An adaptive-neuro fuzzy inference system based-hybrid technique for performing load disaggregation for residential customers

Abstract

Effective and efficient use of energy is key to sustainable industrial and economic growth in modern times. Demand-side management (DSM) is a relatively new concept for ensuring efficient energy use at the consumer level. It involves the active participation of consumers in load management through different incentives. To enable the consumers for efficient energy management, it is important to provide them information about the energy consumption patterns of their appliances. Appliance load monitoring (ALM) is a feedback system used for providing feedback to customers about their power consumption of individual appliances. For accessing appliance power consumption, the determination of the operating status of various appliances through feedback systems is necessary. Two major approaches used for ALM are intrusive load monitoring (ILM) and non-intrusive load monitoring (NILM). In this paper, a hybrid adaptive-neuro fuzzy inference system (ANFIS) is used as an application for NILM. ANFIS model being sophisticated was difficult to work with, but ANFIS model helps to achieve better results than other competent approaches. An ANFIS system is developed for extracting appliance features and then a fine tree classifier is used for classifying appliances having more than 1 kW power rating based on the extracted feature. Several case studies have been performed using ANFIS on a publicly available United Kingdom Domestic Appliance Level Electricity (UK-Dale dataset). The simulation results obtained from the ANFIS for NILM are compared with relevant literature to show the performance of the proposed technique. The results prove that the novel application of ANFIS gives better performance for solving the NILM problem as compared to the other existing techniques.

Adaptive threshold event detection method based on standard deviation

“…Grover et al (2022) [12] used a NILM technique based on Mh-Net CNN to achieve real-time energy consumption and ToU identification of individual devices connected in a building microgrid. Abbas et al (2022) [13] applied a hybrid adaptive neuro-fuzzy inference system to the NILM problem and achieved better results. In addition, non-eventbased methods include optimization-based methods.…”

A Scoping Review of Energy Load Disaggregation

“…The second most popular approaches are HMM-based [77,78] and GSP-based models [36,43]. Less commonly used methods include filtering techniques, such as particle filtering in article [79], and decision trees [47].…”

“…Residential buildings. The most commonly used dataset for residential household research is the REDD dataset, featured in 29 articles, e.g., [21,[38][39][40][41][42][43][44][45], followed by the UK-DALE dataset, used in 12 articles, e.g., [39,[46][47][48]. The least used datasets, such as LIFTED, appeared in only one article [49].…”

Regularized NCA based Prominent Feature Selection for Load Identification Using Boosted Tree Classifier

“…Since during pre-processing stage, each event under observation is divided into eights 𝑜𝑤s, therefore eight values for each of the four parameters defined in ( 9)-( 12) can be computed. Four values of pre-event and four values of post-event are stored in a 4x8 matrix P∈ ℜ which is expressed in (13).…”

“…Machine learning (ML) and deep learning (DL) techniques have been widely used for load identification [12,13]. ML techniques classify the switching events of target appliances by using the significant features.…”