| » Other publications |
The FLEXERGY project team has published the following thesis:
Master’s degree in Electrotechnical Engineering – Load Forecast on a Micro Grid Level through Machine Learning Algorithms
Abstract:
Micro Grids constitute a growing sector of the energetic industry, representing a paradigm shift from the central power generation plans to a more distributed generation. The capacity to work isolated from the main electric grid make the MG resilient system, capable of conducting flexible operations while providing services that make the network more competitive. Additionally, Micro Grids supply clean and efficient low-cost energy, enhance the flexible assets coordination and improve the operation and stability of the local electric grid, through the capability of providing a dynamic response to the energetic resources. For that, it is required an intelligent coordination which balances all the available technologies. With this, rises the need to integrate accurate and robust load and production forecasting models into the MG management platform, thus allowing a more precise coordination of the flexible resource according to the emerging demand needs.
For these reasons, the HALOFMI methodology was developed, which focus on the creation of a precise 24-hour load forecast model. This methodology includes firstly, a hybrid multi-level approach for the creation and selection of features. Then, these inputs are fed to a Neural Network (Multi-Layer Perceptron) with hyper-parameters tuning. In a second phase, two ways of data operation are compared and assessed, which results in the viability of the network operating with a reduced number of training days without compromising the model’s performance. Such process is attained through a sliding window application.
Furthermore, the developed methodology is applied in two case studies, both with 15-minute time steps: the first one is composed by aggregated load profiles of Standard Low Voltage clients, including production and self-consumption units. This case study presents regular and very smooth load profile curves. The second case study concerns a touristic island and represents an irregular load curve with high granularity with abrupt variations.
From the attained results, it is evaluated the impact of integrating a recursive intelligent feature selection routine, followed by an assessment on the sliding window application and at last, a comparison on the errors coming from different estimators for the model, through several well-defined performance metrics.
Master’s degree in Electrotechnical Engineering - Integrating Hybrid Off-grid Systems with Battery Storage: Key Performance Indicators
Abstract:
The high generation costs of off-grid systems and their large greenhouse gas emissions led to the need to integrate renewable energy sources into these electric grids. The generation from renewable energy sources has low operational costs and has few or zero greenhouse gas emissions but imposes some challenges that the system operator must address, such as intermittence, limited predictability and controllability. The integration of energy storage systems into the isolated grid allows increasing the integration of production based on renewable energy sources, enhancing the value of the grid assets and increasing the efficiency and flexibility of the grid. In this work key performance indicators are identified in order to assess the integration of battery energy storage systems in hybrid off-grid systems. Regarding the assessment performed through the key performance indicators, the DIOPHOS (Day-ahead and Intra-day Operational Planning for Hybrid Off-grid Systems) methodology is developed. The methodology is implemented from the perspective of the system operator and, through the optimisation of the operating strategy, the methodology aims to minimise the operational costs and increase the integration of renewable energy sources, ensuring the system security constraints while considering the performance and degradation over time of the battery energy storage system. The developed methodology is applied to a case study in which the main challenge is the lack of flexibility in the operation of the thermal power plants for the integration of high levels of renewable energy. Through the results obtained, it is verified that the integration of the battery energy storage system improves the flexibility of the off-grid system while efficiently integrating the production through renewable energy sources. In addition, the coordination of the energy storage system with the thermal power plant improves the operating point of the thermal units leading to a lower fossil fuel consumption and, thus, lower GHG emissions.
Master’s degree in Electrotechnical Engineering – Energy Storage in Batteries – Dynamic System Modelling and Response
Abstract:
The integration of renewable resources has contributed to increase flexibility requirements in electric power systems. Parallel to this constant increase in the introduction of dispersed production, new solutions have been created to cope with the variability of renewable production, namely energy storage systems. As a result, there are difficulties in coordinating both technologies for such complex and active networks. It is foreseeable that these limitations may be tackled by the adoption of microgrids, with multiple distributed energy resources and equipped with intelligent communication systems, allowing resource flexibility and optimized coordination.
One of the distinguishing characteristics of microgrids is the ability to operate interconnected with the local distribution network, or isolated, meaning, disconnected from the main network. The operation of isolated microgrids is a sensitive mode of operation and requires the implementation of specific control strategies for the correct functioning of the system, namely at the level of protection systems. The present dissertation presents the operation of a microgrid, focusing on the analysis of its behaviour in fault scenarios, namely symmetric and asymmetric short circuits.
The methodology is applied to three different case studies, supported by a computational simulation, concerning the connection of the microgrid to the medium voltage and low voltage distribution networks, as well as its operation in isolated mode. These studies allow the evaluation of the contribution of the various elements of the system to the short-circuit current and the suitability of the system protection systems that may require the adaptability of existing protections.
Master’s degree in Chemical Engineering – Thermal analysis of a containerized battery storage system
Abstract:
The application of Battery Energy Storage Systems in the distribution network is one fundamental step towards a decarbonization of the sector. The need to make an old distribution network with low flexibility suitable for transporting electricity from renewable sources such as photovoltaic and wind power is the main reason to promote the investment in this technology.
Notwithstanding, due to the exothermic behaviour, the batteries, namely lithium, are subjected to an increase of temperature during operation, causing a decline in the storage capacity and, therefore, a cutback in their useful life. This work develops the thermal modelling using the advanced simulation tool ANSYS Fluent. Through this analysis, it is intended to acknowledge and understand the thermal behaviour of the batteries, both individually and organized in a rack, to incorporate, in the future, an optimized refrigeration system which allows to extend the useful life of the batteries in a containerized battery system.
|
|
|
