Article
Biology
Vidya K. Sudarshan, Mikkel Brabrand, Troels Martin Range, Uffe Kock Wiil
Summary: The accurate prediction of patient arrivals at Emergency Departments is crucial for hospital management, and while traditional time series methods have limitations in practical situations, new Machine Learning-based models show promise in improving forecasting accuracy.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Energy & Fuels
Ibrahim Salem Jahan, Vojtech Blazek, Stanislav Misak, Vaclav Snasel, Lukas Prokop
Summary: Off-grid power systems are commonly used for supplying electricity to remote households, and different forecasting models were compared in this study to predict the power quality parameters for small-scale off-grid systems. Decision tree models were found to be the most accurate in forecasting PQPs.
Article
Multidisciplinary Sciences
Pyae-Pyae Phyo, Yung-Cheol Byun, Namje Park
Summary: This study proposes an ensemble model based on machine learning for short-term energy forecasting in the electric industry. Experimental results using energy and weather data from Jeju Island demonstrate the superior performance of the proposed model compared to benchmark models, indicating promising potential for application.
Review
Energy & Fuels
Stephen Haben, Siddharth Arora, Georgios Giasemidis, Marcus Voss, Danica Vukadinovic Greetham
Summary: The increased digitalisation and monitoring of the energy system offer numerous opportunities for decarbonisation, especially through applications on low voltage, local networks. Reliable forecasting is crucial for these systems to anticipate key features and uncertainties. This paper aims to provide an overview of the current landscape, challenges, and recommendations for low voltage level forecasts to facilitate further research and development.
Review
Green & Sustainable Science & Technology
Azar Niknam, Hasan Khademi Zare, Hassan Hosseininasab, Ali Mostafaeipour, Manuel Herrera
Summary: The challenge for city authorities in managing growing cities is exacerbated by the increasing exposure to climate change effects. This paper provides a timely review of predictive methods for short-term water demand, offering a comprehensive guideline for selecting forecasting methods. It also emphasizes the importance of sustainable management objectives in the era of technological developments.
Article
Medicine, General & Internal
Istiak Mahmud, Md Mohsin Kabir, M. F. Mridha, Sultan Alfarhood, Mejdl Safran, Dunren Che
Summary: Accurate prediction of heart failure can help prevent life-threatening situations. Developing a machine learning metamodel based on clinical test data, this research proposes a model that can predict heart failure more accurately than other machine learning models, with an accuracy of 87%. The metamodel utilizes a combined dataset comprising five well-known heart datasets and incorporates various machine learning algorithms.
Review
Chemistry, Analytical
Javier Manuel Aguiar-Perez, Maria Angeles Perez-Juarez
Summary: Smart grids can forecast customers' energy demand and transmit electricity accordingly by considering the expected demand. To tackle the challenges of demand forecasting with large amounts of data generated by smart grids, modern data-driven techniques are needed. Among these techniques, Long Short-Term Memory networks based on Recurrent Neural Networks are widely used for learning patterns from customer data and predicting demand for various time horizons. This paper emphasizes the importance of demand forecasting and related factors in the context of smart grids, and shares experiences of using Deep Learning techniques for this purpose.
Article
Energy & Fuels
Jaiyesh Chahar, Jayant Verma, Divyanshu Vyas, Mukul Goyal
Summary: This study explores the potential use of machine learning-based approaches in the petroleum industry for predicting oil production. The study utilized artificial neural network (ANN), random forest regressor (RF), and gradient boosting regressor (GB) algorithms to forecast daily oil production based on available production parameters. The models were validated using coefficient of determination (R2 score), mean squared error (MSE), and mean absolute error (MAE). The results show that the ANN model performed the best for well 15/9-F-1C with an R2 score of 0.9, while the RF model performed the best for well 15/9-F-12 with an R2 score of 0.98. This novel approach has the potential to assist in oil forecasting in other datasets.
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING
(2022)
Article
Chemistry, Multidisciplinary
Md Mahraj Murshalin Al Moti, Rafsan Shartaj Uddin, Md Abdul Hai, Tanzim Bin Saleh, Md Golam Rabiul Alam, Mohammad Mehedi Hassan, Md Rafiul Hassan
Summary: This research proposes a blockchain-based electricity marketplace for the smart grid environment, introducing a decentralized ledger for trust and traceability among stakeholders. The use of the Stackelberg model and reinforcement learning enables dynamic price forecasting, optimizing the smart grid system.
APPLIED SCIENCES-BASEL
(2022)
Article
Engineering, Electrical & Electronic
Ryan S. Tulabing, Brian C. Mitchell, Grant A. Covic, John T. Boys
Summary: The increased adoption of electric vehicles is challenging the traditional electricity grid, especially at the local residential network level, due to higher peak demands, system overloads, and voltage violations. This study proposes a non-wire solution called Localized Demand Control, which enables the local grid to follow a preferred demand curve through coordinated actions of flexible loads. The system has been validated in a real-world microgrid facility and recommended rates for gradual technology adoption in the next 20 years have been created through simulations of a representative network.
IEEE TRANSACTIONS ON SMART GRID
(2023)
Article
Engineering, Civil
Maria Xenochristou, Chris Hutton, Jan Hofman, Zoran Kapelan
Summary: This study uses smart demand metering data, household characteristics, and weather data to develop a demand forecasting methodology that combines the accuracy of machine learning models with the interpretability of statistical methods. Results show that past consumption data are the most important, while a combination of household and temporal characteristics can produce a model with similar accuracy.
JOURNAL OF WATER RESOURCES PLANNING AND MANAGEMENT
(2021)
Article
Materials Science, Textiles
Ilker Guven, Ozer Uygun, Fuat Simsir
Summary: Demand forecasting is crucial for apparel retail stores, especially those with a wide range of products and fluctuating demand. This study utilized machine learning methods such as random forest and k-nearest neighbour to forecast intermittent demand, considering various variables including special days that may affect sales. By using four different datasets and 28 variables, the study found that random forest outperformed k-nearest neighbour in all datasets in terms of accuracy and reliability.
TEKSTIL VE KONFEKSIYON
(2021)
Article
Environmental Sciences
Yasin Wahid Rabby, Md Belal Hossain, Joynal Abedin
Summary: This study evaluates and compares the performance of three machine learning models (KNN, RF, and XGBoost) for landslide susceptibility mapping in Rangamati District, Bangladesh, and finds that XGBoost has the best performance.
GEOCARTO INTERNATIONAL
(2022)
Article
Green & Sustainable Science & Technology
Kang-Min Koo, Kuk-Heon Han, Kyung-Soo Jun, Gyumin Lee, Jung-Sik Kim, Kyung-Taek Yum
Summary: Accurately forecasting water demand is crucial for the efficient and stable operation of a water supply system. The introduction of the Smart Water Grid allows real-time monitoring of water consumption through smart meters for short-term demand forecasting.
Article
Energy & Fuels
Xinran Yu, Semiha Ergan
Summary: This study proposes a machine learning method to infer the DR performance of data-scarce buildings by leveraging an accurate prediction model. The results demonstrate increased accuracy in DR capacities and the identification of potential demand shaving capacity in buildings.
Article
Energy & Fuels
Bikash Kumar Saw, Aashish Kumar Bohre, Jalpa H. Jobanputra, Mohan Lal Kolhe
Summary: This paper reports the concurrent planning of multiple Distributed Generations (DGs) with reconfiguration in IEEE 33 and 69 bus Radial Distribution Network (RDN) using Adaptive Particle Swarm Optimization (APSO) and hybrid Grey Wolf-Particle Swarm Optimization (GWO-PSO). A novel multiple objective-based fitness function (MOFF) is proposed based on various performance parameters and economic perspectives. Two case studies on IEEE 33 and 69 bus RDN are presented to validate the proposed methodology. The results analysis shows better performance with GWO-PSO and enhanced short-circuit tolerance capacity of the RDN.
Article
Energy & Fuels
Paramjeet Kaur, Krishna Teerth Chaturvedi, Mohan Lal Kolhe
Summary: CHP plants in the smart network environment require optimal techno-economic dispatching to provide both electricity and heat demand while minimizing energy cost.
Article
Energy & Fuels
Konara Mudiyanselage Sandun Y. Konara, Mohan Lal Kolhe, Nils Ulltveit-Moe, Indika A. M. Balapuwaduge
Summary: This study aims to improve the charging reliability of electric vehicle (EV) users in a fast charging station (FCS) by proposing charging coordination strategies and analyzing the performance of off-board mobile chargers (MOBCs) reservation. The proposed strategies allow optimal utilization of limited charging resources while ensuring reliable charging for plugged-in EVs under random failures. The results show that the strategies outperform the current charging process in terms of resource utilization, reliability, and satisfactory quality of service for EV users.
Article
Energy & Fuels
Thomas B. B. Ferriday, Suhas Nuggehalli Sampathkumar, Peter Hugh Middleton, Jan Van Herle, Mohan Lal Kolhe
Summary: Nickel foam substrates are commonly used as porous 3D substrates for renewable energy applications. This study reports the effects of acid washing on the electrochemical performance of these substrates. It was found that acid washing increased the current density and electrochemically active surface area, and improved the initial water dissociation step of the hydrogen evolution reaction. This demonstrates the utility of acid washing nickel foam electrodes.
Article
Energy & Fuels
Akash Talwariya, Pushpendra Singh, Jalpa H. Jobanputra, Mohan Lal Kolhe
Summary: Renewable energy generation is crucial to address the challenges posed by fossil fuels, environmental impact, and variable consumption patterns. This study proposes a machine learning-based neural network algorithm to accurately forecast the generation and consumption of renewable energy. The results demonstrate that the proposed methods significantly improve the accuracy of solar and wind power generation forecasting as well as energy consumption forecast.
ENERGY SOURCES PART A-RECOVERY UTILIZATION AND ENVIRONMENTAL EFFECTS
(2023)
Article
Engineering, Chemical
Paramjeet Kaur, Krishna Teerth Chaturvedi, Mohan Lal Kolhe
Summary: Cogeneration, also known as combined heat and power (CHP) system, reduces costs and emissions by using waste heat from steam turbines and helps overcome the intermittency of renewable energy. This study analysed the economic dispatch of a CHP system connected with a wind power plant and found that operational costs were significantly reduced with the integration of wind energy.
Article
Electrochemistry
Konara Mudiyanselage Sandun Y. Konara, Mohan Lal Kolhe, Nils Ulltveit-Moe, Indika A. M. Balapuwaduge
Summary: The key challenge of electric vehicle (EV) rapid growth is how to manage energy charging resources optimally at EV fast-charging stations (FCSs). The rapid deployment of fast-charging stations provides a viable solution to the potential driving range anxiety and charging autonomy. This study proposes resource allocation and charging coordination strategies to maximize the utilization of limited charging resources by opportunistic ultra-fast charging EV users (UEVs) when pre-scheduled users (SEVs) do not occupy them.
Article
Green & Sustainable Science & Technology
Manuel S. Mathew, Mohan Lal Kolhe, Surya Teja Kandukuri, Christian W. Omlin
Summary: The objective of this study is to propose a real-time management system for EV charging that maximizes the utilization of renewable energy. An electric power distribution network with average and peak demands of 1.51 MW and 3.6 MW respectively was chosen. Models based on k-Nearest Neighbors algorithms were developed to predict the performances of renewable energy systems, and a demand side management algorithm was developed for the charge/discharge scheduling of EVs.
JOURNAL OF CLEANER PRODUCTION
(2023)
Article
Energy & Fuels
Sven Myrdahl Opalic, Fabrizio Palumbo, Morten Goodwin, Lei Jiao, Henrik Kofoed Nielsen, Mohan Lal Kolhe
Summary: In this paper, the combination of augmented random search algorithm and artificial neural networks is proposed to optimize the energy cost in a smart warehouse by controlling the battery energy storage system and the thermal energy storage system simultaneously. The developed solution demonstrates superior performance in terms of energy cost minimization compared to the state-of-the-art solutions.
JOURNAL OF ENERGY STORAGE
(2023)
Article
Green & Sustainable Science & Technology
Sonali Nandanwar, Narayan Prasad Patidar, M. Deva Brinda, Mohan Lal Kolhe
Summary: This paper proposes a decision tree-based approach for real-time estimation of power flows and node voltages in electrical energy networks. The decision tree accurately estimates the line power flows and bus voltages, providing the needed information for prioritizing power injection from clean energy resources in sustainable energy networks.
CLEANER ENGINEERING AND TECHNOLOGY
(2023)
Article
Engineering, Environmental
T. B. Ferriday, P. H. Middleton, M. L. Kolhe, J. Van Herle
Summary: This study investigates the effects of annealing temperature and time on the activity and stability of the anode and cathode electrodes in an anion exchange membrane water electrolyser (AEMWE). The results show that moderate heat-treatment improves morphology, enhances reaction kinetics, and increases surface area. The annealing temperature also affects hydrogen adsorption. The stability of the electrodes is carefully characterized, and a degradation pathway for carbon catalysts is proposed.
CHEMICAL ENGINEERING JOURNAL ADVANCES
(2023)
Article
Energy & Fuels
Akira Nishimura, Daiki Mishima, Kyohei Toyoda, Syogo Ito, Mohan Lal Kolhe
Summary: The effect of separator thickness on the mass distributions and current density in PEFC is investigated in this study. Numerical simulations using a 3D model show that using a 2.0mm thickness separator results in lower molar concentrations of H-2 and O-2 at initial operation temperatures of 363K and 373K. Additionally, lower molar concentration of H2O is observed along the gas channel at 373K for separators with thicknesses of 1.5mm and 1.0mm. Moreover, the current density is highest when using a 2.0mm thickness separator, regardless of the initial operation temperature, with the most significant difference observed in the case of A40%RH&C40%RH.
Article
Energy & Fuels
Amandeep Gill, Pushpendra Singh, Jalpa H. Jobanputra, Mohan Lal Kolhe
Summary: This article discusses the optimal placement of distributed energy resources in the distribution network to reduce power loss and enhance voltage quality. By considering constraints such as size, location, number, type, and power factor, intelligent techniques are used to determine the optimal placement strategy.
Article
Computer Science, Information Systems
Surendra Solanki, Vasudev Dehalwar, Jaytrilok Choudhary, Mohan Lal Kolhe, Koki Ogura
Summary: Cognitive radio aims to improve spectrum utilization in wireless communication, with spectrum sensing being a critical component. Traditional methods involve extracting features from received signals, but advancements in AI and deep learning have allowed for more accurate spectrum sensing through models like a hybrid CNN-RNN. Transfer learning is used to enhance accuracy for low SNR signals, with improved performance compared to other models in the field.
Proceedings Paper
Construction & Building Technology
Ruben Lliuyacc-Blas, Svein Olav Nyberg, Muhandiram Arachchige Subodha Tharangi Ireshika, Mohan Lal Kolhe, Peter Kepplinger
Summary: This study applies Bayesian statistical inference to estimate the PV hosting capacities of more than 5000 feeders in Austria. The results show that the hosting capacity of the majority of feeders can be estimated with a small error using only a random sample of 5%. The proposed approach also allows for the evaluation of new parameters to improve the accuracy of hosting capacity estimation.
PROCEEDINGS OF 2022 12TH INTERNATIONAL CONFERENCE ON POWER, ENERGY AND ELECTRICAL ENGINEERING (CPEEE 2022)
(2022)
Article
Green & Sustainable Science & Technology
Lars odegaard Bentsen, Narada Dilp Warakagoda, Roy Stenbro, Paal Engelstad
Summary: This study investigates uncertainty modeling in wind power forecasting using different parametric and non-parametric methods. Johnson's SU distribution is found to outperform Gaussian distributions in predicting wind power. This research contributes to the literature by introducing Johnson's SU distribution as a candidate for probabilistic wind forecasting.
JOURNAL OF CLEANER PRODUCTION
(2024)
Article
Green & Sustainable Science & Technology
Xing Liu, Qiuchen Wang, Yunhao Wen, Long Li, Xinfang Zhang, Yi Wang
Summary: This study analyzes the characteristics of process parameters in three lean gas ethane recovery processes and establishes a prediction and multiobjective optimization model for ethane recovery and system energy consumption. A new method for comparing ethane recovery processes for lean gas is proposed, and the addition of extra coolers improves the ethane recovery. The support vector regression model based on grey wolf optimization demonstrates the highest prediction accuracy, and the multiobjective multiverse optimization algorithm shows the best optimization performance and diversity in the solutions.
JOURNAL OF CLEANER PRODUCTION
(2024)
Article
Green & Sustainable Science & Technology
Cairong Song, Haidong Yang, Xian-Bing Meng, Pan Yang, Jianyang Cai, Hao Bao, Kangkang Xu
Summary: The paper proposes a novel deep learning-based prediction framework, aTCN-LSTM, for accurate cooling load predictions. The framework utilizes a gate-controlled multi-head temporal convolutional network and a sparse probabilistic self-attention mechanism with a bidirectional long short-term memory network to capture both temporal and long-term dependencies in the cooling load sequences. Experimental results demonstrate the effectiveness and superiority of the proposed method, which can serve as an effective guide for HVAC chiller scheduling and demand management initiatives.
JOURNAL OF CLEANER PRODUCTION
(2024)
Article
Green & Sustainable Science & Technology
Zhe Chen, Xiaojing Li, Xianli Xia, Jizhou Zhang
Summary: This study uses survey data from the Loess Plateau in China to evaluate the impact of social interaction on the adoption of soil and water conservation (SWC) technology by farmers. The study finds that social interaction increases the likelihood of farmers adopting SWC, and internet use moderates this effect. The positive impact of social interaction on SWC adoption is more pronounced for farmers in larger villages and those who join cooperative societies.
JOURNAL OF CLEANER PRODUCTION
(2024)
Article
Green & Sustainable Science & Technology
Chenghua Zhang, Yunfei Yan, Kaiming Shen, Zongguo Xue, Jingxiang You, Yonghong Wu, Ziqiang He
Summary: This paper reports a novel method that significantly improves combustion performance, including heat transfer enhancement under steady-state conditions and adaptive stable flame regulation under velocity sudden increase.
JOURNAL OF CLEANER PRODUCTION
(2024)
