Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
11 results
Search Results
Item Stacking Deep learning and Machine learning models for short-term energy consumption forecasting(Elsevier Ltd, 2022) Sujan Reddy, A.; Akashdeep, S.; Harshvardhan, R.; Kamath S․, S.Accurate prediction of electricity consumption is essential for providing actionable insights to decision-makers for managing volume and potential trends in future energy consumption for efficient resource management. A single model might not be sufficient to solve the challenges that result from linear and non-linear problems that occur in electricity consumption prediction. Moreover, these models cannot be applied in practice because they are either not interpretable or poorly generalized. In this paper, a stacking ensemble model for short-term electricity consumption is proposed. We experimented with machine learning and deep models like Random Forests, Long Short Term Memory, Deep Neural Networks, and Evolutionary Trees as our base models. Based on the experimental observations, two different ensemble models are proposed, where the predictions of the base models are combined using Gradient Boosting and Extreme Gradient Boosting (XGB). The proposed ensemble models were tested on a standard dataset that contains around 500,000 electricity consumption values, measured at periodic intervals, over the span of 9 years. Experimental validation revealed that the proposed ensemble model built on XGB reduces the training time of the second layer of the ensemble by a factor of close to 10 compared to the state-of-the-art, and also is more accurate. An average reduction of approximately 39% was observed in the Root mean square error. © 2022 Elsevier LtdItem Understanding of synergy in non-isothermal microwave-assisted in-situ catalytic co-pyrolysis of rice husk and polystyrene waste mixtures(Elsevier Ltd, 2022) Sridevi, V.; Suriapparao, D.V.; Tukarambai, M.; Terapalli, A.; Ramesh, R.; Sankar Rao, C.S.; Gautam, R.; Moorthy, J.V.; Suresh Kumar, C.Rice husk (RH) and polystyrene (PS) wastes were converted into value-added products using microwave-assisted catalytic co-pyrolysis. The graphite susceptor (10 g) along with KOH catalyst (5 g) was mixed with the feedstock to understand the products and energy consumption. RH promoted the char yield (20–34 wt%) and gaseous yields (16–25 wt%) whereas PS enhanced the oil yield (23–70 wt%). Co-pyrolysis synergy induced an increase in gaseous yields (14–53 wt%) due to excessive cracking. The specific microwave energy consumption dramatically decreased in co-pyrolysis (5–22 kJ/g) compared to pyrolysis (56–102 kJ/g). The pyrolysis index increased (17–445) with the increase in feedstock quantity (5–50 g). The obtained oil was composed of monoaromatics (74%) and polyaromatics (18%). The char was rich in carbon content (79.5 wt%) and the gases were composed of CO (24%), H2 (12%), and CH4 (22%). © 2022 Elsevier LtdItem Microwave-assisted in-situ catalytic pyrolysis of polystyrene: Analysis of product formation and energy consumption using machine learning approach(Institution of Chemical Engineers, 2022) Terapalli, A.; Kamireddi, D.; Sridevi, V.; Tukarambai, M.; Suriapparao, D.V.; Sankar Rao, C.S.; Gautam, R.; Modi, P.R.Microwave-assisted catalytic pyrolysis is a prominent technology for the production of high-quality fuel intermediates and value-added chemicals from polystyrene waste. The objectives of this study were to understand the role of catalyst (KOH) on polystyrene (PS) pyrolysis. Pyrolysis experiments were conducted using a microwave oven at a power of 450 W and a temperature of 600 °C. Graphite susceptor (10 g) was used to achieve the required pyrolysis conditions. In addition, the design of experiments (DoE) with machine learning (ML) was used to understand the loading of PS (5 g, 27.5 g, and 50 g), and KOH (5 g, 7.5 g, and 10 g). The products including oil, gas, and char were collected in every experiment. The average heating rates achieved were in the range of 30–50 °C/min. The specific microwave power (microwave power per unit mass of feedstock) decreased with an increase in PS amount from 90 to 9 W/g. However, the specific microwave energy (microwave energy per unit mass of feedstock) (27–73 kJ/g) was in line with the average heating rate. The maximum yield of pyrolysis oil was found to be 95 wt%, which was obtained with a PS:KOH ratio of 27.5 g: 7.5 g. The oil yield increased from 80 to 95 wt% when the mass of the catalyst increased from 5 to 7.5 g. On the other hand, the gas yield (3–18 wt%) varied significantly and char yield (1–2 wt%) was not influenced. The yields predicted by ML matched well with the experimental yields. This study demonstrated the potential of KOH as a catalyst for PS pyrolysis technology as the formation of aliphatic hydrocarbons in the oil fraction was significantly promoted. © 2022 The Institution of Chemical EngineersItem Improved Harmony Search Algorithm for Multihop Routing in Wireless Sensor Networks(Pleiades Publishing, 2022) Sowmya, G.V.; Manjappa, M.Abstract: Energy efficiency is critical for prolonging the network lifetime of Wireless Sensor Network (WSN), and is the most important objective for any routing algorithm for WSN. In this article authors have proposed a Multihop harmony search algorithm for WSN with two objectives, first being increasing the throughput of the network and second being optimizing the energy consumption of the sensor nodes and thereby prolonging the lifetime of network. Finding the goodness of the communication channel/path is quite important. Sometimes, though the channel capacity is more, fewer amounts of data may be transmitted in the channel resulting in under utilization of the resources; and other times, though the channel capacity is less, more data may be dumped into the channel resulting in channel congestion and less output. Thus, if the goodness of the communication channel is known in advance, then it is easy for the algorithms to decide the upper bound of the channel and can have a congestion free and error free information transmission. Thus, the proposed algorithm employ Shannon channel capacity ‘C’ (baud rate) for finding the best next hop and the same is used for initialization of Harmony Memory. An effective local search strategy is also proposed to strengthen the local harmony search ability so that the convergence speed and the accuracy of routing algorithm is improved. Finally, an objective function model is developed by taking path length, energy consumption, and residual energy in to consideration. The proposed algorithm is compared with existing Multihop LEACH, BRM (Baud rate based Multihop routing protocol) and EEHSBR (Energy Efficient Harmony Search Based Routing) algorithm for the quantitative and qualitative analysis. The simulation results reveal that the proposed algorithm performs better than the considered algorithms in terms of network lifetime, throughput and energy consumption. © 2022, Pleiades Publishing, Ltd.Item Geo-Distributed Multi-Tier Workload Migration Over Multi-Timescale Electricity Markets(Institute of Electrical and Electronics Engineers Inc., 2023) Addya, S.K.; Satpathy, A.; Ghosh, B.C.; Chakraborty, S.; Ghosh, S.K.; Das, S.K.Virtual machine (VM) migration enables cloud service providers (CSPs) to balance workload, perform zero-downtime maintenance, and reduce applications' power consumption and response time. Migrating a VM consumes energy at the source, destination, and backbone networks, i.e., intermediate routers and switches, especially in a Geo-distributed setting. In this context, we propose a VM migration model called Low Energy Application Workload Migration (LEAWM) aimed at reducing the per-bit migration cost in migrating VMs over Geo-distributed clouds. With a Geo-distributed cloud connected through multiple Internet Service Providers (ISPs), we develop an approach to find out the migration path across ISPs leading to the most feasible destination. For this, we use the variation in the electricity price at the ISPs to decide the migration paths. However, reduced power consumption at the expense of higher migration time is intolerable for real-time applications. As finding an optimal relocation is $\mathcal {NP}$NP-Hard, we propose an Ant Colony Optimization (ACO) based bi-objective optimization technique to strike a balance between migration delay and migration power. A thorough simulation analysis of the proposed approach shows that the proposed model can reduce the migration time by 25%-30% and electricity cost by approximately 25% compared to the baseline. © 2008-2012 IEEE.Item Life Cycle Assessment of construction materials: Methodologies, applications and future directions for sustainable decision-making(Elsevier Ltd, 2023) Barbhuiya, S.; Das, B.B.This review paper presents a comprehensive analysis of Life Cycle Assessment (LCA) methodologies applied to construction materials. It begins with an introduction highlighting the significance of LCA in the construction industry, followed by an overview of LCA principles, phases and key parameters specific to construction materials. The methodological approaches utilised in LCA, including inventory analysis, impact assessment, normalisation, allocation methods and uncertainty analysis, are discussed in detail. The paper then provides a thorough review of LCA studies on various construction materials, such as cement, concrete, steel and wood, examining their life cycle stages and environmental considerations. The review also explores recent advances in LCA for construction materials, including circular economy principles, renewable alternatives, technological innovations and policy implications. The challenges and future directions in LCA implementation for construction materials are discussed, emphasising the need for data quality, standardisation, social aspects integration and industry-research collaboration. The provides valuable insights for researchers, policymakers and industry professionals to enhance sustainability in the construction sector through informed decision-making based on LCA. © 2023 The AuthorsItem Energy- and Reliability-Aware Provisioning of Parallelized Service Function Chains With Delay Guarantees(Institute of Electrical and Electronics Engineers Inc., 2024) Chintapalli, V.R.; Killi, B.R.; Partani, R.; Tamma, B.R.; Siva Ram Murthy, C.Network Functions Virtualization (NFV) leverages virtualization and cloud computing technologies to make networks more flexible, manageable, and scalable. Instead of using traditional hardware middleboxes, NFV uses more flexible Virtual Network Functions (VNFs) running on commodity servers. One of the key challenges in NFV is to ensure strict reliability and low latency while also improving energy efficiency. Any software or hardware failures in an NFV environment can disrupt the service provided by a chain of VNFs, known as a Service Function Chain (SFC), resulting in significant data loss, delays, and wasted resources. Due to the sequential nature of SFC, latency increases linearly with the number of VNFs. To address this issue, researchers have proposed parallelized SFC or VNF parallelization, which allows multiple independent VNFs in an SFC to run in parallel. In this work, we propose a method to solve the parallelized SFC deployment problem as an Integer Linear Program (ILP) that minimizes energy consumption while ensuring reliability and delay constraints. Since the problem is NP-hard, we also propose a heuristic scheme named ERASE that determines the placement of VNFs and routes traffic through them in a way that minimizes energy consumption while meeting capacity, reliability, and delay requirements. The effectiveness of ERASE is evaluated through extensive simulations and it is shown to perform better than benchmark schemes in terms of total energy consumption and reliability achieved. © 2017 IEEE.Item Energy efficient and delay aware deployment of parallelized service function chains in NFV-based networks(Elsevier B.V., 2024) Chintapalli, V.R.; Partani, R.; Tamma, B.R.; Siva Ram Murthy, C.Network Functions Virtualization (NFV) replaces traditional hardware-based network equipment and middleboxes with flexible Virtualized Network Functions (VNFs) in order to reduce costs and improve agility and scalability. The VNFs are logically arranged in a specific sequence to form a Service Function Chain (SFC) which ensures that the traffic is processed according to the desired service requirements. However, the inherent length of SFCs leads to an undesirable increase in end-to-end delay experienced by the packets. Parallelized SFC (PSFC) addresses this problem by trying to allow multiple VNFs of the SFC to process packets in parallel by co-locating parallelizable VNFs on the same server. The energy-efficient deployment of PSFCs while considering the impact of contention for the shared resources on the server is unexplored in the literature. Hence, in this work, we formulate the PSFC deployment problem as an Integer Linear Program (ILP) that minimizes energy consumption while considering the impact of shared resource contentions without violating end-to-delay constraints. Since the ILP is NP-hard, we also propose a heuristic scheme named EPSFC, which provides flexible resource allocation-based deployment that minimizes the total energy consumption and ensures end-to-end delay requirements while considering the effects of shared resource contentions on the end-to-end delay. The effectiveness of EPSFC is evaluated through extensive simulations, and the results show a significant reduction in energy consumption while improving the PSFC acceptance ratio as compared to state-of-the-art schemes. © 2024 Elsevier B.V.Item IoT energy efficiency routing protocol using FHO-based clustering and improved CSO model-based routing in MANET(John Wiley and Sons Ltd, 2024) Sanshi, S.; Karthik, N.; Vatambeti, R.Many protocols, services, and electrical devices with built-in sensors have been developed in response to the rapid expansion of the Internet of Things. Mobile ad hoc networks (MANETs) consist of a collection of autonomous mobile nodes that can form an ad hoc network in the absence of any pre-existing infrastructure. System performance may suffer due to the changeable topology of MANETs. Since most mobile hosts operate on limited battery power, energy consumption poses the biggest challenge for MANETs. Both network lifetime and throughput improve when energy usage is reduced. However, existing approaches perform poorly in terms of energy efficiency. Scalability becomes a significant issue in large-scale networks as they grow, leading to overhead associated with routing updates and maintenance that can become unmanageable. This article employs a MANET routing protocol combined with an energy conservation strategy. The clustering hierarchy is used in MANETs to maximize the network's lifespan, considering its limited energy resources. In the MANET communication process, the cluster head (CH) is selected using Fire Hawk Optimization (FHO). When choosing nodes to act as a cluster for an extended period, CH election factors in connectivity, mobility, and remaining energy. This process is achieved using an optimized version of the Ad hoc On-Demand Distance Vector (AODV) routing protocol, utilizing Improved Chicken Swarm Optimization (ICSO). In comparison to existing protocols and optimization techniques, the proposed method offers an extended network lifespan ranging from 90 to 160 h and reduced energy consumption of 80 to 110 J, as indicated by the implementation results. © 2024 John Wiley & Sons Ltd.Item Infrared Perspectives: Computing laptop energy dissipation via thermal imaging and the Stefan-Boltzmann equation(Elsevier Ltd, 2024) Anbalagan, A.; Arumuga Perumal, D.; Persiya, J.Energy conservation is crucial for reducing greenhouse gas emissions and addressing climate change. Laptops contribute significantly to energy consumption, emphasizing the need for improved energy efficiency. This paper explores the application of thermal imaging technology to enhance energy conservation in laptops. Thermal imaging provides valuable insights into heat distribution on the laptop's surface, aiding in identifying areas of excessive energy consumption. By identifying areas of a laptop that generate excessive heat and implementing energy-efficient measures, energy consumption can be reduced, and the device's lifespan can be extended. The study leverages computer vision and artificial intelligence techniques to analyze thermal images. We collected the thermal images for the dataset using the FLIR E75 Thermal camera. Two methods of Region of Interest (ROI) extraction, contour-based thresholding, and Detectron2-based extraction are employed. Feature extraction includes statistical, texture, spatial, and energy features, and Principal Component Analysis (PCA) is used to reduce dimensionality. K-means clustering categorizes data points based on reduced features, and performance metrics validate the effectiveness of the clustering methods. The study also computes energy dissipation from thermal images using the Stefan-Boltzmann Law. Results indicate that thermal imaging, coupled with advanced analysis techniques, holds promise for improving energy conservation in laptops. © 2024 Elsevier Ltd