A novel approach for load profiling in smart power grids using smart meter data

Khan, Zafar A.; Jayaweera, Dilan; Alvarez-Alvarado, Manuel S.

doi:10.1016/j.epsr.2018.09.013

Cited by 39 publications

(39 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Four clustering techniques, i.e., random forest approach, k-Nearest Neighbour, decision tree and artificial neural network, are compared and it is found that random forest clustered the data better than others. But due to high computational cost and redundancy in data, instead of using raw data, extraction of salient features is considered an important step before clustering [2] [4][5][6][7][8][9][10] [12][13][14]. Features can be found in time [2] [7,8] [13], frequency [8] and time frequency [9] domains in order to have better knowledge about characteristics of meter data.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Then k means clustering technique was used on reduced dataset and it was found that for 32,241 smart meter data (over a period of one week) the optimal number of clusters were 12 (found by evaluating DBI mean index). In [13] a novel approach for modelling smart meter data is proposed using clustering and linearization of smart meter data curves. After pre-processing the data, extended k means algorithm is applied for obtaining the patterns with similar energy consumption.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Domain Feature Extraction for Improved Clustering of Smart Meter Data

Shamim¹,

Rihan²

2020

Technol Econ Smart Grids Sustain Energy

View full text Add to dashboard Cite

The advent of smart grid is a revolution that has enabled power distribution in a more efficient way. However, load forecasting, demand response management and accurate consumer load profiling using smart meter data continue to be challenging industry and research problems. Clustering is an efficient technique for load profiling. K-means clustering algorithm for clustering electricity consumers based on raw meter data directly result in cumbersome, redundant and inefficient computations. This paper presents a methodology for reducing the raw data set dimension via features extraction and cluster the load profiles based on computed features. The feature set formed comprises of Singular Values by Singular Value Decomposition and Wavelet Energy Entropy of approximate and detailed Coefficients. K means Clustering technique is used. The proposed method enables efficient and quick clustering and at the same time the information content in load profiling is preserved. The time consumed for clustering of feature set formed is found to be much less than that of raw data set. By comparing the Silhouette Values K = 6 was found to be the optimal number of clusters with average silhouette coefficient around 0.79. Clustering of load profiles both for Raw Data Set as well as computed Feature Set are compared by evaluating average silhouette value, number of negative silhouettes and computation time for clustering and Silhouette Coefficient was found to be 0.79 by proposed methodology showing better clustering result as compared to raw dataset.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Multi-Domain Feature Extraction for Improved Clustering of Smart Meter Data

Shamim¹,

Rihan²

2020

Technol Econ Smart Grids Sustain Energy

View full text Add to dashboard Cite

show abstract

“…The proposed RPM strategies are investigated based on the electricity consumption of a community consisting of a randomly selected 20 family-houses in Ireland [32]. The data set are collected from the smart meter data with half-hourly records for more than one year [33]. In this study, the temperature and solar energy in Dublin, Ireland are used to evaluate PV generation.…”

Section: Description Of Case Studymentioning

confidence: 99%

Economic Performance of Net-Zero Energy Community under Reward-Penalty Mechanism Considering PV System Reliability

Khan

Gunduz

et al. 2019

Environmental and Climate Technologies

View full text Add to dashboard Cite

Economic performance of net-zero energy building/community (ZEB/ZEC) is an important factor that affects potential investors’ decision on installing renewable energy systems (RES). A reward-penalty mechanism (RPM) is proposed for accelerating the development of zero energy communities, which is developed without considering the reliability effect from RES generation. However, an investigation is deserved for the reliability effect of RES on building economic performance. A case study is therefore conducted based on an assumed community consisting of 20 family houses, in which the electricity load was collected by the smart meter for more than one year. The results show that the proposed RPM works efficiently under an ideal condition, while the costs of the community and its buildings are greatly increased when the effect of PV system reliability is considered. Specifically, the total cost of the community under 1.0ZEC design is 5 005 USD/yr in the first year, which increases to 11 341 USD/yr in the 25th year. By contrast, the total cost of the community under 1.2ZEC design is 5 243 USD/yr in the first year and increases to 9 607 USD/yr in the 25th year. It is believed that the results of this study can provide a progressive perspective for scheme makers and building owners in terms of its economic benefit. Development of enhanced RPM by considering system reliability will be investigated in our future work.

show abstract

“…This variation reflects a nonuniform character of power demand related to on‐peak and off‐peak loads. Such a load profile nonuniformity brings a negative impact on electrical energy generation and distribution . A typical load‐levelling approach applied for “peak shaving” and “valley filling” of daily load profile usually aggregates a number of solutions aimed to control the consumption at the load side.…”

Section: Introductionmentioning

confidence: 99%

“…There are many methods and tools for load profile assessment and analysis. Majority of these methods are based on analysis of the load profile represented as time series (load power against time) . However, this paper focuses on the morphometric method of the load profile analysis proposed in Komenda and Komenda .…”

Section: Introductionmentioning

confidence: 99%

Criteria of morphometric analysis of a daily load profile

Komenda

Vagapov

2019

Int Trans Electr Energ Syst

View full text Add to dashboard Cite

Summary Analysis of electrical loads is crucial for a proper operation and control of electrical energy sources and planning and design of electrical power systems in terms of optimum capacity of the electricity generation. A typical daily load profile significantly varies over the 24‐hour day and requires levelling actions which can be advised from the detailed analysis of the profile. This paper discusses the principles and implementation of morphometric analysis for a daily load profile evaluation using three criteria: roundness, compactness, and elongation. In order to conduct the morphometric analysis, the daily load profile represented as a time series has to be converted into a polygon of a particular form in a radar chart. The criteria for the profile analysis are based on geometrical interpretation of the shape of the polygon. The criterion roundness assesses the maximum and minimum loads of the profile and are related to the ratio of the inner circle of the polygon to the outer circle. The criterion compactness is based on the polygon perimeter and its inner area. The criterion elongation is defined as a relationship between the length of perpendicular to main axis of the polygon and the length of the main axis. The examples of the load profiles represented as a regular polygon and the case study have been used to demonstrate implementation of the analysis using the roundness, compactness, and elongation. It has been shown that the analysis using the morphometric criteria can be effectively applied for the detailed assessment of the load profiles.

show abstract

A novel approach for load profiling in smart power grids using smart meter data

Cited by 39 publications

References 19 publications

Multi-Domain Feature Extraction for Improved Clustering of Smart Meter Data

Multi-Domain Feature Extraction for Improved Clustering of Smart Meter Data

Economic Performance of Net-Zero Energy Community under Reward-Penalty Mechanism Considering PV System Reliability

Criteria of morphometric analysis of a daily load profile

Contact Info

Product

Resources

About