Photovoltaic (PV) power1 as a source of renewable energy is inherently uncertain due to atmospheric and environmental variables. This uncertainty has, however, not disqualified PV power from attaining commercial success as is evident from the most recent REN21 Global Status Report. The report shows the extent of the contribution made by utility-scale PV-power systems to electrical grids around the world and highlights that “installed power capacity grew more than 200 gigawatts (GW) (mostly solar photovoltaics, PV” in 2019. The exact modelling and forecasting of the power output of PV systems are therefore critical to effectively manage their integration in smart grids, delivery, and storage. In recent years, PV power forecasting has further advanced to become an extremely active research field. 1. The main research objectives 2. Methodology 3. Conclusion Furthermore, as PV system power supply is characteristically intermittent, PV forecasting is essential for decision-makers overseeing electrical grid stability. However, as commercial PV systems increase in physical size, so does the non-uniform exposure for different PV-module segments within the PV system. Since almost all published PV forecasting models are based on a conventional macro-level forecasting approach, there is reason to question the ability of these solutions to capture low-level power dynamics.
Reinforcement Learning in the Minecraft Gaming Environment 1. Introduction Researchers are keen to solve the challenge of a robot successfully interacting with an external environment. In this regard, the progress made in reinforcement learning (RL), such as Atari 2600 from Google DeepMind, Alpha Go winning the current world champion in the board game Go, and OpenAI winning a 5v5 match against the top players in the world in Dota 2, RL has become a powerful tool to achieve superhuman results in games. RL agents appear to be able to master any game, but what about a game such as Minecraft. The long-term objective of this research is to use RL to teach an agent to survive a day-night cycle in the Minecraft gaming environment. To achieve this, the research tests a new method, referred to as dojo learning based on curriculum learning, against current methods to progress one step closer to the mentioned objective. Although Minecraft is used as a testing platform, the method investigated in this thesis could be generalised and adapted to work in any appropriate gaming environment.
