Abstract
This paper addresses the problem of Volt-Var optimization for conservation voltage reduction (CVR) implementation in medium voltage electric distribution systems (EDS) with high penetration levels of renewable energy sources (RES)-based distributed generation (DG). The proposed strategy seeks to coordinate the power dispatch of aggregated electric vehicles (EVs) for EDS voltage control taking into account technical characteristics and the driving patterns of individual EVs. The strategy is for the day-ahead operation scheduling, where decisions are made based on predictions of RES-based DG power production, conventional load consumption and EV driving patterns. Forecast errors are taken into account through a two-stage stochastic programming formulation, where probability density functions are used to describe the uncertainties of predicted parameters. Simulations were carried out on a 33-bus test system and results showed energy savings of up to 3% when EVs participate in voltage control.

Abstract
The competency-based learning approach arose from the Bologna signed declaration. However, a competency definition has never been easy and has been evolving and adapted over time, from indicators and learning goals to learning outcomes, which were formulated in terms of competencies. Meanwhile, the competency concept becomes discussed by pears, in particular, associating knowledge, skills, and human dispositions or attitudes into the competency definition. This information will be an essential update to the previous approaches and certainly contribute to achieving more accurate and reliable competencies information for employers and higher education institutions (HEI). This paper aims to reinforce the relevance of these concepts and suggest how each construct of “knowledge, skills and human dispositions” could be approached to formulate a competency. In addition, due to accelerated digital transformation, an example of a digital competency defined by the DigComp 2.0 framework, with proposed information regarding each of the three constructs, will be presented to consolidate this challenge. As future work, it is intended to analyze the eight different levels, and competency profiles defined by the European Qualification Framework (EQF) and assign a profile to each defined competency. In the end, it is expected altogether to contribute to achieving a competency roadmap definition.

Abstract

Abstract
Many time series exhibit conditional heteroscedasticity such as stock prices or returns, interest rates or exchange rates. Time series used in empirical analysis are often temporal aggregates. We study the effects of using temporally aggregated time series in testing for heteroscedasticity. The distribution of the test statistics is affected by aggregation which causes a severe power loss that worsens with the order of aggregation. Thus, the tests often fail to detect the heteroscedastic nature of the data which is a misleading outcome and can entail wrong decisions. Our conclusions are illustrated by an empirical application.

Abstract
Modern online systems for user modeling and recommendation need to continuously deal with complex data streams generated by users at very fast rates. This can be overwhelming for systems and algorithms designed to train recommendation models in batches, given the continuous and potentially fast change of content, context and user preferences or intents. Therefore, it is important to investigate methods able to transparently and continuously adapt to the inherent dynamics of user interactions, preferably for long periods of time. Online models that continuously learn from such flows of data are gaining attention in the recommender systems community, given their natural ability to deal with data generated in dynamic, complex environments. User modeling and personalization can particularly benefit from algorithms capable of maintaining models incrementally and online. The objective of this workshop is to foster contributions and bring together a growing community of researchers and practitioners interested in online, adaptive approaches to user modeling, recommendation and personalization, and their implications regarding multiple dimensions, such as evaluation, reproducibility, privacy, fairness and transparency.

Abstract
Accurate household profiles (e.g., house type, number of occupants) identification is the key to the successful implementation of behavioral demand response. Currently, supervised learning methods are widely adopted to identify household profiles using smart meter data. Such methods could achieve promising performance in the case of sufficient labeled data but show low accuracy if labeled data is insufficient or even unavailable. However, the acquisition of accurately labeled data (usually obtained by survey) is very difficult, costly, and time-consuming in practice due to various reasons such as privacy concerns. To this end, a semi-supervised learning approach is proposed in this paper to address the above issues. Firstly, 78 preliminary features reflecting the household profiles information are extracted from both time and frequency domain. Secondly, feature selection methods are introduced to select more relevant ones as the input of the identification model from the preliminary features. Thirdly, a transductive support vector machine method is adopted to learn the mapping relation between the input features and the output household profile identification results. Case study on an Irish dataset indicates that the proposed approach outperforms supervised learning methods when only limited labeled data is available. Furthermore, the impacts of different feature selection methods (i.e., Filter, Wrapper and Embedding methods) are also investigated, among which the wrapper method performs best, and the identification accuracy improves with the increase of data resolution.