Cláudio Monteiro

Abstract
This article introduces BetaMemo models, a set of advanced probabilistic forecasting models aimed at predicting the hourly power output of photovoltaic plants. By employing a semiparametric approach based on beta distributions and deterministic models, BetaMemo offers detailed forecasts, including point forecasts, variance, quantiles, uncertainty measures, and probabilities of power generation falling within specific intervals or exceeding predefined thresholds. BetaMemo models rely on input data derived from weather forecasts generated by a Numerical Weather Prediction model coupled with variables pertaining to solar positioning in the forthcoming hours. Eleven BetaMemo models were created, each using a unique combination of explanatory variables. These variables include data related to the location of the plant and spatiotemporal variables from weather forecasts across a broad area surrounding the plant. The models were validated using a real-life case study of a photovoltaic plant in Portugal, including comparisons of their performance with benchmark forecasting models. The results demonstrate the superior performance of the BetaMemo models, surpassing those of benchmark models in terms of forecasting accuracy. The BetaMemo model that integrates the most extensive set of spatiotemporal explanatory variables provides notably better forecasting results than simpler versions of the model that rely exclusively on the local plant information. This model improves the continuous ranked probability score by 13.89% and the reliability index by 45.66% compared to those obtained from a quantile random forest model using the same explanatory variables. The findings highlight the potential of BetaMemo models to enhance decision-making processes related to photovoltaic power bidding in electricity markets.

Abstract
This article presents original probabilistic forecasting models for day-ahead hourly energy generation forecasts for a photovoltaic (PV) plant, based on a semi-parametric approach using three deterministic forecasts. Input information of these new models consists of data of hourly weather forecasts obtained from a Numerical Weather Prediction model and variables related to the sun position for future instants. The proposed models were satisfactorily applied to the case study of a real-life PV plant in Portugal. Probabilistic benchmark models were also applied to the same case study and their forecasting results compared with the ones of the proposed models. The computer results obtained with these proposed models achieve better point and probabilistic forecasting evaluation indexes values than the ones obtained with the benchmark models. (c) 2023 The Author(s). Published by Elsevier Ltd. This is an open access article under theCCBY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Abstract
Traditional power grids, being highly centralized in terms of generation, economy, and operation, continually employed probabilistic methods to account for load uncertainties. In modern smart grids (SG), rapid proliferation of non-dispatchable generation (physical decentralization) and liberal markets (market decentralization) leads to dismantling of the centralized paradigm, with operation being performed by several decentralized agents. Handling uncertainty in this new paradigm is aggravated due to 1) a vastly increased number of uncertainty sources, and 2) decentralized agents only having access to local data and limited information on other parts of the grid. A major problem identified in modern and future SGs is the need for fully decentralized optimal operation techniques that are computationally efficient, highly accurate, and do not jeopardize data privacy and security of individual agents. Machine learning (ML) techniques, being successors to traditional probabilistic methods are identified as a solution to this problem. In this paper, a conceptual model is constructed for the transition from a fully centralized operation of a SG to a decentralized one, proposing the transition scheme between the two paradigms. A novel ML algorithm for fully decentralized operation is proposed, formulated, implemented, and tested. The proposed algorithm relies solely on local historical data for local agents to accurately predict their optimal control actions without knowledge of the physical system model or access to historical data of other agents. The capability of cloud-based cooperative information exchange was augmented through a new concept of s-index activation codes, being encoded vectors shared between agents to improve their operation without sharing raw information. The algorithm is tested on a modified IEEE 24-bus test system and synthetically generating historical data based on typical load profiles. A week-ahead high-resolution (15 minute) fully decentralized operation case is tested. The algorithm is shown to guarantee less than 0.1% error compared to a centralized solution and to outperform a neural network (NN). The algorithm is exceptionally accurate while being highly computationally efficient and has great potential as a versatile model for fully decentralized operation of SGs.

Abstract
The rapid proliferation of Electric Vehicles (EVs) creates an inherent link between the previously independent transport and power sectors. This is especially relevant in the smart cities paradigm, which focuses on optimizing resource management using modern software tools and communication infrastructures. The optimal management of energy resources is of key importance, and with mobile EVs playing a pivotal role in smart city power flows, the coordination of energy management systems (EMSs) at their parking locations can bear global benefits. In this study the coordination between home energy management systems (HEMSs) and EV parking lot management systems (PLEMS) is proposed, modeled, and simulated, as a new contribution to earlier studies. The EMSs coordinate through partially sharing individual EV schedules and without sharing private information. Missing information is completed through public cloud repositories and services. The HEMS and PLEMS are implemented using mixed-integer linear programming (MILP). The proposed coordination framework is computationally implemented and simulated based on a real-life case study. The results show that the proposed EMS coordination framework is both technically beneficial for power grids and economically beneficial for EV owners.

Abstract
A novel ensemble algorithm based on kernel density estimation (KDE) is proposed to forecast distributed generation (DG) from renewable energy sources (RES). The proposed method relies solely on publicly available historical input variables (e.g., meteorological forecasts) and the corresponding local output (e.g., recorded power generation). Given a new case (with forecasted meteorological variables), the resulting power generation is forecasted. This is performed by calculating a KDE-based similarity index to determine a set of most similar cases from the historical dataset. Then, the outputs of the most similar cases are used to calculate an ensemble prediction. The method is tested using historical weather forecasts and recorded generation of a PV installation in Portugal. Despite only being given averaged data as input, the algorithm is shown to be capable of predicting uncertainties associated with high frequency weather variations, outperforming deterministic predictions based on solar irradiance forecasts. Moreover, the algorithm is shown to outperform a neural network (NN) in most test cases while being exceptionally faster (32 times). Given that the proposed model only relies on public locally-metered data, it is a convenient tool for DG owners/operators to effectively forecast their expected generation without depending on private/proprietary data or divulging their own.