Article
Engineering, Chemical
Yinlong Liu, Jinze Li
Summary: The long-term demand forecast for annual national electricity and energy consumption is crucial for strategic planning, power system installation programming, energy investment planning, and next-generation unit construction. In this study, three machine learning algorithms were used to train forecasting models using data on population, GDP, temperature, sunshine, rainfall, and frost days from 1993-2019. The results showed an increase in population and electricity consumption in the UK over the years, while GDP showed fluctuations. The models performed well on the training set but had some overestimation on the test set.
Article
Environmental Sciences
Ying Deng, Xiaoling Zhou, Jiao Shen, Ge Xiao, Huachang Hong, Hongjun Lin, Fuyong Wu, Bao-Qiang Liao
Summary: This study investigated the feasibility of different prediction models for estimating the occurrence of haloketones in water supply systems. The results showed that RBF and BP artificial neural networks outperformed linear/log linear models in terms of prediction ability, with RBF ANN demonstrating the capability to recognize complex nonlinear relationships between haloketones occurrence and water quality.
SCIENCE OF THE TOTAL ENVIRONMENT
(2021)
Article
Environmental Sciences
Z. Yi, J. Qin, Z. Deng, Q. Liu
Summary: The study established a hybrid neural network model for predicting NOx emission in iron and steel enterprises, by optimizing the model structure and setting up connection layer to improve prediction accuracy and convergence speed.
INTERNATIONAL JOURNAL OF ENVIRONMENTAL SCIENCE AND TECHNOLOGY
(2022)
Article
Engineering, Multidisciplinary
Yan Liu, Min Zhao
Summary: This research proposes a two-stage obsolescence forecasting model, utilizing ELECTRE I method and radial basis function neural network, with three improvements leading to an improved prediction accuracy from 92.2% to 95.23%.
AIN SHAMS ENGINEERING JOURNAL
(2022)
Article
Computer Science, Hardware & Architecture
Yuvaraj Natarajan, Srihari Kannan, Chandragandhi Selvaraj, Sachi Nandan Mohanty
Summary: The study utilizes a large feature set to optimize the prediction of energy generation from PV plants using Radial Belief Neural Network (RBNN). The experimental results demonstrate that RBNN provides improved prediction accuracy with reduced errors compared to other deep learning and machine learning classifiers.
SUSTAINABLE COMPUTING-INFORMATICS & SYSTEMS
(2021)
Article
Energy & Fuels
Wangwang Yang, Jing Shi, Shujian Li, Zhaofang Song, Zitong Zhang, Zexu Chen
Summary: This paper proposes a deep learning load forecasting model considering multi-time scale electricity consumption behavior of single household resident user to achieve high-accuracy and stable load forecasting. The model utilizes similarity analysis and feature selection to improve the accuracy and stability of the forecast. Evaluation results show that the proposed model outperforms the traditional LSTM model in terms of Mean Arctangent Absolute Percentage Error (MAAPE).
Article
Multidisciplinary Sciences
Lina Alhmoud, Qosai Nawafleh, Waled Merrji
Summary: The electricity distribution system serves as a link between the utility and the end users, facing issues with unbalanced loads. Manual load swapping in radial distribution systems is an effective method for phase balancing. With the development of smart grids and automated networks, dynamic phase balancing is receiving more attention for improved performance.
Article
Engineering, Chemical
Nehal Elshaboury, Abobakr Al-Sakkaf, Ghasan Alfalah, Eslam Mohammed Abdelkader
Summary: This study develops a model based on specific factors to anticipate sources of failure in oil pipelines, providing assistance to operators and decision makers in prioritizing maintenance and replacement actions.
Article
Chemistry, Multidisciplinary
Fatih Unal, Abdulaziz Almalaq, Sami Ekici
Summary: Short-term load forecasting models are crucial for distribution companies to make effective decisions, especially when forecasting load profiles of many end-users at the customer-level which faces challenges such as high variability and uncertainty. The novel hybrid deep learning approach for energy consumption prediction outperforms traditional prediction models, showing higher accuracy and robustness.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Artificial Intelligence
Wei Sun, Bin Tan, Qiqi Wang
Summary: Improving the reliability of wind speed forecasting in wind power generation is crucial, and this study introduces a hybrid forecasting system using secondary decomposition and neural network, demonstrating the competitive strength of this combination strategy.
APPLIED SOFT COMPUTING
(2021)
Article
Energy & Fuels
Yanhong Wu, Peibo Xie, Aida Dahlak
Summary: The study introduces a neural network model for predicting water production capacity in solar seawater greenhouse desalination, integrating different optimization algorithms. By investigating the impact of hidden layer neuron numbers, accurate prediction results were obtained. The optimized neural network model showed superior forecasting accuracy under specific parameters.
Article
Engineering, Electrical & Electronic
Jinsong Wang, Xuhui Chen, Fan Zhang, Fangxi Chen, Yi Xin
Summary: The energy consumption of buildings is rising steadily, and deep learning techniques offer advanced forecasting capabilities to manage electricity demand efficiently.
JOURNAL OF MODERN POWER SYSTEMS AND CLEAN ENERGY
(2021)
Article
Education, Scientific Disciplines
Hui Wen, Tao Yan, Zhiqiang Liu, Deli Chen
Summary: An integrated neural network model with pre-RBF kernels is proposed to improve the network performance of RBF and BP networks on complex nonlinear problems. By connecting the RBF kernel mapping layer and BP neural network, local features are effectively extracted to improve separability and learning and classification in the kernel space can be performed. The proposed model combines the advantages of RBF and BP networks, and improves the performance of both networks.
Article
Energy & Fuels
Bian Haihong, Wang Qian, Xu Guozheng, Zhao Xiu
Summary: This paper proposes a short-term power load forecasting method based on accumulated temperature effect and improved Temporal Convolutional Network. The method considers the multi-dimensionality of load data and the continuity of time series, and achieves optimal load estimation through TCN and BP Network. The calculation example shows that the method has high prediction accuracy.
Article
Engineering, Electrical & Electronic
N. M. M. Bendaoud, N. Farah, S. Ben Ahmed
Summary: This paper introduces an innovative load forecasting approach using Load Profiles (LPs) to accurately model electrical energy and develop efficient forecasting systems. The study analyzes the power consumption in Algeria and applies temperature profiles to capture seasonal fluctuations. Short-term and mid-term load forecasting models are developed using Artificial Intelligence techniques, including a two-dimensional Convolutional Neural Network (CNN). The AI-based and LP-based models both achieve high prediction accuracies, with the two-dimensional CNN producing the best results.
ELECTRIC POWER SYSTEMS RESEARCH
(2022)
Article
Computer Science, Interdisciplinary Applications
Xiaolin Wang, Liyi Zhan, Yong Zhang, Teng Fei, Ming-Lang Tseng
Summary: This study proposes an environmental cold chain logistics distribution center location model to reduce transportation costs and carbon emissions. It also introduces a hybrid arithmetic whale optimization algorithm to overcome the limitations of the conventional algorithm.
COMPUTERS & INDUSTRIAL ENGINEERING
(2024)
Article
Computer Science, Interdisciplinary Applications
Hong-yu Liu, Shou-feng Ji, Yuan-yuan Ji
Summary: This study proposes an architecture that utilizes Ethereum to investigate the production-inventory-delivery problem in Physical Internet (PI), and develops an iterative heuristic algorithm that outperforms other algorithms. However, due to gas prices and consumption, blockchain technology may not always be the optimal solution.
COMPUTERS & INDUSTRIAL ENGINEERING
(2024)
Article
Computer Science, Interdisciplinary Applications
Paraskevi Th. Zacharia, Elias K. Xidias, Andreas C. Nearchou
Summary: This article discusses the assembly line balancing problem in production lines with collaborative robots. Collaborative robots have the potential to improve automation, productivity, accuracy, and flexibility in manufacturing. The article explores the use of a problem-specific metaheuristic to solve this complex problem under uncertainty.
COMPUTERS & INDUSTRIAL ENGINEERING
(2024)
