The supply of energy is a key factor in modern societies. As the old fossil sources for energy are dwindling, conflicts arise between competing nations and regions. Fossil energy sources also contribute to the pollution of the environment and emission of greenhouse gases. With renewable energy sources many of these drawbacks with fossil fuels can be eliminated as the energy will be readily available for all without cost or environmental impact. Combining the renewable energy sources will be very effective, particularly in commercial areas where lake of electricity is high. The cost of combining onshore wind and solar power plant is affordable. Furthermore there is no power failure or load shedding situation at any times. When it is manufactured in a large scale, cost of this integrated natural resources power generation system is affordable. Moreover there is no power failure or load shedding situation at any times. Therefore, it is the most reliable renewable power or electricity resources with less spending and highly effective production. ref [1]. The thesis work would take planning of offshore renewable plant (Lillgrund) with considering the resources of renewable power. The study would take in account combining the Lillgrund wind farm with solar system and take close look into the advantage and disadvantage of combining the renewable resources together and figure out if such station can work in proper way and provide sufficient power production. The study would take in account the effect of each resource on other resource, also calculations would be done. The study site is Lillgrund in south of Sweden. The Lillgrund wind farm is the most important offshore wind power plant installed in Sweden with a total capacity of 110 MW, corresponding to 48 turbines. ref [2].

As wind industry is developing steadily oshore, the wind turbine spacing remainsa key element for maximizing revenues and reducing loading from turbineswake interaction. In the case of relatively close to shore oshore wind farms, orlarge arrays onshore, the turbulence intensity coming from dierent sectors canhave an eect on wake growth and decay. In an attempt to obtain wind featuresat site, some boundary conditions for micro-siting simulation are found, using acommercial RANS ow solver CFD software was used. The approach in this workcould be described more practical than theoretical and could be more useful fordevelopers than pure CFD specialists.By simulating with three dierent roughness length for open sea, with theappropriate and contextual assumptions, for the oshore Lillgrund wind farm,vertical proles and turbulence intensity were extracted from the WindSim softwareat the meteorological mast position and enabled measurement comparison.In a second attempt to compare the eect of the wind and turbulence prolespreviously obtained, a sector of interest is simulated with the actuator disc model.In general, the site conditions over the large-scale domain evaluated by thecommercial software are satisfactory after adjusting the roughness length for theopen sea. The turbulence intensity trend for various in ow angle is capturedby the simulations and computed wind proles are for the most part adequately.A comparison of spring and winter ltered measurements enable discussion uponsome sectors disagreement. As for the small-scale actuator disc model using thedeveloped site conditions, the result is over-estimated by the simulations, especiallyfor the second row downstream.

Wind energy is one of the most promising sources of renewable energy worldwide. Its utilization has substantially increased for the last decades, both onshore and offshore. Offshore wind energy will have a lot to offer within the following decades, thus their foundations need to be prepared. Some of the current wind farms and wind turbines are now reaching their lifespan and, the turbines’ market is developing itself so rapidly that current turbines are getting behind the times with tremendous ease. It is here where the scope of this Master Thesis comes: what shall we do? Should we dismantle wind farms when they reach their lifespan, or should we maybe try to give them a further use? Accommodating for a new a larger wind turbine will need to account for new and higher climate actions and loads, namely winds, waves, ocean currents, the water level variation and the always difficult to predict ice actions. What is aimed in this Master Thesis is to set the basis for a procedure to dimension and define feasible solutions for the offshore wind turbines Gravity-Based Foundations to be expanded, avoiding the necessity of replacing them completely, with the environmental and economic benefits this would have. As this could turn to be an unmanageable problem to be solved, a Case Study where details can be set is performed at the Lillgrund Wind Farm site, in the south-west coast of Sweden, in the Öresund that separates Copenhagen and Malmö. A thorough description of the climatic actions and surrounding aspects is performed, while always dealing with uncertainties. With all that information, an analytical stability analysis is performed to account for three failure modes, namely: sliding, tilting andground failure. Additionally, a numerical FE-model is carried out in ANSYS in the aim of assessing the stresses and deformations that this kind of structure will suffer. Four alternatives are evaluated, and their behaviour is assessed based on the new external design actions. Analytical results show stability difficulties in two of the geometries inspected, while assure it in the other two. The FE-analyses show high concentrations of stresses on the GBS shaft, while model affordable deformations under the load combinations inspected. These results are also compared and contrasted in between them, and sensitivity analyses for the FE-models are performed in order to assure their good behaviour and development, and the trustworthiness ofthe results found. Based on these results, some conclusions are drawn from the developed processes. The main finding is the width and weight dependence of the solution, as well as the shape and dimensions. Future research needs such as scouring effects are finally accounted for necessary inspection to be made as continuation of the work here presented.

In recent years, machine learning applications have gained great attention in the wind power industry. Among these, artificial neural networks have been utilized to predict the fatigue loads of wind turbine components such as rotor blades. However, the limited number of contributions and differences in the used databases give rise to several questions which this study has aimed to answer. Therefore, in this study, 5-min SCADA data from the Lillgrund wind farm has been used to train two feed-forward neural networks to predict the fatigue loads at the blade root in flapwise and edgewise directions in the shape of damage equivalent loads.The contribution of different features to the model’s performance is evaluated. In the absence of met mast measurements, mesoscale NEWA data are utilized to present the free flow condition. Also, the effect of wake condition on the model’s accuracy is examined. Besides, the generalization ability of the model trained on data points from one or multiple turbines on other turbines within the farm is investigated. The results show that the best accuracy was achieved for a model with 34 features, 5 hidden layers with 100 neurons in each hidden layer for the flapwise direction. For the edgewise direction, the best model has 54 features, 6 hidden layers, and 125 neurons in each hidden layer.For a model trained and tested on the same turbine, mean absolute percentage errors (MAPE) of 0.78% and 9.31% are achieved for the flapwise and edgewise directions, respectively. The seen difference is argued to be a result of not having enough data points throughout the range of edgewise moments. The use of NEWA data has been shown to improve the model’s accuracy by 10% for MAPE values, relatively. Training the model under different wake conditions did not improve the model showing that the wake effects are captured through the input features to some extent. Generalization of the model trained on data points from one turbine resulted in poor results in the flapwise direction. It was shown that using data points from multiple turbines can improve the model’s accuracy to predict loading on other turbines.