Energy Disaggregation of Appliances Consumptions Using HAM Approach

Abstract

Non-intrusive load monitoring (NILM) makes it possible for users to track the energy consumption of a household. In this paper, we present a new hybrid energy disaggregation approach named HAM. This event-based load disaggregation algorithm uses an improved multi-layer Hungarian algorithm to match appliances transient features and a supervised adaptive resonance theory mapping neural network (ARTMAP) to cluster steady features. This approach using a modified dual sliding window-based cumulative sum control chart algorithm (DSWC) to detect the transient event first, and we convert the multi-dimensional electrical features of appliances into a bipartite graph matching problem. This way, an improved Hungarian algorithm is proposed to find the perfect matching when appliances are in different states. For classification and identification, the ARTMAP network is used to learn and classify the steady features of appliances. Furthermore, we introduced a grey correlation evaluation and multiple matching strategies to increase the fitness and accuracy of the approach. Experimental results demonstrate that the proposed HAM outperforms the comparative algorithm in both our resident appliances dataset (RAD) and BLUED public dataset. The proposed approach could also facilitate NILM more applicable for common households.

Maximum likelihood least squares‐based iterative methods for output‐error bilinear‐parameter models with colored noises

“…Compared with the overparameterization model identification methods, the parameter separation technique introduced in this article can be applied to identify large-scale systems through the effective reduction of the number of parameters to be identified, thereby greatly reducing the computational cost and simplifying the identification procedure. The proposed methods in this article can be used for modeling and prediction and can be extended to study the parameter estimation problems of different systems with colored noises [47][48][49][50][51][52] and can be applied to other literatures [53][54][55] such as signal modeling and communication systems, engineering application systems, and so on.…”

Three‐stage least squares‐based iterative estimation algorithms for bilinear state‐space systems based on the bilinear state estimator

“…Obviously, it is larger than that of the 3S-LSI algorithm. The proposed iterative algorithm for a class of observability canonical bilinear systems in this paper can combine some mathematical tools [39][40][41][42][43] to study the parameter estimation problems of different stochastic systems with colored noises [44][45][46][47][48][49][50][51] and can be applied to other fields [52][53][54][55][56][57] such as signal processing and communication networked systems [58][59][60][61] and transportation communication systems, [62][63][64][65] and engineering systems and so on.…”

Maximum likelihood‐based adaptive differential evolution identification algorithm for multivariable systems in the state‐space form

“…The proposed algorithms in this article are based on this identification model. Many identification methods are derived based on the identification models of the systems [32][33][34][35] and can be used to estimate the parameters of other linear systems and nonlinear systems [36][37][38][39] and can be applied to other fields [40][41][42][43] such as chemical process control systems.…”