Abstract
This paper presents three ensemble learning models for short term load forecasting. Machine learning has evolved quickly in recent years, leading to novel and advanced models that are improving the forecasting results in multiple fields. However, in highly dynamic fields such as power and energy systems, dealing with the fast acquisition of large amounts of data from multiple data sources and taking advantage from the correlation between the multiple available variables is a challenging task, for which current models are not prepared. Ensemble learning is bringing promising results in this sense, as, by combining the results and use of multiple learners, is able to find new ways for current learning models to be used and optimized. In this paper three ensemble learning models are developed and the respective results compared: gradient boosted regression trees, random forests and an adaptation of Adaboost. Results for electricity consumption forecasting in hour-ahead are presented using a case-study based on real data from an office building. Results show that the adapted Adaboost model outperforms the reference models for hour-ahead load forecasting.

Abstract
Recent changes in the energy sector are increasing the importance of portfolio optimization for market participation. Although the portfolio optimization problem is most popular in finance and economics, it is only recently being subject of study and application in electricity markets. Risk modeling in this domain is, however, being addressed as in the classic portfolio optimization problem, where investment diversity is the adopted measure to mitigate risk. The increasing unpredictability of market prices as reflection of the renewable generation variability brings a new dimension to risk formulation, as market participation risk should consider the prices variation in each market. This paper thereby proposes a new portfolio optimization model, considering a new approach for risk management. The problem of electricity allocation between different markets is formulated as a classic portfolio optimization problem considering market prices forecast error as part of the risk asset. Dealing with a multi-objective problem leads to a heavy computational burden, and for this reason a particle swarm optimization-based method is applied. A case study based on real data from the Iberian electricity market demonstrates the advantages of the proposed approach to increase market players? profits while minimizing the market participation risk.

Abstract
Electricity markets are complex and dynamic environments with very particular characteristics. Ambitious goals, including those set by the European Union, foster the increased use of distributed generation, essentially based on renewable energy sources. This requires major changes in electricity markets and energy systems, namely through the adoption of the smart grid paradigm. The use of simulation tools and the study of different market mechanisms and the relationships between their stakeholders are essential. One of the main challenges in this area is developing decision support tools to address the problem as a whole. This work contributes to increasing interoperability between heterogeneous systems, namely agent-based, directed to the study of electricity markets, the operation of smart grid, and energy management. To this end, this work proposes the use of ontologies to ease the interaction between entities of different natures and the use of semantic web technologies to develop more intelligent and flexible tools. A multiagent systems society, composed of several heterogeneous multiagent systems, which interact using the proposed ontologies, is presented as a proof-of-concept.

Abstract

Abstract
Agent-based simulation tools have found many applications in the field of Power and Energy Systems, as they can model and analyze the complex synergies of dynamic and continuously evolving systems. While some studies have been done w.r.t. simulation and decision support for electricity markets and smart grids, there is still a generalized limitation referring to the significant lack of interoperability between independently developed systems, hindering the task of addressing all the relevant existing interrelationships. This work presents the Semantic Services Catalog (SSC), developed and implemented for the automatic registry, discovery, composition, and invocation of web and agent-based services. By adding a semantic layer to the description of different types of services, this tool supports the interaction between heterogeneous multiagent systems and web services with distinct capabilities that complement each other. The case study confirms the applicability of the developed work, wherein multiple simulation and decision-support tools work together managing a microgrid of residential and office buildings. Using SSC, besides discovering each other, agents also learn about the ontologies and languages to use to communicate with each other effectively.

Abstract
The increasing penetration of renewable energy sources and the need to adjust to the future demand requires adopting measures to improve energy resources management, especially in buildings. In this context, PV generation forecast has an essential role in the energy management entities by preventing problems related to intermittent weather conditions and allowing participation in incentive programs to reduce energy consumption. This paper proposes an automatic model for the day-ahead PV generation forecast, combining several forecasting algorithms with the expected weather conditions. To this end, this model communicates with a SCADA system, which is responsible for the cyberphysical energy management of an actual building.