Low-Frequency Non-Intrusive Load Monitoring of Electric Vehicles in Houses with Solar Generation: Generalisability and Transferability
by Apostolos Vavouris, Benjamin Garside, Lina Stankovic and Vladimir Stankovic
Published: 17 March 2022
Electrification of transportation is gaining traction as a viable alternative to vehicles that use fossil-fuelled internal combustion engines, which are responsible for a major part of carbon dioxide emissions. This global turn towards electrification of transportation is leading to an exponential energy and power demand, especially during late-afternoon and early-evening hours, that can lead to great challenges that electricity grids need to face. Therefore, accurate estimation of Electric Vehicle (EV) charging loads and time of use is of utmost importance for different participants in the electricity markets. In this paper, a scalable methodology for detecting, from smart meter data, household EV charging events and their load consumption with robust evaluation, is proposed. This is achieved via a classifier based on Random Decision Forests (RF) with load reconstruction via novel post-processing and a regression approach based on sequence-to-subsequence Deep Neural Network (DNN) with conditional Generative Adversarial Network (GAN). Emphasis is placed on the generalisability of the approaches over similar houses and cross-domain transferability to different geographical regions and different EV charging profiles, as this is a requirement of any real-case scenario. Lastly, the effectiveness of different performance and generalisation loss metrics is discussed. Both the RF classifier with load reconstruction and the DNN, based on the sequence-to-subsequence model, can accurately estimate the energy consumption of EV charging events in unseen houses at scale solely from household aggregate smart meter measurements at 1–15 min resolutions.
Particle Swarm Optimization in Residential Demand-Side Management: A Review on Scheduling and Control Algorithms for Demand Response Provision
by Christoforos Menos-Aikateriniadis, Ilias Lamprinos and Pavlos S. Georgilakis
Published: 17 March 2022
Power distribution networks at the distribution level are becoming more complex in their behavior and more heavily stressed due to the growth of decentralized energy sources. Demand response (DR) programs can increase the level of flexibility on the demand side by discriminating the consumption patterns of end-users from their typical profiles in response to market signals. The exploitation of artificial intelligence (AI) methods in demand response applications has attracted increasing interest in recent years. Particle swarm optimization (PSO) is a computational intelligence (CI) method that belongs to the field of AI and is widely used for resource scheduling, mainly due to its relatively low complexity and computational requirements and its ability to identify near-optimal solutions in a reasonable timeframe. The aim of this work is to evaluate different PSO methods in the scheduling and control of different residential energy resources, such as smart appliances, electric vehicles (EVs), heating/cooling devices, and energy storage. This review contributes to a more holistic understanding of residential demand-side management when considering various methods, models, and applications. This work also aims to identify future research areas and possible solutions so that PSO can be widely deployed for scheduling and control of distributed energy resources in real-life DR applications.