

Community Model for Smart TV over the Top Services

Pandey, Suman,Won, Young Joon,Choi, Mi-Jung,Gil, Joon-Min Korea Information Processing Society 2016 Journal of information processing systems Vol.9 No.3

We studied the current state-of-the-art of Smart TV, the challenges and the drawbacks. Mainly we discussed the lack of end-to-end solution. We then illustrated the differences between Smart TV and IPTV from network service provider point of view. Unlike IPTV, viewer of Smart TV's over-the-top (OTT) services could be global, such as foreign nationals in a country or viewers having special viewing preferences. Those viewers are sparsely distributed. The existing TV service deployment models over Internet are not suitable for such viewers as they are based on content popularity, hence we propose a community based service deployment methodology with proactive content caching on rendezvous points (RPs). In our proposal, RPs are intermediate nodes responsible for caching routing and decision making. The viewer's community formation is based on geographical locations and similarity of their interests. The idea of using context information to do proactive caching is itself not new, but we combined this with "in network caching" mechanism of content centric network (CCN) architecture. We gauge the performance improvement achieved by a community model. The result shows that when the total numbers of requests are same; our model can have significantly better performance, especially for sparsely distributed communities.

Netflix, Amazon Prime, and YouTube: Comparative Study of Streaming Infrastructure and Strategy

Suman Pandey,문양세,최미정 한국정보처리학회 2022 Journal of information processing systems Vol.18 No.6

Netflix, Amazon Prime, and YouTube are the most popular and fastest-growing streaming services globally. Itis a matter of great interest for the streaming service providers to preview their service infrastructure andstreaming strategy in order to provide new streaming services. Hence, the first part of the paper presents adetailed survey of the Content Distribution Network (CDN) and cloud infrastructure of these service providers. To understand the streaming strategy of these service providers, the second part of the paper deduces a commonquality-of-service (QoS) model based on rebuffering time, bitrate, progressive download ratio, and standarddeviation of the On-Off cycle. This model is then used to analyze and compare the streaming behaviors of theseservices. This study concluded that the streaming behaviors of all these services are similar as they all useDynamic Adaptive Streaming over HTTP (DASH) on top of TCP. However, the amount of data that theydownload in the buffering state and steady-state vary, resulting in different progressive download ratios,rebuffering levels, and bitrates. The characteristics of their On-Off cycle are also different resulting in differentQoS. Hence a thorough adaptive bit rate (ABR) analysis is presented in this paper. The streaming behaviors ofthese services are tested on different access network bandwidths, ranging from 75 kbps to 30 Mbps. The surveyresults indicate that Netflix QoS and streaming behavior are significantly consistent followed by Amazon Primeand YouTube. Our approach can be used to compare and contrast the streaming services’ strategies and finetunetheir ABR and flow control mechanisms.

Screening and molecular identification of Streptomyces species isolated from high altitude soil of Nepal

Pandey Bishnu Prasad,Pradhan Suman Prakash,Adhikari Kapil,Shresth Rajib Kumar 한국미생물학회 2021 미생물학회지 Vol.57 No.3

Streptomyces are widely distributed in soil and known for the production of bioactive secondary metabolites. It has been reported that among microbial-derived antibiotics, two-third are produced by the Streptomyces species alone. Hence, continuous screening of the Streptomyces species is of growing scientific interest. A small Himalayan country like Nepal is in a unique geographical location with a huge biodiversity. However, little is known about microbial diversity. The aim of this study was to isolate and characterize the Streptomyces species from a high-altitude soil sample collected from an altitude of 4,380 meters above sea level. The 16S rRNA sequence analysis revealed that four isolated strains; G-10, G-14, G-18, and S4L belong to the Streptomyces species. On the basis of phylogenetic analysis of 16S rRNA gene sequences of the isolates with the best match in the database revealed that G-18 isolates closely related to Streptomyces albidoflavus strain PAS-12. Moreover, the ranges of radical scavenging activities by crude extract of isolates were observed against DPPH and ABTS. Furthermore, crude extract of isolates revealed the range of antimicrobial activities against the four pathogenic strains namely Klebsiella pneumoniae, Staphylococcus aureus, Enterococcus species, and Bacillus substilis. Moreover, isolated Streptomyces species revealed amylase, cellulase, and L-asparaginase enzyme activities.

Chemical composition, in vitro antioxidant, and enzymes inhibitory potential of three medicinally important plants from Nepal (Lepisorus mehrae, Pleurospermum benthamii, and Roscoea auriculata)

Pandey Bishnu Prasad,Pradhan Suman Prakash 경희대학교 융합한의과학연구소 2022 Oriental Pharmacy and Experimental Medicine Vol.22 No.1

The aim of this study was to examine antioxidant properties, major enzyme inhibition activities, and targeted metabolites profiling of Lepisorus mehrae, Pleurospermum benthamii, and Roscoea auriculata in different solvent extracts. This is the first report on metabolites profiling and biochemical activities of these plant species. Our results revealed that L. mehrae, P. benthamii, and R. auriculata are rich source of bioactive secondary metabolites and have good antioxidant potential. The methanol extract of L. mehrae, P. benthamii, and R. auriculata showed substantial inhibitory potential towards elastase, whereas water extract of L. mehrae and R. auriculata were more strong inhibitors of tyrosinase. Among the three plants, P. benthamii showed noteworthy inhibition on α-amylase, α-glucosidase, lipase, tyrosinase, elastase, and cholinesterases enzymes. High resolution mass spectrometry analysis revealed the presence of metabolites such as Protocatechuic acid, Gal- lic acid, 7,8,3′,4′-tetrahydroxyflavanone, Rhamnocitrin, Quercetin, Hyperoside, Quercetin-7-glucoside, Rutin, Rhamnetin, Aromadendrin, Camphor, and Hexanoic acid in L. mehrae. Moreover, Catechin and Fisetin were present in P. benthamii and Kaempferide, 7,8,3′,4′-Tetrahydroxyflavone, 5,7-Dihydroxy-2,3-dihydroflavonol 3-acetate, and Aromadendrin were present in R. auriculata. The results presented here provide enough scientific evidence that these plant species have diverse biochemi- cal potential and can be examined further for their potential use in modern pharmaceuticals, cosmetics, and nutraceuticals.

안정적인 IPTV VoD 서비스 제공을 위한 측정 지표 연구

최혁수(Hyeok-Soo Choi),Suman Pandey,원영준(Young J. Won),홍원기(James Won-Ki Hong) 한국통신학회 2009 한국통신학회 학술대회논문집 Vol.2009 No.6