A novel time-of-use tariff design based on Gaussian Mixture Model

Ran Li, Zhimin Wang, Chenghong Gu, Furong Li, Hao Wu

Research output: Contribution to journalArticlepeer-review

81 Citations (SciVal)


This paper proposes a novel method to design feasible Time-of-Use (ToU) tariffs for domestic customers from flat rate tariffs by clustering techniques. The method is dedicated to designing the fundamental window patterns of ToU tariffs rather than optimising exact prices for each settlement period. It makes use of Gaussian Mixture Model clustering technique to group half-hour interval flat rate tariffs within a day into clusters to determine ToU tariffs. Two groups of ToU are designed following the variations in energy prices and system loading demand respectively. With a number of price-oriented and load-oriented ToU tariffs, the investigation is further carried out to explore the effects of these ToU tariffs on domestic demand response (DR), especially in terms of energy cost reduction and peak shaving. The DR in this paper is assumed to be enabled by household storage battery and the objective of the DR in response to each ToU tariff is to minimise the electricity bills for end customers and/or mitigate network pressures. An example study in the UK case is also carried out to demonstrate the effectiveness of the proposed methods.

Original languageEnglish
Pages (from-to)1530-1536
Number of pages7
JournalApplied Energy
Early online date21 Mar 2015
Publication statusPublished - 15 Jan 2016


  • Benefit quantification
  • Clustering
  • Demand response
  • Energy storage
  • Time-of-use tariff


Dive into the research topics of 'A novel time-of-use tariff design based on Gaussian Mixture Model'. Together they form a unique fingerprint.

Cite this