Related references
Note: Only part of the references are listed.
Article
Energy & Fuels
Muhammad Hilal Khan et al.
Summary: Energy consumption in buildings is expected to increase by 40% in the next 20 years, necessitating the development of energy improvement strategies. The introduction of a smart energy management system in buildings has gained momentum worldwide due to its potential in saving energy costs.
Article
Computer Science, Information Systems
Primoz Bencak et al.
Summary: This paper presents a cost-effective Indoor Positioning System (IPS) based on Bluetooth Low Energy (BLE) technology for automating warehouse operations and improving operational efficiency.
Editorial Material
Computer Science, Information Systems
Marco Lanuzza et al.
Review
Computer Science, Information Systems
Walid Osamy et al.
Summary: This survey analyzes the research trends and potential applications of artificial intelligence methods in wireless sensor networks (WSNs). It focuses on the challenges of data collection, aggregation, and dissemination in WSNs and provides a comprehensive discussion on recent studies that used AI methods to address these challenges. The survey compares and contrasts different algorithms based on various criteria and explores future research directions and open issues.
Article
Chemistry, Analytical
Sameh Mahjoub et al.
Summary: With the rapid development of smart grids and measuring infrastructure, short term power consumption forecasting has become increasingly important. This study proposes three different machine learning algorithms, namely LSTM, GRU, and Drop-GRU, for time series power forecasting. Experimental results using real data from French cities show that the LSTM model outperforms the other methods, with fewer prediction errors and higher precision. These predictions based on the LSTM method have a significant impact on power quality planning and equipment maintenance.
Article
Computer Science, Information Systems
Magdalena Szymczyk et al.
Summary: Wireless network devices have gained significant attention in research areas such as human health, control systems, smart homes, and the Internet of Things (IoT). This paper focuses on the energy consumption aspects of sensor data transmission using wireless Bluetooth Low Energy Mesh Long Range (BLE-M-LR) technology and presents findings from testing different operation modes and sensor-side processing procedures.
Article
Computer Science, Information Systems
Chia-Wei Tsai et al.
Summary: Due to the climate crisis, energy-saving and carbon reduction have become the top priority for all countries. The popularity of advanced metering infrastructure and smart meters has reduced the cost of acquiring data on residential electricity consumption. Machine learning has been used to analyze the complex consumption behaviors in residential electricity consumption for energy saving and carbon reduction measures, with the identification of abnormal consumption behaviors as a main subtopic. However, current methods based on low-level features collected by sensors and meters have low training efficiency due to the large number of dimensions and redundant information. This study proposes the use of autoencoder, a deep learning technology, to extract high-level electricity consumption information and improve anomaly detection performance. One-class SVM models are trained using high-level features of actual residential users to validate the benefits of high-level features.
Article
Computer Science, Information Systems
Shun Li et al.
Summary: An improved convolutional long- and short-term memory (CLSTM) hybrid neural network is proposed to predict photovoltaic (PV) power output. The network utilizes a fluctuation feature identification model to classify samples based on weather changes, adapts variational modal decomposition for multimodal characteristics, and uses an optimized sparrow search algorithm (SSA) to train the LSTM and CNN models. The experimental results show that the proposed method achieves better accuracy and adapts to weather changes more effectively compared to other methods.
Article
Energy & Fuels
Kusnandar et al.
Summary: The energy use intensity of convenience stores is higher due to a compact footprint but a high density of equipment. This study evaluates energy consumption and performs a CFD simulation to understand the impact of cold storage showcase equipment on the environment.
Review
Chemistry, Analytical
Alessandro Massaro et al.
Summary: This paper provides a systematic review of complex energy monitoring and control systems, focusing on sensors, technology choices, advanced measurement methods, and energy Key Performance Indicators. The study aims to provide helpful insights for modeling and simulating energy systems in detail for performance prediction purposes.
Article
Computer Science, Information Systems
Damian Blaszczok et al.
Summary: This paper discusses the characteristics of electricity customers in small and medium-sized enterprises, focusing on the system of unbalanced current consumption and power factor polarization. It introduces the use of artificial neural networks for reactive power forecasting, which can help optimize reactive power compensation strategies.
Article
Computer Science, Information Systems
Bowen Ren et al.
Summary: The study introduces a prediction model combining multi-dimensional feature fusion technique, which improves the accuracy of integrated energy system load forecasting and demonstrates higher precision in short-term multi-energy load forecasting of electricity, heating, and cooling.
Article
Computer Science, Information Systems
Muhammad Asim Nawaz et al.
Summary: This research investigates the relationship between smart energy consumption and consumer comfort level, proposing an Energy Management System (EMS) as a solution. By incorporating environmental parameters and consumer body dynamics, intelligent control and energy transactions are achieved to improve energy efficiency and reduce costs.
Review
Computer Science, Information Systems
Gopal Krishna et al.
Summary: This study discusses the importance of digital technologies in enhancing battery management systems, such as WSN, IoT, AI, cloud computing, etc., and proposes significant recommendations like AI-based edge computing devices, customized IoT devices, hybrid AI models, and ML-based computing.
Article
Computer Science, Information Systems
Hugo A. Ruiz Florez et al.
Summary: This paper introduces a mathematical modeling approach to solve power flow and state estimation problems in electric power systems using the mathematical programming language AMPL. The advantages of representing these issues through mathematical optimization models in AMPL are highlighted, including handling specific issues not typically considered in classical approaches. The proposed optimization models were validated through several tests, demonstrating their applicability.
Article
Computer Science, Information Systems
Jiansong Tang et al.
Summary: This study proposes a prediction model based on LSTM neural network coupled with wavelet transformation for reservoir scheduling. The model extracts scheduling operation data and utilizes the characteristics of time-series prediction models to achieve high learning capability and prediction accuracy.
Article
Computer Science, Information Systems
Lingsheng Li et al.
Summary: This paper proposes an adaptive seasonal auto-regressive integrated moving average model (ASARIMA) for solar energy harvesting prediction and demonstrates that this model outperforms other algorithms in terms of performance.
Review
Computer Science, Information Systems
Liang Zhao et al.
Summary: With the development of communication technology, indoor air quality (IAQ) monitoring technology has made significant progress. This review conducts a comprehensive analysis of the literature in the relevant fields over the past decade, investigating the development of IAQ monitoring technology and the application of communication technology. It also discusses the problems and challenges in the IAQ monitoring system, providing a reference for researchers and promoting its rapid development.
Article
Computer Science, Information Systems
Miona Andrejevic Stosovic et al.
Summary: This study proposes a method for predicting electricity consumption in a cold storage facility using artificial neural networks. Results show that modified recurrent neural networks outperform ordinary recurrent neural networks, with GRU and LSTM structures with horizons of 168h and 336h demonstrating the best performance.
Article
Computer Science, Information Systems
Tom Springer et al.
Summary: Machine learning models are increasingly being used on embedded platforms, but face challenges in terms of resource constraints. This paper proposes a quality-of-service based resource allocation scheme that uses feedback control to dynamically adjust compute resources, and demonstrates its feasibility through experimentation.
Article
Computer Science, Information Systems
Yousef A. Al-Gumaei et al.
Summary: This article proposes an enhanced ADR+ algorithm that adjusts transmission parameters based on the average signal-to-noise ratio, achieving efficient energy consumption in complex environments. Implementation of the algorithm on the network server demonstrates significant improvements in network delivery ratio and energy efficiency.
Article
Computer Science, Information Systems
Oussama Laayati et al.
Summary: Digitization and machine learning have improved the mining industry by providing insights and solutions to energy consumption. This study presents a new infrastructure for open-pit mines, incorporating artificial intelligence to improve energy efficiency and provide insights on energy consumption and electrical grid quality. The application of a monitoring and peak load forecasting system in an experimental open-pit mine successfully addressed the challenges of energy consumption.
APPLIED SYSTEM INNOVATION
(2022)
Article
Energy & Fuels
Robert Basmadjian et al.
Summary: This paper investigates forecasting methods for renewable energy sources, proposing a methodology with two main phases to generate accurate predictions. By comparing the results of three time-series auto-regression methods and considering different months, the evaluation shows mean absolute error rates between 6.76% and 11.57% when considering both inter- and intra-day scenarios.
Article
Computer Science, Information Systems
Sunny Katyara et al.
Summary: This study uses a Genetic Algorithm to address the proper placement of new DGs in a distribution system and designs energy management models based on a fuzzy inference system, analyzing them in a simulated environment. The research concludes that the optimal placement for a 3.33 MVA synchronous DG is near the load center, and the proposed EMS effectively mitigates various contingencies within approximately 2.5 cycles of operation.
Article
Computer Science, Information Systems
Francisco Sanchez-Sutil et al.
Summary: Smart meters are increasingly important in electrical engineering, with applications ranging from real-time monitoring to load profile studies. The use of LoRa technology has helped solve issues such as coverage and locations without Internet access, allowing for the development of SM networks with large coverage and low consumption.
Article
Computer Science, Information Systems
Van Bui et al.
Summary: This study proposes a novel multi-behavior with bottleneck features long short-term memory (LSTM) model for load forecasting in building energy management systems, combining the predictive behavior of long-term, short-term, and weekly feature models. The model offers improved performance and stability compared to single-model LSTM, displaying excellent adaptability to unexpected situations.
Article
Chemistry, Multidisciplinary
Tzu-Lun Yuan et al.
Summary: This paper proposes a spline bases-assisted Recurrent Neural Network (RNN) for Short-term Load Forecasting (STLF), which accurately predicts the short-term variations in power demand. Experimental results show that the method can help system operators accommodate unexpected load changes, with great potential for real-time applications.
APPLIED SCIENCES-BASEL
(2021)
Review
Energy & Fuels
Andrzej Lis et al.
Article
Energy & Fuels
Andres M. Alonso et al.
Article
Environmental Sciences
Lenka Demkova et al.
Article
Green & Sustainable Science & Technology
Anna Devitofrancesco et al.
Article
Multidisciplinary Sciences
Mohammed H. Alsharif et al.
Review
Engineering, Electrical & Electronic
Alireza Akrami et al.
JOURNAL OF MODERN POWER SYSTEMS AND CLEAN ENERGY
(2019)
Article
Electrochemistry
Christophe Savard et al.
Review
Construction & Building Technology
Tuan Anh Nguyen et al.
ENERGY AND BUILDINGS
(2013)