Overview and performance assessment of the clustering methods for electrical load pattern grouping

[tctuvan]

Free download pdf for Ketnooi members

abstract
In the current structure of the electricity business, distribution and supply services have been unbundled
in many jurisdictions. As a consequence of unbundling, electricity supply to customers is now provided
on a competitive basis. In this context, the electricity suppliers need to get accurate information on the
actual behaviour of their customers for setting up dedicated commercial offers. Customer grouping on
the basis of consumption pattern similarity is likely to provide effective results. This paper provides an
overview of the clustering techniques used to establish suitable customer grouping, included in a general
scheme for analysing electrical load pattern data. The characteristics of the various stages of the
customer grouping procedure are illustrated and discussed, providing links to relevant literature refer-
ences. The specific aspect of assessing the performance of the clustering algorithms for load pattern
grouping is then addressed, showing how the parameters used to formulate different clustering methods
impact on the clustering validity indicators. It emerges that the clustering methods able to isolate the
outliers exhibit the best performance. The implications of this result on the use of the clustering methods
for electrical load pattern grouping from the operator’s point of view are discussed.
1. Introduction
Enhanced knowledge on the shape of the electricity consump-
tion can be decidedly useful to deal with effective management of
local generation and loads for energy system planning and opera-
tion [1e6]. The attention towards the nature of the electricity
consumption is becoming increasingly high, also owing to avail-
ability of advanced technology for load control and to emerging
opportunities for flexible demand management, producing incen-
tives and rewards to the participating customers [7e10].
In most restructured electricity markets, the distribution and
supply services have been unbundled. The electricity suppliers are
now operating within a competitive environment, with some
degrees of freedom in formulating the tariff offers, provided that
their offers meet the requirements set by the regulatory authorities
in the formof price or revenue caps [11,12]. Each tariff is formulated
with reference to a specific customer category, defined by a series of
technical and economic attributes.
Conceptually, electricity customer categorisation could follow
the rules of segmentation referring to the commercial types of
activity, as established for instance by the national institutes of
statistics. However, the load patterns of the customers belonging to
the same type of activity or associated to the same commercial code
may exhibit large differences [13,14]. As such, categorisations based
on the type of activity and on commercial codes are generally not
efficient for representing the specific aspects of the electricity
consumption. The distinction can then be limited to a few macro-
categories (e.g., residential, industrial, commercial, or other specific
categories such as electric lighting and traction). Further identifi-
cation of some “external” features can be useful to obtain a more
refined customer partitioning into macro-categories. Possible
external features are the rated values of electrical quantities (e.g.,
the contract power and the supply voltage level), and other infor-
mation such as the annual active and reactive energy (maximum,
minimum, average value and standard deviation), the utilisation
level (defined as the energy consumption to rated power ratio), and
the power factor. Moreover, it is possible to build separate models
for weather-dependent loads. Using macro-categories, the number
of load patterns to be handled togetherwithin eachmacro-category
by the categorisationmethods is reduced with respect to the whole
set of electricity customers, making the calculation procedures
more affordable.
Load pattern categorisation for tariff purposes is typically per-
formed on aggregate residential load data, or on individual non-
residential load data. Residential consumers are generally not
handled as individual entities, for the following reasons:

Do Drive thay đổi chính sách, nên một số link cũ yêu cầu duyệt download. các bạn chỉ cần làm theo hướng dẫn.
Password giải nén nếu cần: ket-noi.com | Bấm trực tiếp vào Link để tải:

You must be registered for see links