Smart meter data analytics using R and Hadoop

Mathiyalagan, P.; Shanmugapriya, A.; Geethu, A. V.

doi:10.1109/eit.2017.8053438

Cited by 6 publications

(2 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dr.P.Mathiyalagan, Ms.A.Shanmugapriya [5] created economical energy conservation policies should be enforced so as to scale back residential electricity consumption victimization R and Hadoop. It's been terminated that The streaming information is loaded into HDFS in a veryhive table, that is additional exported into Rso as to perform prophetic analysis and cargo profileanalysis.Yang Jincheng, Jiang Ping, et al [6] uses the technology ofC5.0 algorithmic program with good meter failure happens thus it ought to be known and also the limitation is merely halfdozen attributes that will have an effect on the good meters were elect to investigate during this paper it's been finished that Results from example verification indicate that accuracy of failure prediction model for good meters supported C5.0 algorithmic program.…”

Section: Related Workmentioning

confidence: 99%

Smart Electric Meter Notification System Using Iot

Vaishnavi¹,

Valarmathi²

2020

Intelligent Systems and Computer Technology

View full text Add to dashboard Cite

Electricity is the basic needs of our life and one cannot think of a world without electricity. In the existing meter reading technology, the meter reading process is done by the help of labor force. But this methodology is subjected to many disadvantages like errors throughout calculation, absence of consumer throughout billing time and additional expenses for the billing method. Existing work aims to reduce the labor force for the billing. An energy measurement through wireless smart meter using IoT is proposed for automatic meter data collection, gives announcement through messages displayed on LCD and energy auditing. To overcome this problem IoT based smart electric meter is developed as proposed project.

show abstract

Section: Related Workmentioning

confidence: 99%

Smart Electric Meter Notification System Using Iot

Vaishnavi¹,

Valarmathi²

2020

Intelligent Systems and Computer Technology

View full text Add to dashboard Cite

show abstract

“…Authors have presented how R can be used to see daily, monthly and quarterly consumption pattern and profile based on consumers' usage. With the help of Apache Hadoop and R, analysis of time series smart meter data by applying ARIMA and ARMA models to forecast the demand for electricity have been introduced by [P. Mathiyalagan et al, 2017]. Energy consumption behavioural shapes of different households show high variance, due to the fact that their decision makings about electricity usage affected by various intra-personal, inter-personal and outside factors was presented by [Zhou and Yang, 2016] to enhance the understanding of social issues in energy consumption from the information science [or more specifically data science] perspective.…”

Section: Literature Reviewmentioning

confidence: 99%

Electricity Consumption Patterns Using Som-Based Twolevel Clustering of Residential Households

Chavda¹,

Pandya²,

Kotwal³

2022

INDJCSE

View full text Add to dashboard Cite

Electricity consumption in residential households' accounts for a huge share of energy use, which encourages researchers, policy makers towards energy conservation of residential household. The goal of Clustering using Unsupervised Machine Learning algorithms is to find likenesses in the data point of D-EC and cluster similar data points of D-EC together. This paper emphasis on application of machine learning techniques for pattern identification with the implementation of dimension reduction technique Self-Organizing Map algorithm trailed by unsupervised clustering algorithms such as K-means, Gaussian Mixture clustering, MiniBatchKMeans, Agglomerative Clustering, Spectral Clustering on D-EC data of electrical usage. Consumers classified into 4 clusters and labelled as per the usage pattern, also identified as a consistent and non-consistent consumer based on their electricity usage. A proposed methodology concluded using SOM followed by Kmeans algorithm which helpful for awareness and alerts to consumers based on consumption patterns participates in demand-supply decision making with timely recommendation.

show abstract