Conference Papers
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506
Browse
5 results
Search Results
Item FQ-PIE Queue Discipline in the Linux Kernel: Design, Implementation and Challenges(Institute of Electrical and Electronics Engineers Inc., 2019) Ramakrishnan, G.; Bhasi, M.; Saicharan, V.; Monis, L.; Patil, S.D.; Tahiliani, M.P.Proportional Integral controller Enhanced (PIE) is an Active Queue Management (AQM) mechanism to address the bufferbloat problem. AQM mechanisms tackle bufferbloat by dropping or marking packets before the buffers fill up, but typically do not ensure fairness between responsive and unresponsive flows that share the same bottleneck link i.e., unresponsive flows can starve responsive flows when they co-exist. Recently, there has been an active interest in integrating flow protection mechanisms with AQM mechanisms to collectively tackle the problem of bufferbloat and fairness. There exist two such algorithms: Flow Queue Controlled Delay (FQ-CoDel) and Flow Queue Proportional Integral Controller Enhanced (FQ-PIE) that integrate flow protection with AQM mechanisms. Flow protection is achieved by dividing the incoming flows into separate queues and then applying CoDel/PIE algorithm on respective queues. Although FQ-CoDel is available in the mainline of Linux, there does not exist a model for FQ-PIE. In this paper, we discuss the design and implementation of FQ-PIE in the Linux kernel. We test and evaluate our proposed model of FQ-PIE in different scenarios by comparing the results obtained from it to those obtained for PIE and FQ-CoDel. Besides evaluating the fairness among responsive and unresponsive flows, we also evaluate the fairness among different types of responsive flows, such as when CUBIC TCP shares the same bottleneck link as TCP BBR. We also assess the benefits of integrating flow protection with AQM mechanisms in terms of reducing the latency for thin, latency sensitive flows when they coexist with thick, latency tolerant flows. © 2019 IEEE.Item Collaborative Filtering for Book Recommendation System(Springer, 2020) Ramakrishnan, G.; Saicharan, V.; Chandrasekaran, K.; Rathnamma, M.V.; Ramana, V.V.Collaborative filtering is one of the most important techniques in the market nowadays. It is prevalent in almost every aspect of the internet, in e-commerce, music, books, social media, advertising, etc., as it greatly grasps the needs of the user and provides a comfortable platform for the user to find what they like without searching. This method has a few drawbacks; one of them being, it is based only on the explicit feedback given by the user in the form of a rating. The real needs of a user are also demonstrated by various implicit indicators such as views, read later lists, etc. This paper proposes and compares various techniques to include implicit feedback into the recommendation system. The paper attempts to assign explicit ratings to users depending on the implicit feedback given by users to specific books using various algorithms and thus, increasing the number of entries available in the table. © 2020, Springer Nature Singapore Pte Ltd.Item Quantification and Assessment of The Virtual Water Content of Rice Crop: A Case Study of Mysore District, India(Institute of Electrical and Electronics Engineers Inc., 2023) Saicharan, V.; Shwetha, H.R.Agriculture is the largest consumer of freshwater among all sectors. Currently, there are minimal studies to quantify a crop's water consumption and virtual water content of crops in India, especially using geospatial products. To address this issue, the current study employed a geospatial approach to quantify and assess the virtual content of rice crop. The actual evapotranspiration, NDVI and crop yield datasets are used in this study to quantify the virtual water content (VWC) of rice crops in the Mysore district from 2015 to 2019. The results show that the rice crop's water consumption (CWC) and VWC are higher in Kharif than in summer. The rice crop yield in Mysore is reducing, but the CWC was increasing with respect to time during the study period. The maximum VWC was observed in the 2018 Kharif season, i.e., 5228.9 m3/ton, and the lowest VWC (962.7 m3/ton) was observed in the summer of 2016. The findings will make it easier to comprehend how much water rice crops need over the course of various seasons and years, allowing for more effective water management. It will also assist officials and water planners in determining which seasons to minimise supply to achieve sustainable water management, especially in arid and semi-arid regions. © 2023 IEEE.Item ENHANCING SPATIAL RESOLUTION OF GPM RAINFALL DATA IN UPPER CAUVERY BASIN, INDIA: MACHINE LEARNING APPROACH(Institute of Electrical and Electronics Engineers Inc., 2024) Kumar, P.G.; Saicharan, V.; Shwetha, H.R.Spatial downscaling is an effective way to obtain rainfall with sufficient spatial details. The spatial resolution of the Global Precipitation Measurement (GPM) mission (IMERG) satellite rainfall products is 0.1° × 0.1°, which is too coarse for regional-scale analysis. This study employed two Model averaging methods (Random Forest + XGBoost, Random Forest + CatBoost), Ensemble methods (Random Forest, XGBoost, CatBoost) and Stacked Random Forest + XGBoost model for downscaling GPM IMERG monthly rainfall over the Upper Cauvery Basin from 2015 to 2020 from 0.1°(~ 10 km) to 1 km resolution. Five land surface variables (auxiliary variables), NDVI, elevation, LST, slope, and aspect, were employed for this purpose. The stacked RFR+XGB model outperformed the model averaging techniques, achieving a higher R2 of 0.694 and a lower RMSE/MAE of 44.57/35.23. While the ensemble method yielded promising results, it struggled to predict extreme rainfall values. The downscaled dataset facilitates improved hydrological applications, including water footprint analysis, hydrological monitoring, and disaster warning systems. © 2024 IEEE.Item Spatio-temporal Assessment and Monitoring of Agricultural Drought in Karnataka, India(Springer Science and Business Media Deutschland GmbH, 2025) Chandankumar, N.M.; Saicharan, V.; Shwetha, H.R.Agricultural drought monitoring is crucial as it affects food production and fodder, especially in countries like India; consequently, it affects the country’s economy, where nearly 70% of the population depends on agriculture for livelihood. Conventional drought indices consider the mean monthly rainfall values to assess the drought conditions by ignoring the intra-monthly rainfall variations. Due to climate change and erratic rainfall patterns, monthly mean values are not a suitable representation of the rainfall that occurred in the corresponding month. To address this challenge, the current study employed a methodology for calculating agricultural drought using a standardized net-precipitation evapotranspiration index (SNEPI) from 2000 to 2022 by accounting for rainfall variations at an intra-monthly scale. This study employed daily gridded rainfall data and monthly evapotranspiration obtained from the India Meteorological Department (IMD) and NASA’s global land data assimilation system (GLDAS), respectively, at 0.25° × 0.25° spatial resolution for the calculation of SNEPI. Intra-monthly variation of rainfall pattern is addressed by deriving the uniformity coefficient and multiplying it with mean monthly rainfall values. The results were compared with the widely used drought index, the standardized precipitation evapotranspiration index (SPEI). The spatial (agroclimatic zones and whole Karnataka level) and temporal (annual and monthly scale) analyses of SNEPI and SPEI were performed. According to the yearly reports of the Karnataka State Natural Disaster Management Centre (KSNDMC), the highest negative rainfall departure occurred in 2003 and 2016, both termed as deficiency periods. The results showed that in 2006, the drought was observed; however, the annual rainfall was near normal magnitude. Therefore, this study presented the detailed results of 2003, 2006, and 2016. A higher magnitude (0.98) of the correlation coefficient was observed for October, the monsoon season’s termination month. Also, the decreased correlations of 0.88, 0.88, and 0.84 were observed for the months of July, August, and September, respectively. This can be interpreted as increased intra-monthly variations, which SNEPI successfully captures, whereas SPEI ignores the variation. SNEPI succeeds in the early detection of drought events due to its ability to detect short-term dry and wet spells, which correlates well with SPEI at all considered months, inferred that it can be used for drought identification. The results suggest that this index is better for understanding the agricultural drought patterns spatially and temporally across Karnataka’s agro-climatic zones, which incorporates the intra-monthly rainfall variations and helps the agricultural community and policymakers. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.