In a synchronous electric grid the consumption of electricity must always be met by an equal amount of generation. In the Nordic power system, this balance is first and foremost kept by the balance responsible parties in the electric markets. However, from one hour before delivery, it is the Swedish Transmission System Operator (TSO), Svenska kraftnät (Svk) together with its Nordic counterparts, who take over the responsibility. They achieve this by for example purchasing ancillary services such as Frequency Restoration Reserves (FRR) to compensate for frequency deviations. A way of explaining the frequency deviations that would have occurred without the TSO taking actions, is that they are caused by imbalances. Imbalances are the difference between measured and traded energy volumes in the bidding areas, where volumes equals HVDC-connections, consumption and different kinds of power production. In the future, these imbalances will be one of the dimensioning factors of FRR. The purpose of this thesis is to study the imbalances caused by wind power production and to create a model that can simulate future wind power imbalances. The long term goal is that the model will be part of a larger project whose purpose is predicting the future need of FRR. The model has been designed to use future market data, such as traded volumes and spot prices to make the predictions. The model has been developed using statistical methods in MATLAB together with another master student, who has studied consumption imbalances. Due to lack of deterministic correlations, the final model created was an Autoregressive-Moving-Average (ARMA) model together with a linear correlation between quarterly average traded volumes and quarterly standard deviations of the wind power imbalances. The model can recreate the historical autoregressive behaviour and the historical distribution of the imbalances to a satisfactory degree, as well as scaling up the imbalances with a correlation of 0.92. Applying future market data on the model, imbalances are expected to increase by 50\% to 180\% from today to the year 2023, depending on bidding area. However, there are uncertainties due to yearly variations in the wind power production. One conclusion is therefore that a windy year probably also will increase the required need of FRR. Before applying the model to evaluate the future need for FRR, the reliability used in the traded data for developing the model should be checked. A final validation of the total simulated imbalances, not just wind power imbalances, against historic data should also be performed. To develop the model further, a suggestion is to study possible spatial correlations of the imbalances between bidding areas.

Hydropower plants create blockages in fish migration routes. Fish ladders can serve as alternative routes but are complex to install and follow up to help adapt and develop them further. In this study, computer vision tools are considered in this regard. More specifically, object detection is applied to images collected in a hydropower plant fish ladder to localise and classify wild, farmed and unknown fish labelled according to the presence, absence or uncertainty of an adipose fin. Fish migration patterns are not deterministic, making it a challenge to collect representative and balanced data to train a model that is resilient to changing conditions. In this study, two data imbalances are addressed by modifying a YOLOv3 baseline model: foreground-foreground class imbalance is targeted using hard and soft resampling and positional imbalance using translation augmentation. YOLOv3 is a convolutional neural network predicting bounding box coordinates, class probabilities and confidence scores simultaneously. It divides images into grids and makes predictions based on grid cell locations and anchor box offsets. Performance is estimated across 10 random data splits and different bounding box overlap thresholds, using (mean) average precision as well as recall, precision and F1 score estimated at optimal validation set confidence thresholds. The Wilcoxon signed-ranks test is used for determining statistical significance. In experiments, the best performance was observed on wild and farmed fish, with F1 scores reaching 94.8 and 89.0 percent respectively. The inconsistent appearance of unknown fish appears harder to generalise to, with a corresponding F1 score of 65.7 percent. Soft sampling but especially translation augmentation contributed to enhanced performance and reduced variance, implying that the baseline model is particularly sensitive to positional imbalance. Spatial dependencies introduced by YOLOv3’s grid cell strategy likely produce local bias or overfitting. An experimental evaluation highlight the importance of not relying on a single data split when evaluating performance on a moderately large or custom dataset. A key challenge observed in experiments is the choice of a suitable confidence threshold, influencing the dynamics of the results. / Vattenkraftverk blockerar fiskars vandringsvägar. Fisktrappor kan skapa alternativa vägar men är komplexa att installera och följa upp för vidare anpassning och utveckling. I denna studie betraktas datorseende i detta avseende. Mer specifikt appliceras objektdetektering på bilder samlade i en fisktrappa i anslutning till ett vattenkraftverk, med målet att lokalisera och klassificera vilda, odlade och okända fiskar baserat på förekomsten, avsaknaden eller osäkerheten av en fett-fena. Fiskars migrationsmönster är inte deterministiska vilket gör det svårt att samla representativ och balanserad data för att trana en modell som kan hantera förändrade förutsättningar. I denna studie addresseras två obalanser i datan genom modifikation av en YOLOv3 baslinjemodell: klass-obalans genom hård och mjuk återanvändning av data och positionell obalans genom translation av bilder innan träning. YOLOv3 är ett convolutional neural network som simultant förutsäger avgränsnings-lådor, klass-sannolikheter och prediktions-säkerhet. Bilder delas upp i rutnätceller och prediktioner görs baserat på cellers position samt modifikation av fördefinierade avgränsningslådor. Resultat beräknas på 10 slumpmässiga uppdelningar av datan och för olika tröskelvärden för avgränsningslådors överlappning. På detta beräknas (mean) average precision, liksom recall, precision och F1 score med tröskelvärden för prediktions-säkerhet beräknat på valideringsdata. Wilcoxon signed-ranks test används för att avgöra statistisk signifikans. Bäst resultat observeras på vilda och odlade fiskar, med F1 scores som når 94.8 respektive 89.0 procent. Okända fiskars inkonsekventa utseenden verkar svårare att generalisera till, med en motsvarande F1 score på 65.7 procent. Mjuk återanvändning av data men speciellt translation bidrar till förbättrad prestanda och minskad varians, vilket pekar på att baslinjemodellen är särskilt känslig för positionell obalans. Spatiala beroenden skapade av YOLOv3s rutnäts-strategi producerar troligen lokal partiskhet eller överträning. I en experimentell utvärdering understryks vikten av multipel uppdelning av datan vid evaluering på ett måttligt stort eller egenskapat dataset. Att välja tröskelvärdet för prediktions-säkerhet anses utmanande och påverkar resultatens dynamik.