Browsing by Author "Yadav, V."

Now showing 1 - 6 of 6

Efficient Kalman filter based deep learning approaches for workload prediction in cloud and edge environments
(Springer, 2025) Kumar, M.R.; Annappa, B.; Yadav, V.
Offering cloud resources to consumers presents several difficulties for cloud service providers. When utilizing resources efficiently in cloud and edge contexts, precisely forecasting workload is a crucial problem. Accurate workload prediction allows intelligent resource allocation, preventing needless waste of computational and storage resources while meeting user’s Quality of Service(QoS). In order to mitigate this issue, Kalman filter-based novel hybrid models, including Long Short Term Memory (LSTM), Bi-directional Long Short Term Memory (BI-LSTM), and Gated Recurrent Unit (GRU), are proposed. These models utilize CNN and attention mechanisms to predict workloads at Edge Servers accurately. The proposed models were extensively evaluated on real world traces like Alibaba_v2018, Materna, Bitbrains, Microsoft Azure_2019 and Planet lab datasets at various time intervals with and without using Kalman filter. The experimental comparison shows that 97%, 82% and 90% reduction in MSE for Alibaba, 73%, 73% and 63% reduction in MSE for Materna, 72%, 63% and 40% reduction in MSE for Planet lab, 95%, 77% and 96% reduction in MSE for Microsoft Azure and 91%, 87% and 91% reduction in MSE for Bitbrains with respect to CPU utilization %. The effectiveness of the proposed forecasting model is validated through statistical analysis using the Friedman and Nemenyi post-hoc tests. © The Author(s), under exclusive licence to Springer-Verlag GmbH Austria, part of Springer Nature 2024.
GA-PSO: Service Allocation in Fog Computing Environment Using Hybrid Bio-Inspired Algorithm
(2019) Yadav, V.; Natesha, B.V.; Ram Mohana Reddy, Guddeti
Internet of Thing (IoT) applications require an efficient platform for processing big data. Different computing techniques such as Cloud, Edge, and Fog are used for processing big data. The main challenge in the fog computing environment is to minimize both energy consumption and makespan for services. The service allocation techniques on a set of virtual machines (VMs) is the decidable factor for energy consumption and latency in fog servers. Hence, the service allocation in fog environment is referred to as NP-hard problem. In this work, we developed a hybrid algorithm using Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) technique to solve this NP-hard problem. The proposed GA-PSO is used for optimal allocation of services while minimizing the total makespan, energy consumption for IoT applications in the fog computing environment. We implemented the proposed GA-PSO using customized C simulator, and the results demonstrate that the proposed GA-PSO outperforms both GA and PSO techniques when applied individually. � 2019 IEEE.
GA-PSO: Service Allocation in Fog Computing Environment Using Hybrid Bio-Inspired Algorithm
(Institute of Electrical and Electronics Engineers Inc., 2019) Yadav, V.; Natesha, B.V.; Guddeti, R.M.R.
Internet of Thing (IoT) applications require an efficient platform for processing big data. Different computing techniques such as Cloud, Edge, and Fog are used for processing big data. The main challenge in the fog computing environment is to minimize both energy consumption and makespan for services. The service allocation techniques on a set of virtual machines (VMs) is the decidable factor for energy consumption and latency in fog servers. Hence, the service allocation in fog environment is referred to as NP-hard problem. In this work, we developed a hybrid algorithm using Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) technique to solve this NP-hard problem. The proposed GA-PSO is used for optimal allocation of services while minimizing the total makespan, energy consumption for IoT applications in the fog computing environment. We implemented the proposed GA-PSO using customized C simulator, and the results demonstrate that the proposed GA-PSO outperforms both GA and PSO techniques when applied individually. Â© 2019 IEEE.
New thiophene-based donor-acceptor conjugated polymers carrying fluorene or cyanovinylene units: Synthesis, characterization, and electroluminescent properties
(John Wiley and Sons Inc, 2013) Murali, M.G.; Udayakumar, U.; Yadav, V.; Srivastava, R.
Two new thiophene-based donor-acceptor (D-A) conjugated polymers, PDTOFV and PDTOCN, are synthesized and characterized. The polymers are readily soluble in common organic solvents and exhibit good thermal stability with onset decomposition temperature (Td) in the range 310-330°C. Cyclic voltammetry studies revealed that polymers possess low-lying highest occupied molecular orbital (HOMO) energy levels (-5.94 eV for PDTOFV and -5.86 eV for PDTOCN) and low-lying lowest unoccupied molecular orbital (LUMO) energy levels (-3.35 eV for PDTOFV and -3.55 eV for PDTOCN). The optical band gap is calculated from onset absorption edge of the polymer film. The polymers exhibit green fluorescence with fluorescence quantum yields (?fl) of 38% and 42%, respectively, for PDTOFV and PDTOCN. Polymer light-emitting diodes (PLEDs) are fabricated using these polymers with a device configuration of ITO/PEDOT:PSS/polymer/Al. The device based on PDTOFV emitted green light with Commission Internationale de I'Eclairage (CIE) coordinate values of (0.25, 0.39). Whereas, the device based on PDTOCN showed white light emission with CIE coordinate values of (0.32, 0.35), which is very close to the values (0.33, 0.33) of standard white light emission. The threshold voltages of the PLEDs are determined by current density-voltage characteristics and are found to be 7.3 and 3.9 V for PDTOFV and PDTOCN, respectively. © 2012 Society of Plastics Engineers.
Synthesis and characterization of thiophene and fluorene based donor-acceptor conjugated polymer containing 1,3,4-oxadiazole units for light-emitting diodes
(2012) Murali, M.G.; Naveen, P.; Udayakumar, U.; Yadav, V.; Srivastava, R.
A new donor-acceptor (D-A) conjugated polymer (PDTOF) containing 3,4-didodecyloxythiophene, fluorene and 1,3,4-oxadiazole units is synthesized by using Wittig reaction methodology. The synthesized polymer is characterized by 1H NMR, FTIR, GPC, and elemental analysis. The optical energy band gap of the polymer is found to be 2.42 eV as calculated from the onset absorption edge. The electrochemical studies of PDTOF reveal that, the HOMO and LUMO energy levels of the polymer are -5.45 eV and -3.58 eV, respectively. The polymer is thermally stable up to 320 °C. Polymer light-emitting diode devices are fabricated with a configuration of ITO/PEDOT: PSS/PDTOF/Al using PDTOF as the emissive layer. The electroluminescence (EL) spectrum of the device showed green emission with CIE coordinate values (0.34, 0.47). By current density-voltage characteristics, threshold voltage of the PLED device is found to be 6.5 V. © 2011 Elsevier Ltd. All rights reserved.
Thiophene-based donor-acceptor conjugated polymer as potential optoelectronic and photonic material
(2013) Murali, M.G.; Udayakumar, U.; Yadav, V.; Srivastava, R.; Safakath, K.
In this paper, we report the synthesis, characterization and optical properties of a donor-acceptor conjugated polymer, PTh-CN, containing 3,4-didodecyloxythiophene and cyanovinylene units. The polymer possesses a low band gap of 1.75 eV as calculated from the onset absorption edge. From the electrochemical study, the HOMO and LUMO energy levels of the polymer are figured out to be -5.52 eV and -3.52 eV, respectively. Polymer light-emitting diodes are fabricated using PTh-CN as the emissive layer with a device configuration of ITO/PEDOT:PSS/PTh-CN/Al. The device showed stable saturated red electroluminescence with CIE coordinate values (0.65, 0.32) at 12 V, which are very close to the values for standard red demanded by the NTSC. In addition, the device showed good colour stability under different bias voltages and the threshold voltage of the PLED device is found to be as low as 3.1 V. Further, a nanocomposite of the polymer and TiO2 nanoparticles is prepared by the dispersion method. The nonlinear optical properties of PTh-CN and PTh-CN/TiO 2 nanocomposite are studied using z-scan technique. The polymer solution, polymer film and polymer/TiO2 nanocomposite film show a strong saturable absorption behaviour. The value of saturation intensity (I s) is found to be of the order 1011-1012 W/m2, indicating that the materials are useful candidates for photonic applications. [Figure not available: see fulltext.] © 2013 Indian Academy of Sciences.