One of the key techniques towards energy efficiency and conservation is Non-Intrusive Load Monitoring (NILM) which lies in the domain of energy monitoring. Event detection is a core component of event-based NILM systems. This paper proposes two new low-complexity and computationally fast algorithms that detect the variations of load data and return the time occurrences of the corresponding events. The proposed algorithms are based on the phenomenon of a sliding window that tracks the statistical features of the acquired aggregated load data. The performance of the proposed algorithms is evaluated using real-world data and a comparative analysis has been carried out with one of the recently proposed event detection algorithms. Based on the simulations and sensitivity analysis it is shown that the proposed algorithm can provide the results of up to 93% and 88% in terms of recall and precision respectively.

Abstract-The sizing of a stand-alone wind-photovoltaic-battery hybrid renewable energy system (HRES) is greatly influenced by socio-demographic factors however, few studies have examined how sociodemographic factors, as borne out by different electrical usage patterns, influence the size of HRESs. This paper investigates how these factors influence the optimal sizing of a stand-alone HRES using a hybrid optimization method to match the available renewable energy with the demand. In this regard, different energy usage patterns resulting from users socio-demographic profile have been investigated and used for the optimal sizing of a HRES. The results show that the electricity usage profile of a site has a significant impact on the sizing and design of the system. Further, the results illustrate that one can design a system that meets the demand profiles resulting from socio-demographic factors with a minimum unmet load; however, by optimizing systems to the users socio-demographic profile, significant cost savings can be made.

No abstract

No abstract

The recent advancement in computational capabilities and deployment of smart meters have caused non-intrusive load monitoring to revive itself as one of the promising techniques of energy monitoring. Toward effective energy monitoring, this paper presents a non-invasive load inference approach assisted by feature selection and ensemble machine learning techniques. For evaluation and validation purposes of the proposed approach, one of the major residential load elements having solid potential toward energy efficiency applications, i.e., water heating, is considered. Moreover, to realize the real-life deployment, digital simulations are carried out on low-sampling real-world load measurements: New Zealand GREEN Grid Database. For said purposes, MATLAB and Python (Scikit-Learn) are used as simulation tools. The employed learning models, i.e., standalone and ensemble, are trained on a single household’s load data and later tested rigorously on a set of diverse households’ load data, to validate the generalization capability of the employed models. This paper presents a comprehensive performance evaluation of the presented approach in the context of event detection, feature selection, and learning models. Based on the presented study and corresponding analysis of the results, it is concluded that the proposed approach generalizes well to the unseen testing data and yields promising results in terms of non-invasive load inference.