A non‐intrusive Smart metering system: Analytics and simulation of power consumption

Fecil'ak, Peter; Pekár, Adrián; Ádám, Norbert; Baláž, Anton; Chovancová, Eva

doi:10.1002/cpe.5250

Cited by 6 publications

(2 citation statements)

References 18 publications

(29 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many works have treated the implementation of the forecasting algorithms for energy prediction and PV generation forecasting [10] [11][12] [13]. Renato et al [14] [15] have used WSN to measure electrical energy. They tested their measurement approach in an environment of largescale smart meters.…”

Section: Introductionmentioning

confidence: 99%

Novel Training Methods Based ANN for the Consumed Energy Forecasting

Farhat¹,

Cherif²

2022

Advances in Intelligent Systems Research

View full text Add to dashboard Cite

Artificial Neural Networks have demonstrated best effectiveness and excellent scheduling capabilities in realizing many purposes like recognition, clustering, classification, management and even prediction. For this reason, we have used RBF based Artificial NN for the dynamic forecasting of load and Photovoltaic production using many operations like forecasting, training and validation of the data accuracy. For the validation, the Mean Absolute Percent Error is calculated in function of the most three relevant input parameters, which are previous load and Photovoltaic production measurements, seasonability and temperature or solar radiation data. This work has used real-time measurements of load and Photovoltaic production for their comparison with the predicted load data using RBFNN algorithms for the calculation of MAE and MAPE, to deduce the performance of forecasting algorithms including the accuracy of the forecasted data. This research paper has treated 2 goals. The first is the short-term energy and Photovoltaic production forecasting including training operations. The 2nd goal is the calculation of Mean Absolute Error and Mean Absolute Percent Error via the comparison between the forecasted data and real-time measurements to evaluate the reliability of forecasted data and the performance of the forecasting algorithms. By this way, the dynamic prediction algorithms were implemented, the predicted data were compared to the same time-series measurements and forecasted energy MAPE was calculated.

show abstract

Section: Introductionmentioning

confidence: 99%

Novel Training Methods Based ANN for the Consumed Energy Forecasting

Farhat¹,

Cherif²

2022

Advances in Intelligent Systems Research

View full text Add to dashboard Cite

show abstract

“…The authors presented a prototype chip that contained main components of such sensors. This contribution 9 dealt with the design and experimental implementation of a Smart Metering Architecture which supported different communication technologies-Ethernet, WiFi, and LoRa. Appropriate methods for measuring electrical quantities were analyzed.…”

mentioning

confidence: 99%

Editorial on Innovative Network Systems and Applications together with the Conference on Information Systems Innovations for Community Services

Hodoň

Furtak

Fahrnberger

et al. 2020

Concurrency and Computation

View full text Add to dashboard Cite

The purpose of this special issue is to assemble a selection of best research articles that were presented within the 6th International Conference on Innovative Network Systems and Applications (iNetSApp'18), 1 which was organized under the Federated Conference on Computer Science and Information Systems 2018 (FedCSIS'18), 2 which was held in the Polish city Pozna ń. According to the FedCSIS policy, 23% acceptance rate was kept in all regular paper submissions with the help of the well-structured and experienced conference program committee. Since only the little amount of papers met the quality for the publication in this special issue, other selected best papers from the 18th International Conference on Innovations for Community Services (I4CS 2018), 3 which was held in Žilina, Slovakia, were selected for the publication. For this special issue, only the papers with best review score were selected, thus the quality of the CPE series can be conserved.This special issue focuses on different applications and algorithm developments in the area of modern network systems which encompass a wide range of solutions and technologies, including wireless and wired networks, network systems, services, and applications. The scope of this special issue is broad, aiming at different results in numerous active research areas oriented toward various technical, scientific, and social aspects of network systems and applications. This is supplied by the recent advances in the theory and practice in a wide range of aspects of Internet community services, especially of how community services can be used in many areas and how they have been deployed.The authors in Reference 4 focused on the improvements of the convergence time in IP networks. They introduced a new kind of IP fast re-route (IPFRR) mechanism called the multicast repair (MREP) IPFRR mechanism, which provides an advanced fast reroute technique for Internet service providers' core networks. The M-REP IPFRR mechanism is based on IP multicast and utilizes Protocol Independent Multicast-Dense Mode with the modification of an internal reverse path forwarding check. The M-REP IPFRR mechanism does not depend on any particular routing protocol type (distance-vector or link-state) and requires less system resources because of its precomputation-less character but still provides immediate reaction to failure.The article 5 dealt with the problematic of the work with the large datasets. The article proposed a Flower Index Approach as the method for dealing with the data processing. With this approach, it was possible to remove the impact of the High-Water Mark, as well as to remove useless block loading with no relevant data. On the other hand, it provided effective data access stream using a specific index. Full Table Scan could be the skipped and data could be accessed directly using the index ROWID locators.Data reliability with temporal data retrieval was discussed in the article. 6 The authors referenced an attribute-oriented temporal model with reflection on data grouping tech...

show abstract

Novel Training Methods Based Artificial Neural Network for the Dynamic Prediction of the Consumed Energy

Farhat¹,

Cherif

2022

Mining Intelligence and Knowledge Exploration

View full text Add to dashboard Cite

A non‐intrusive Smart metering system: Analytics and simulation of power consumption

Cited by 6 publications

References 18 publications

Novel Training Methods Based ANN for the Consumed Energy Forecasting

Novel Training Methods Based ANN for the Consumed Energy Forecasting

Editorial on Innovative Network Systems and Applications together with the Conference on Information Systems Innovations for Community Services

Novel Training Methods Based Artificial Neural Network for the Dynamic Prediction of the Consumed Energy

Contact Info

Product

Resources

About