615 Hits in 8.7 sec

Super Resolution Perception for Improving Data Completeness in Smart Grid State Estimation

Gaoqi Liang, Guolong Liu, Junhua Zhao, Yanli Liu, Jinjin Gu, Guangzhong Sun, Zhaoyang Dong
2020 Engineering  
Society, and partially supported by Youth Innovation Promotion Association of Chinese Academy of Sciences.  ...  Municipal Science and Technology Innovation Committee Basic Research project (JCYJ20170410172224515), partially supported by funding from Shenzhen Institute of Artificial Intelligence and Robotics for  ...  : 1 d b b S S b      (17) d d : l W W W W S      (18) Adaptive moment estimation The other disadvantage of the dominant gradient descent methods is that the current gradient is the only  ... 
doi:10.1016/j.eng.2020.06.006 fatcat:t7jtpbkb2bfbbjcij74ejbycl4

AMI-FML: A Privacy-Preserving Federated Machine Learning Framework for AMI [article]

Milan Biswal, Abu Saleh Md Tayeen, Satyajayant Misra
2021 arXiv   pre-print
Machine learning (ML) based smart meter data analytics is very promising for energy management and demand-response applications in the advanced metering infrastructure(AMI).  ...  The aggregator uses the learned model gradients received from the federated smart meters to generate an aggregate, robust RNN model which improves the forecasting accuracy for individual and aggregated  ...  We used LSTM networks to accurately forecast energy consumption based on the historical smart meter readings.  ... 
arXiv:2109.05666v2 fatcat:3jciof2rmbfdvbkhxrkmo23ifi

Efficient Design of Energy Disaggregation Model with BERT-NILM Trained by AdaX Optimization Method for Smart Grid

İsmail Hakkı ÇAVDAR, Vahit FERYAD
2021 Energies  
We propose an efficient BERT-NILM tuned by new adaptive gradient descent with exponential long-term memory (Adax), using a deep learning (DL) architecture based on bidirectional encoder representations  ...  With the updated training function, BERT-NILM outperformed state-of-the-art adaptive moment estimation (Adam) optimization across various metrics on REDD datasets; lastly, we evaluated the TEAD dataset  ...  Acknowledgments: The article was extracted from the PhD thesis prepared by Vahit Feryad under the supervision of ˙Ismail Hakkı Çavdar.  ... 
doi:10.3390/en14154649 fatcat:ailkfndy2bcatc27ycw45io2pm

Data-Stream-Based Intrusion Detection System for Advanced Metering Infrastructure in Smart Grid: A Feasibility Study

Mustafa Amir Faisal, Zeyar Aung, John R. Williams, Abel Sanchez
2015 IEEE Systems Journal  
We propose a realistic and reliable IDS architecture for the whole AMI system which consists of individual IDSs for three different levels of AMI's components: smart meter, data concentrator, and AMI headend  ...  and then to a headend system in the utility side, the security of AMI is of great concern in the deployment of Smart Grid (SG).  ...  new training instance is obtained from the data stream using stochastic gradient descent.  ... 
doi:10.1109/jsyst.2013.2294120 fatcat:7bowkudbg5dvznexkzvoduf24m

Intelligent energy management

Seshadri Srinivasa Raghavan, Alireza Khaligh
2012 Proceedings of the Workshop on Performance Metrics for Intelligent Systems - PerMIS '12  
the weights are adapted using gradient descent as: And there is also: (5.5) Where denotes the derivative of with respect to θ l , which is adapted according to Equation 5.5.  ...  which consists of a combination of the gradient descent algorithm and improved growing cell structure algorithm.  ... 
doi:10.1145/2393091.2393118 dblp:conf/permis/RaghavanK12 fatcat:6aldvjh2d5dhbksq47fp765l6q

A Review of the Recent Developments in Integrating Machine Learning Models with Sensor Devices in the Smart Buildings Sector with a View to Attaining Enhanced Sensing, Energy Efficiency, and Optimal Building Management

Dana-Mihaela Petroșanu, George Căruțașu, Nicoleta Luminița Căruțașu, Alexandru Pîrjan
2019 Energies  
based on the body of knowledge.  ...  Lately, many scientists have focused their research on subjects like smart buildings, sensor devices, virtual sensing, buildings management, Internet of Things (IoT), artificial intelligence in the smart  ...  [144] ; methods discussed and evaluated on the basis of real-life data and the Confusion Matrix [145] ; Accuracy and Root Mean Square Error (RMSE) [9] ; energy cost savings [40] ; Precision, Specificity  ... 
doi:10.3390/en12244745 fatcat:eix222pupjcmddolute2qh4wia

An Ensemble Energy Consumption Forecasting Model Based on Spatial-Temporal Clustering Analysis in Residential Buildings

Anam-Nawaz Khan, Naeem Iqbal, Atif Rizwan, Rashid Ahmad, Do-Hyeun Kim
2021 Energies  
First, the apartment-level historical electric consumption data is clustered. Later the clusters are aggregated based on consumption profiles of consumers.  ...  The dataset used in this study comprises high-resolution electric consumption data acquired through smart meters recorded on an hourly basis over the period of one year.  ...  Conflicts of Interest: The authors declare no conflict of interest regarding the publication of this paper.  ... 
doi:10.3390/en14113020 fatcat:a5bj4gvcvvb7vedq33giyzau3a

Short-Term Energy Consumption Forecasting at the Edge: A Federated Learning Approach

Marco Savi, Fabrizio Olivadese
2021 IEEE Access  
By exploiting Federated Learning and Edge Computing capabilities, many Long Short-Term Memory (LSTM) models are locally trained by different users based on their own historical energy consumption samples  ...  model, with implications on privacy and scalability.  ...  We chose the Mean Absolute Error (MAE) as evaluation metric for the loss function, and we adopt the Adaptive Moment Estimation (Adam) variant of Stochastic Gradient Descent as optimization algorithm, with  ... 
doi:10.1109/access.2021.3094089 fatcat:sk4zz3oukjhbbk3lalykgoosl4

A Two-Layer Water Demand Prediction System in Urban Areas Based on Micro-Services and LSTM Neural Networks

Ahmed Abdelnasser, M. Z. Rashad, Sherif E. Hussein
2020 IEEE Access  
The solution paradigm uses an Internet of Things (IoT) based on micro-services and containers. The design incorporates real-time streaming and infrastructure performance optimization to store data.  ...  In this research, smart water meters were implemented, distributed, and installed in a regional area in Cairo while data were collected at uniform intervals then sent to the cloud instantly.  ...  The Adam optimization algorithm is an extension to stochastic gradient descent that combines both the root mean square propagation, and the adaptive gradient algorithm [68] .  ... 
doi:10.1109/access.2020.3015655 fatcat:bcctlxmrljgd3gk6krjce4i4di

A Comprehensive Survey for Deep-Learning-Based Abnormality Detection in Smart Grids with Multimodal Image Data

Fangrong Zhou, Gang Wen, Yi Ma, Hao Geng, Ran Huang, Ling Pei, Wenxian Yu, Lei Chu, Robert Qiu
2022 Applied Sciences  
Traditional approaches are also summarized together with their performance comparison with deep-learning-based approaches, based on which the necessity, seen in the surveyed literature, of adopting image-data-based  ...  In this paper, we provide a comprehensive survey of the recent advances in abnormality detection in smart grids using multimodal image data, which include visible light, infrared, and optical satellite  ...  YNKJXM20191246), which focuses on the construction of satellite remote-sensing technology for power applications and wide-area intelligent monitoring of environments.  ... 
doi:10.3390/app12115336 fatcat:ot7ptci7bzafng3ytwhkk53ole

IoT with Evolutionary Algorithm Based Deep Learning for Smart Irrigation System

Javaria Amin, Muhammad Almas Anjum, Abida Sharif, Mudassar Raza, Seifedine Kadry, Yunyoung Nam
2022 Computers Materials & Continua  
Secondly, these estimated outcomes are fed into the clustering technique to minimize the predicted error.  ...  The goal of the IoTDL-SIS technique focuses on the design of smart irrigation techniques for effectual water utilization with less human interventions.  ...  Conflicts of Interest: The authors declare that they have no conflicts of interest to report regarding the present study.  ... 
doi:10.32604/cmc.2022.021789 fatcat:klkb57pv6zfslbsmtemqwbwmo4

Forecasting Heating Consumption in Buildings: A Scalable Full-Stack Distributed Engine

Andrea Acquaviva, Daniele Apiletti, Antonio Attanasio, Elena Baralis, Lorenzo Bottaccioli, Tania Cerquitelli, Silvia Chiusano, Enrico Macii, Patti
2019 Electronics  
To this aim, PHi-CiB relies on a pipeline of three algorithms: the Exponentially Weighted Moving Average, the Multivariate Adaptive Regression Spline, and the Linear Regression with Stochastic Gradient  ...  error and an optimal horizontal scalability.  ...  Adaptive Regression Spline, (iii) PP based on linear regression with stochastic gradient descent.  ... 
doi:10.3390/electronics8050491 fatcat:abyvmeoopvcnjiv2bjysbgpl2m

Survey of machine learning methods for detecting false data injection attacks in power systems

Ali Sayghe, Yaodan Hu, Ioannis Zografopoulos, XiaoRui Liu, Raj Gautam Dutta, Yier Jin, Charalambos Konstantinou
2020 IET Smart Grid  
SE is an essential process performed by the energy management system towards estimating unknown state variables based on system redundant measurements and network topology.  ...  To overcome the limitations of traditional residual-based BDD approaches, datadriven solutions based on machine learning algorithms have been widely adopted for detecting malicious manipulation of sensor  ...  MLPs use back-propagation training algorithms and the weights are updated using gradient descent to minimise the error function. Ashrafuzzaman et al.  ... 
doi:10.1049/iet-stg.2020.0015 fatcat:kzfjgzhmybgntijdpszkhk4p7i

HSIC Bottleneck based Distributed Deep Learning Model for Load Forecasting in Smart Grid with A Comprehensive Survey

Md. Akhtaruzzaman, Mohammad Kamrul Hasan, S. Rayhan Kabir, Siti Norul Huda Sheikh Abdullah, Muhammad Jafar Sadeq, Eklas Hossain
2020 IEEE Access  
HSIC Bottleneck does not sustain the exploding gradients and vanishing gradients issues.  It is based on a single layer-based distributed training process were used the Stochastic Gradient Descent (SGD  ...  data and gradient-based learning methods.  ...  CONFLICTS OF INTEREST The authors declare no conflict of interest.  ... 
doi:10.1109/access.2020.3040083 fatcat:tsqokovkm5gpfdsnm7bph73piu

Development of CNN-based visual recognition air conditioner for smart buildings

Qian Huang, Kangli Hao
2020 Journal of Information Technology in Construction  
To address this challenge, this paper proposes a visual recognition method based on convolutional neural networks (CNN), which can intelligently interpret visual contents of surveillance cameras to identify  ...  Demand-oriented HVAC control largely relies on accurate detection of building occupancy levels and locations.  ...  Relative Errors versus Distance Based on the Data in Point Face toward the camera Estimated distance (meter) Estimated angle (degree) Point Face toward the camera Estimated distance (meter  ... 
doi:10.36680/j.itcon.2020.021 fatcat:ds2rd6tg5zbjflnvgrjhr2ulzm
« Previous Showing results 1 — 15 out of 615 results