Search

Highlights • We describe new optimisation approaches for improving the operational design of tidal power plants. • We demonstrate the value of flexible operation in maximising income from the Day Ahead energy market. • An income-based optimisation for a tidal lagoon case led to a 23% improvement in energy market income. • Tidal range power plants can have a short-term storage capability for generation during high-demand periods. Abstract Tidal range renewable power plants have the capacity to deliver predictable energy to the electricity grid, subject to the known variability of the tides. Tidal power plants inherently feature advantages that characterise hydro-power more generally, including a lifetime exceeding alternative renewable energy technologies and relatively low Operation & Maintenance costs. Nevertheless, the technology is typically inhibited by the significant upfront investment associated with capital costs. A key aspect that makes the technology stand out relative to other renewable options is the partial flexibility it possesses over the timing of power generation. In this study we provide details on a design methodology targeted at the optimisation of the temporal operation of a tidal range energy structure, specifically the Swansea Bay tidal lagoon that has been proposed within the Bristol Channel, UK. Apart from concentrating on the classical incentive of maximising energy, we formulate an objective functional in a manner that promotes the maximisation of income for the scheme from the Day-Ahead energy market. Simulation results demonstrate that there are opportunities to exploit the predictability of the tides and flexibility over the precise timing of power generation to incur a noticeable reduction in the subsidy costs that are often negotiated with regulators and governments. Additionally, we suggest that this approach should enable tidal range energy to play a more active role in ensuring security of supply in the UK. This is accentuated by the income-based optimisation controls that deliver on average more power over periods when demand is higher. For the Swansea Bay tidal lagoon case study a 23% increase is observed in the income obtained following the optimisation of its operation compared to a non-adaptive operation. Similarly, a 10% increase relative to an energy-maximisation approach over a year's operation suggests that simply maximising energy generation in a setting where power prices vary may not be an optimal strategy. [ABSTRACT FROM AUTHOR]

Wind turbine wake modelling is of crucial importance to accurate resource assessment, to layout optimisation, and to the operational control of wind farms. This work proposes a surrogate model for the representation of wind turbine wakes based on a state-of-the-art graph representation learning method termed a graph neural network. The proposed end-to-end deep learning model operates directly on unstructured meshes and has been validated against high-fidelity data, demonstrating its ability to rapidly make accurate 3D flow field predictions for various inlet conditions and turbine yaw angles. The specific graph neural network model employed here is shown to generalise well to unseen data and is less sensitive to over-smoothing compared to common graph neural networks. A case study based upon a real world wind farm further demonstrates the capability of the proposed approach to predict farm scale power generation. Moreover, the proposed graph neural network framework is flexible and highly generic and as formulated here can be applied to any steady state computational fluid dynamics simulations on unstructured meshes. • A novel wind turbine wake model is developed based on graph representation learning. • The developed model can generate 3D wake field predictions rapidly and accurately. • The graph neural network employed is directly compatible with unstructured meshes. • The proposed model is validated on a real-scale wind farm. [ABSTRACT FROM AUTHOR]

This work proposes a novel data-driven model capable of providing accurate predictions for the power generation of all wind turbines in wind farms of arbitrary layout, yaw angle configurations and wind conditions. The proposed model functions by encoding a wind farm into a fully connected graph and processing the graph representation through a graph transformer. The resultant graph transformer surrogate demonstrates robust generalisation capabilities and effectively uncovers latent structural patterns embedded within the graph representation of wind farms. The versatility of the proposed approach extends to the optimisation of yaw angle configurations through the application of genetic algorithms. This evolutionary optimisation strategy facilitated by the graph transformer surrogate achieves prediction accuracy levels comparable to industrially standard wind farm simulation tools, with a relative accuracy of more than 99% in identifying optimal yaw angle configurations of previously unseen wind farm layouts. An additional advantage lies in the significant reduction in computational costs, positioning the proposed methodology as a compelling tool for efficient and accurate wind farm optimisation. • A novel wind farm scale model is developed based on graph transformers. • Graph transformers can identify wake interactions within wind farms and accurately predict wind farm power. • The developed model generalises to diverse wind farm layouts and yaw angle configurations. • The proposed model achieves more than 99% accuracy when used as a surrogate for PyWake in yaw angle optimisation. [ABSTRACT FROM AUTHOR]

Tidal range power plants represent an attractive approach for the large-scale generation of electricity from the marine environment. Even though the tides and by extension the available energy resource are predictable, they are also variable in time. This variability poses a challenge regarding the optimal transient control of power plants. We consider simulation methods which include the main modes of operation of tidal power plants, along with algorithms to regulate the timing of these. This paper proposes a framework where simplified power plant operation models are coupled with gradient-based optimisation techniques to determine the optimal control strategy over multiple tidal cycles. The optimisation results inform coastal ocean simulations that include tidal power plants to gauge whether the benefits of an adaptive operation are preserved once their hydrodynamic impacts are also taken into consideration. The combined operation of two prospective tidal lagoon projects within the Bristol Channel and the Severn Estuary is used as an example to demonstrate the potential benefits of an energy maximisation optimisation approach. For the case studies considered, the inclusion of pumping and an adaptive operation is shown to deliver an overall increase in energy output of 20–40% compared to a conventional two-way uniform operation. The findings also demonstrate that smaller schemes stand to gain more from operational optimisation compared to designs of a larger scale. [ABSTRACT FROM AUTHOR]