Identifying susceptible consumers for demand response and energy efficiency policies by time-series analysis and supplementary approaches

Lesani, Hamid; Fereidunian, Alireza; Kojury-Naftchali, Mohsen

doi:10.1109/iraniancee.2016.7585691

Cited by 11 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Clustering and data mining techniques serving the multiple DRP application when assessing customers and predicting their patterns thus helping in (a) detection of prospect customers and their accurate consumption behaviour suitable for implementing DRPs as in [14][15][16], (b) development of criteria for a good baseline for DRP as in [17]. • Architectures suiting the multiple DRP applications and their characteristics (a) global along with its layers as in [18], (b) generic including functionalities like prediction, learning and other topics as in [19], (c) multiple agent system based with local and global control hubs as in [20] or macro, micro grids connectivity based as in [21].…”

Section: Existing Approaches For the Management Of Multiple Drpsmentioning

confidence: 99%

“…Clustering and data mining techniques serving the multiple DRP application when assessing customers and predicting their patterns thus helping in (a) detection of prospect customers and their accurate consumption behaviour suitable for implementing DRPs as in [14–16], (b) development of criteria for a good baseline for DRP as in [17].…”

Section: Existing Approaches For the Management Of Multiple Drpsmentioning

confidence: 99%

See 1 more Smart Citation

Two stages K‐means and PSO‐based method for optimal allocation of multiple parallel DRPs application & deployment

et al. 2020

View full text Add to dashboard Cite

Different types of Demand Response Programmes (DRPs) exist and can be simultaneously offered by the electrical utilities through established contracts with customers. Operating simultaneously multiple types of DRPs might lead to undesired results. DRPs might have different responses to objectives, time-based ones tend to maximise consumption during lowest tariffs periods while incentive-based ones tend to reduce the usage based on peak events, accordingly contradiction might occur. Thus, synchronising these DRPs and their parameters through an optimised process including customer selection for the appropriate one is a mandatory step. A fair allocation of the various types of DRPs including their execution's priority at a specific time is the main objective of this study. An original approach based on clustering technique for predicting customers' behaviour coupled with a particle swarm optimisation (PSO) to reach an optimal solution for relocation is presented. In this study, an optimal solution is developed; it provides the various DRPs with the most convenient parameters for the best demand/ generation balance, utility profit maximisation and operational cost minimisation. The method is validated through a simulation applying a time-based with two incentive-based DRPs in the presence of conventional and renewable generation while using Kmeans clustering and PSO on Matlab.

show abstract

Section: Existing Approaches For the Management Of Multiple Drpsmentioning

confidence: 99%

Section: Existing Approaches For the Management Of Multiple Drpsmentioning

confidence: 99%

Two stages K‐means and PSO‐based method for optimal allocation of multiple parallel DRPs application & deployment

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Besides, the granularity in the nature of the household consumption data is another point complicating customer characterization. Customer characterization is investigated in several studies for the reasons like participating in demand side management (DSM) programs [1], [2]. In [4], a demand response (DR) model is proposed for residential consumers to change their consumption pattern with the aim of maximizing their utility.…”

mentioning

confidence: 99%