scholarly journals Electric Load Data Compression and Classification Based on Deep Stacked Auto-Encoders

Energies ◽  
2019 ◽  
Vol 12 (4) ◽  
pp. 653 ◽  
Author(s):  
Xiaoyao Huang ◽  
Tianbin Hu ◽  
Chengjin Ye ◽  
Guanhua Xu ◽  
Xiaojian Wang ◽  
...  

With the development of advanced metering infrastructure (AMI), electrical data are collected frequently by smart meters. Consequently, the load data volume and length increase dramatically, which aggravates the data storage and transmission burdens in smart grids. On the other hand, for event detection or market-based demand response applications, load service entities (LSEs) want smart meter readings to be classified in specific and meaningful types. Considering these challenges, a stacked auto-encoder (SAE)-based load data mining approach is proposed. First, an innovative framework for smart meter data flow is established. On the user side, the SAEs are utilized to compress load data in a distributed way. Then, centralized classification is adopted at remote data center by softmax classifier. Through the layer-wise feature extracting of SAE, the sparse and lengthy raw data are expressed in compact forms and then classified based on features. A global fine-tuning strategy based on a well-defined labeled subset is embedded to improve the extracted features and the classification accuracy. Case studies in China and Ireland demonstrate that the proposed method is more capable to achieve the minimum of error and satisfactory compression ratios (CR) than benchmark compressors. It also significantly improves the classification accuracy on both appliance and house level datasets.

F1000Research ◽  
2021 ◽  
Vol 10 ◽  
pp. 1099
Author(s):  
Nagisetty Sridhar ◽  
Dr Chinnaiyan Senthilpari ◽  
Dr Mardeni R ◽  
Dr Wong Hin Yong

Background: With the tremendous increase in the usage of smart meters for industrial/ household purposes, their implementation is considered a crucial challenge in the Internet of Things (IoT) world, leading to a demand for emerging 5G technology. In addition, a large amount of data has to be communicated by smart meters efficiently, which needs a significant enhancement in bandwidth. The power amplifier (PA) plays a major role in deciding the efficiency and bandwidth of the entire communication system. Among the various modes of PAs, a newly developed Class-J mode PA has been proven to achieve high efficiency over a wide bandwidth by maintaining linearity. Methods: This paper proposes a Class-J mode PA design methodology using a CGH40010F-GaN device that operates at a 3.5 GHz frequency to meet the requirements of 5G wireless communication technology for the replacement of existing 4G/LTE technology used for advanced metering infrastructure (AMI) in smart grids. This research's main objective is to design the proper matching networks (M.Ns) to achieve Class-J mode operation that satisfies the bandwidth requirements of 5G smart grid applications. With the target impedances obtained using the load-pull simulation, lumped element matching networks are analyzed and designed in 3 ways using the ADS EDA tool. Results: The simulation results reveal that the proposed Class-J PA provides a maximum drain efficiency (D.E) of 82%, power added efficiency (PAE) of 67% with 13 dB small-signal gain at 3.5 GHz, and output power of 40 dBm (41.4 dBm peak) with a power gain of approximately 7 dB over a bandwidth of approximately 400 MHz with a 28 V power supply into a 50 Ω load. Conclusion: The efficiency and bandwidth of the proposed Class-J PA can be enhanced further by fine-tuning the matching network design to make it more suitable for 5G smart meter/grid applications.


Energies ◽  
2018 ◽  
Vol 12 (1) ◽  
pp. 88 ◽  
Author(s):  
Jen-Hao Teng ◽  
Chia-Wei Chao ◽  
Bin-Han Liu ◽  
Wei-Hao Huang ◽  
Jih-Ching Chiu

Advanced Metering Infrastructure (AMI), the foundation of smart grids, can be used to provide numerous intelligent power applications and services based on the data acquired from AMI. Effective and efficient communication performance between widely-spread smart meters and Data Concentrator Units (DCUs) is one of the most important issues for the successful deployment and operation of AMI and needs to be further investigated. This paper proposes an effective Communication Performance Index (CPI) to assess and supervise the communication performance of each smart meter. Some communication quality measurements that can be easily acquired from a smart meter such as reading success rate and response time are used to design the proposed CPI. Fuzzy logic is adopted to combine these measurements to calculate the proposed CPI. The CPIs for communication paths, DCUs and whole AMI can then be derived from meter CPIs. Simulation and experimental results for small-scale AMIs demonstrate the validity of the proposed CPI. Through the calculated CPIs, the communication performance and stability for AMI can be effectively assessed and supervised.


2021 ◽  
Vol 10 (1) ◽  
pp. 412-418
Author(s):  
Hasventhran Baskaran ◽  
Abbas M. Al-Ghaili ◽  
Zul- Azri Ibrahim ◽  
Fiza Abdul Rahim ◽  
Saravanan Muthaiyah ◽  
...  

Smart grids are the cutting-edge electric power systems that make use of the latest digital communication technologies to supply end-user electricity, but with more effective control and can completely fill end user supply and demand. Advanced Metering Infrastructure (AMI), the backbone of smart grids, can be used to provide a range of power applications and services based on AMI data. The increased deployment of smart meters and AMI have attracted attackers to exploit smart grid vulnerabilities and try to take advantage of the AMI and smart meter’s weakness. One of the possible major attacks in the AMI environment is False Data Injection Attack (FDIA). FDIA will try to manipulate the user’s electric consumption by falsified the data supplied by the smart meter value in a smart grid system using additive and deductive attack methods to cause loss to both customers and utility providers. This paper will explore two possible attacks, the additive and deductive data falsification attack and illustrate the taxonomy of attack behaviors that results in additive and deductive attacks. This paper contributes to real smart meter datasets in order to come up with a financial impact to both energy provider and end-user.


Author(s):  
Yona Lopes ◽  
Natalia Castro Fernandes ◽  
Tiago Bornia de Castro ◽  
Vitor dos Santos Farias ◽  
Julia Drummond Noce ◽  
...  

Advances in smart grids and in communication networks allow the development of an interconnected system where information arising from different sources helps building a more reliable electrical network. Nevertheless, this interconnected system also brings new security threats. In the past, communication networks for electrical systems were restrained to closed and secure areas, which guaranteed network physical security. Due to the integration with smart meters, clouds, and other information sources, physical security to network access is no longer available, which may compromise the electrical system. Besides smart grids bring a huge growth in data volume, which must be managed. In order to achieve a successful smart grid deployment, robust network communication to provide automation among devices is necessary. Therefore, outages caused by passive or active attacks become a real threat. This chapter describes the main architecture flaws that make the system vulnerable to attacks for creating energy disruptions, stealing energy, and breaking privacy.


2013 ◽  
Vol 341-342 ◽  
pp. 1434-1438
Author(s):  
Weng Ting Li ◽  
Yan Zheng ◽  
Shao Bo Liu ◽  
Zhao Zhi Long ◽  
Zhi Cheng Li

With the comprehensive construction of the smart grid, the smart grid operation control and interactive service system will be initially formed. The smart terminal of smart grid are smart meters, and they produce a large number of various data all the time. That how to most effectively manage these massive data storage is an important research point for improving the intelligence service. This paper studies the smart meter massive data storage management based on cloud computing platform. The Hadoop distributed computing platform for smart meter massive data management is reliable, efficient, scalable storage.


2019 ◽  
Vol 8 (2S11) ◽  
pp. 3776-3783

A Smart Grid is the advancement for power matrix with utilization of correspondence innovation with number of powerful meters which are interconnected and two-way data / information flows and has the main goals is to the active participants of consumers to improve quality and reliability of energy usage as for reducing energy consumption and provide increasing reliability as communication between smart meters and consumers. Basically, Smart Grid is working with distributed system manner, and create a network infrastructure as Advanced Metering Infrastructure (AMI) with number of different smart meter. This AMI network includes NAN (Neighbourhood Area Network), have connected with number of smart meters (as wired / wireless) connections with repeater / router as commonly name as Gateway collector which collets the all the consumers information’s and send to the Utility centre. The flow of information as energy usages and power in smart grids is bidirectional which is controlled with the help of software and supporting hardware. Here, with using of Optimized Network Engineering Tools (OPNET) Modeler is one of the most dominant simulation tools for the analysis of communication networks. In this paper, the number of smart meters is connected and create an AMI networks were developed with network parameters which related to different communication as wireless for the compute the different network parameters with respect to the time where data transfer and DDoS attack to the network. The security aspect as detect the DDoS attack to the AMI network and provide a guideline to the future of AMI network where escape strange challenges faced by Distribution companies. Here, in this paper the progressed metering foundation (AMI), which is one of the savvy framework's application regions where make a proving ground and arrangement in the OPNET for assessed the exhibition and power the board model for the framework


2013 ◽  
Vol 397-400 ◽  
pp. 1897-1900
Author(s):  
Jian Yang Zhao ◽  
Jing Mei Cheng ◽  
Wei Hong Ding

As an important part of the smart grid, smart meters and advanced metering infrastructures are given the newly missions connected network. Along with Ethernet development smart meters with measurements and networks, meter with BOA can become reality. In this paper a system of smart meter BOA and its smart meter networking has developed. It has real time displays and storage of smart meter data. The system uses a ARM9 (S3C2440) chip with a Linux operation system. Gathering from breaker via RS232, Data are sent to BOA server through named pipes to be displayed on web. At the same time, these data are stored in embed data base SQLite, for feature managements.


10.29007/x6sn ◽  
2018 ◽  
Author(s):  
Lucas Pereira ◽  
Rodolfo Gonçalves ◽  
Filipe Quintal ◽  
Nuno Nunes

In today’s digital age, massive amounts of data are steadily being generated from various sources, such as smart-phones and social media. Smart-Grids are among the fields that are currently experiencing a burst in the data being generated, in part due to the recent investments in Advanced Metering Infrastructure Systems. In this paper, we present a benchmark between MySQL and MongoDB, when used to store and maintain the data that results from Advanced Metering Infrastructure Systems deployments. Our results show that MongoDB clearly outperforms MySQL for reading operations but at a cost of a much larger database size. As such, when deploying such systems, developers should be aware of this important trade-off that may greatly affect the overall experience.


Author(s):  
Yona Lopes ◽  
Natalia Castro Fernandes ◽  
Tiago Bornia de Castro ◽  
Vitor dos Santos Farias ◽  
Julia Drummond Noce ◽  
...  

Advances in smart grids and in communication networks allow the development of an interconnected system where information arising from different sources helps building a more reliable electrical network. Nevertheless, this interconnected system also brings new security threats. In the past, communication networks for electrical systems were restrained to closed and secure areas, which guaranteed network physical security. Due to the integration with smart meters, clouds, and other information sources, physical security to network access is no longer available, which may compromise the electrical system. Besides smart grids bring a huge growth in data volume, which must be managed. In order to achieve a successful smart grid deployment, robust network communication to provide automation among devices is necessary. Therefore, outages caused by passive or active attacks become a real threat. This chapter describes the main architecture flaws that make the system vulnerable to attacks for creating energy disruptions, stealing energy, and breaking privacy.


Author(s):  
Yona Lopes ◽  
Natalia Castro Fernandes ◽  
Tiago Bornia de Castro ◽  
Vitor dos Santos Farias ◽  
Julia Drummond Noce ◽  
...  

Advances in smart grids and in communication networks allow the development of an interconnected system where information arising from different sources helps building a more reliable electrical network. Nevertheless, this interconnected system also brings new security threats. In the past, communication networks for electrical systems were restrained to closed and secure areas, which guaranteed network physical security. Due to the integration with smart meters, clouds, and other information sources, physical security to network access is no longer available, which may compromise the electrical system. Besides smart grids bring a huge growth in data volume, which must be managed. In order to achieve a successful smart grid deployment, robust network communication to provide automation among devices is necessary. Therefore, outages caused by passive or active attacks become a real threat. This chapter describes the main architecture flaws that make the system vulnerable to attacks for creating energy disruptions, stealing energy, and breaking privacy.


Sign in / Sign up

Export Citation Format

Share Document