Online adaptive clustering algorithm for load profiling

Ray, Guillaume Le

doi:10.1016/j.segan.2018.100181

Cited by 32 publications

(18 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The power load profile, as a representative time series, can intuitively illustrate the user's electricity consumption behaviour patterns. Dynamic time warping (DTW) is a distance measurement widely used for assessing the similarity between time series, finding extensive applications in clustering analysis of power load profiles [31,32]. The fundamental concept behind DTW involves recursively adjusting the alignment of time points between curves, accompanied by distance computation.…”

Section: 21mentioning

confidence: 99%

A novel spatial electric load forecasting method based on LDTW and GCN

Wei,

wen,

Zhang

2023

IET Generation Trans & Dist

View full text Add to dashboard Cite

Spatial power load forecasting is crucial for power grid planning, generation planning, dispatching, efficient power utilization, and sustainable development. The integration of new energy sources and electric vehicles has significantly altered grid loads, increasing the complexity of spatial load forecasting. However, existing techniques fail to fully consider the temporal and spatial correlation characteristics of data, leading to challenges in data identification and summarization. This reduces load forecasting accuracy and prolongs prediction time. To address these issues, a spatial electric load forecasting method based on improved scale limited dynamic time warping (LDTW) and graph convolutional network (GCN) are proposed. Firstly, the improved scale LDTW is used to improve the clustering effect of K‐Mediods++, refine the type of load data, and make the subsequent model training more targeted. Secondly, the interconnections and distances of substations in a real network structure is used to build a graph model to capture the power load distribution. Finally, based on the clustering results and the graph model, GCN‐LSTM is used to construct the spatio‐temporal forecasting algorithm. The proposed algorithm is tested using load data from a region in Shanghai and compared with other advanced algorithms. Results show that the algorithm achieves higher prediction accuracy and efficiency.

show abstract

Section: 21mentioning

confidence: 99%

A novel spatial electric load forecasting method based on LDTW and GCN

Wei,

wen,

Zhang

2023

IET Generation Trans & Dist

View full text Add to dashboard Cite

show abstract

“…For residential consumers the variable nature of individual households makes the interpretation of clustering results ambiguous [23], a challenge that is exacerbated in highly diverse, developing country populations, where economic volatility, income inequality, geographic and social diversity contribute to increased variability of residential energy demand [14] [19]. In other clustering studies of diverse populations pre-binning, or two-stage clustering, was implemented and showed promising results [2], [28], [26].…”

Section: Background and Previous Work 21 Clustering Residential Loadmentioning

confidence: 99%

Identifying optimal clustering structures for residential energy consumption patterns using competency questions

Toussaint

Moodley

2020

Conference of the South African Institute of Computer Scientists and Information Technologists 2020

View full text Add to dashboard Cite

Traditional cluster analysis metrics rank clustering structures in terms of compactness and distinctness of clusters. However, in real world applications this is usually insufficient for selecting the optimal clustering structure. Domain experts and visual analysis are often relied on during evaluation, which results in a selection process that tends to be adhoc, subjective and difficult to reproduce. This work proposes the use of competency questions and a cluster scoring matrix to formalise expert knowledge and application requirements for qualitative evaluation of clustering structures. We show how a qualitative ranking of clustering structures can be integrated with traditional metrics to guide cluster evaluation and selection for generating representative energy consumption profiles that characterise residential electricity demand in South Africa. The approach is shown to be highly effective for identifying usable and expressive consumption profiles within this specific application context, and certainly has wider potential for efficient, transparent and repeatable cluster selection in real-world applications. CCS CONCEPTS • Computing methodologies → Cluster analysis; • Applied computing → Engineering.

show abstract

“…Aiming to move from conventional power systems to smart grids, energy storage becomes a relevant issue. Energy storage in DN is an excellent way to increase the efficiency, quality, and reliability of such systems, providing a significant advantage over fluctuations and allowing frequency and voltage control in distribution systems [18,48].…”

Section: Energy Storage Systems In Distribution Networkmentioning

confidence: 99%

“…As production must always match the consumption, the interrupted use of RES must be compensated in terms of consumption. Solutions are available to optimize the use of RES (i.e., storage, demand management); however, they all rely on accurate information regarding the modes of generation and demand [48].…”

Section: Load Control In the Power Gridmentioning

confidence: 99%

“…Contemporary load profiling methods use clustering algorithms in combination with dimensional reduction based on historical data, creating static typical load profiles that could repeat during a year, considering seasonality and other data periodicity [48]. Load forecasting is crucial for prediction of inputs critical for other algorithms intended for distributed control systems, e.g., assessment of the condition, optimization procedures, voltage maintenance, optimal configuration, maintenance schedules, etc.…”

Section: Load Control In the Power Gridmentioning

confidence: 99%

See 1 more Smart Citation

Review of Voltage and Reactive Power Control Algorithms in Electrical Distribution Networks

Stanelytė

Radziukynas

2019

Energies

View full text Add to dashboard Cite

The traditional unidirectional, passive distribution power grids are rapidly developing into bidirectional, interactive, multi-coordinated smart grids that cover distributed power generation along with advanced information communications and electronic power technologies. To better integrate the use of renewable energy resources into the grid, to improve the voltage stability of distribution grids, to improve the grid protection and to reduce harmonics, one needs to select and control devices with adjustable reactive power (capacitor batteries, transformers, and reactors) and provide certain solutions so that the photovoltaic (PV) converters maintain due to voltage. Conventional compensation methods are no longer appropriate, thus developing measures are necessary that would ensure local reactive and harmonic compensation in case an energy quality problem happens in the low voltage distribution grid. Compared to the centralized methods, artificial intelligence (heuristic) methods are able to distribute computing and communication tasks among control devices.

show abstract

Online adaptive clustering algorithm for load profiling

Cited by 32 publications

References 16 publications

A novel spatial electric load forecasting method based on LDTW and GCN

A novel spatial electric load forecasting method based on LDTW and GCN

Identifying optimal clustering structures for residential energy consumption patterns using competency questions

Review of Voltage and Reactive Power Control Algorithms in Electrical Distribution Networks

Contact Info

Product

Resources

About