The digitalization of the energy industry has made tremendous energy data available. This data is utilized across the entire energy value chain to provide value for customers and energy providers. One area that has gained recent attention in the energy industry is the electricity load forecasting for better scheduling and bidding on the electricity market. However, the electricity data that is used for forecasting is prone to have anomalies, which can affect the accuracy of forecasts. In this thesis we propose two anomaly detection methods to tackle the issue of anomalies in electricity demand data. We propose Long short-term memory (LSTM) and Feed-forward neural network (FFNN) based methods, and compare their anomaly detection performance on two real-world electricity demand datasets. Our results indicate that the LSTM model tends to produce a more robust behavior than the FFNN model on the dataset with regular daily and weekly patterns. However, there was no significant difference between the performance of the two models when the data was noisy and showed no regular patterns. While our results suggest that the LSTM model is effective when a regular pattern in data is present, the results were not found to be statistically significant to claim superiority of LSTM over FFNN. / Digitaliseringen inom energibranschen har tillgängliggjort enorma mängder energidata. Dessa data används över hela värdekedjan för energisystem i syfte att skapa värde för kunder och energileverantörer. Ett område som nyligen uppmärksammats inom energibranschen är att skapa prognoser för elbelastning för bättre schemaläggning och budgivning på elmarknaden. Data som används för sådana prognoser är dock benägna att ha avvikelser, vilket kan påverka prognosernas noggrannhet. I det här examensarbetet föreslår vi två metoder för detektering av avvikelser för att ta itu med frågan om avvikelser i data för elektricitetsbehov. Vi föreslår metoder baserade på Long short-term memory (LSTM) och Feedforward neural network (FFNN) och jämför dess prestanda att upptäcka avvikelser på två verkliga databanker över elbehovsdata. Våra resultat indikerar att LSTM-modellen tenderar att producera ett mer robust beteende än FFNN-modellen på data med upprepande dagliga samt veckovisa mönster. Det fanns dock ingen signifikant skillnad mellan prestanda för de två modellerna när data inte uppvisade regelbunda mönster. Även om våra resultat antyder att LSTM-modellen är effektiv när ett regelbundet datamönster finns närvarande, var resultaten inte statistiskt signifikanta för att påstå överlägsenhet av LSTM jämfört med FFNN.

In this thesis two main studies are conducted to compare the predictive capabilities of feed-forward neural networks (FFNN) and long short-term memory networks (LSTM) in electricity load forecasting. The first study compares univariate networks using past electricity load, as well as multivariate networks using past electricity load and air temperature, in day-ahead load forecasting using varying lookback periods and sparsity of past observations. The second study compares FFNNs and LSTMs of different complexities (i.e. network sizes) when restrictions imposed by limitations of the real world are taken into consideration. No significant differences are found between the predictive performances of the two neural network approaches. However, adding air temperature as extra input to the LSTM is found to significantly decrease its performance. Furthermore, the predictive performance of the FFNN is found to significantly decrease as the network complexity grows, while the predictive performance of the LSTM is found to increase as the network complexity grows. All the findings considered, we do not find that there is enough evidence in favour of the LSTM in electricity load forecasting. / I denna uppsats beskrivs två studier som jämför feed-forward neurala nätverk (FFNN) och long short-term memory neurala nätverk (LSTM) i prognostisering av elkonsumtion. I den första studien undersöks univariata modeller som använder tidigare elkonsumtion, och flervariata modeller som använder tidigare elkonsumtion och temperaturmätningar, för att göra prognoser av elkonsumtion för nästa dag. Hur långt bak i tiden tidigare information hämtas ifrån samt upplösningen av tidigare information varieras. I den andra studien undersöks FFNN- och LSTM-modeller med praktiska begränsningar såsom tillgänglighet av data i åtanke. Även storleken av nätverken varieras. I studierna finnes ingen skillnad mellan FFNN- och LSTM-modellernas förmåga att prognostisera elkonsumtion. Däremot minskar FFNN-modellens förmåga att prognostisera elkonsumtion då storleken av modellen ökar. Å andra sidan ökar LSTM-modellens förmåga då storkelen ökar. Utifrån dessa resultat anser vi inte att det finns tillräckligt med bevis till förmån för LSTM-modeller i prognostisering av elkonsumtion.

Maintaining the electricity balance between supply and demand is a challenge for electricity suppliers. If there is an under or overproduction, it entails financial costs and affects consumers and the climate. To better understand how to maintain the balance, can the suppliers use short-term forecasts of electricity load. Hence it is of paramount importance that the forecasts are reliable and of high accuracy. Studies show that time series modeling moves towards more data-driven methods, such as Artificial Neural Networks due to their ability to extract complex relationships and flexibility. This study evaluates the performance of a multivariate Deep Autoregressive Neural Network (DeepAR) in ashort-term forecasting scenario of electricity load, with forecasted weather parameters as exogenous covariates. This thesis’s goal is twofold: to test the performance in terms of evaluation metrics of day-ahead forecasts in exogenous covariates’ presence and examine the robustness when exposing DeepAR to deviations in input data. We perform feature selection on given covariates to identify and extract relevant parameters to facilitate the training process and implement a feature importance algorithm to examine which parameters the model considers essential. To test the robustness, we simulate two cases. In the first case, we introduce Quarantine periods, which mask data prior to the forecast range, and the second case introduces an artificial outlier. An exploratory analysis displays significant annual characteristic differences between seasons, therefore do we use two test sets, one in winter and one in summer. The result shows that DeepAR is robust against potential deviations in input data and that DeepAR surpassed both benchmark models in all of the tested scenarios. In the ideal test scenario where weather parametershad the most significant impact (winter), do DeepAR achieve a Normalized Deviation(ND) of 2.5%, compared to the second-best model, with an ND of 4.4%

L'électricité ne se stockant pas aisément, EDF a besoin d'outils de prévision de consommation et de production efficaces. Le développement de nouvelles méthodes automatiques de sélection et d'estimation de modèles de prévision est nécessaire. En effet, grâce au développement de nouvelles technologies, EDF peut étudier les mailles locales du réseau électrique, ce qui amène à un nombre important de séries chronologiques à étudier. De plus, avec les changements d'habitude de consommation et la crise économique, la consommation électrique en France évolue. Pour cette prévision, nous adoptons ici une méthode semi-paramétrique à base de modèles additifs. L'objectif de ce travail est de présenter des procédures automatiques de sélection et d'estimation de composantes d'un modèle additif avec des estimateurs en plusieurs étapes. Nous utilisons du Group LASSO, qui est, sous certaines conditions, consistant en sélection, et des P-Splines, qui sont consistantes en estimation. Nos résultats théoriques de consistance en sélection et en estimation sont obtenus sans nécessiter l'hypothèse classique que les normes des composantes non nulles du modèle additif soient bornées par une constante non nulle. En effet, nous autorisons cette norme à pouvoir converger vers 0 à une certaine vitesse. Les procédures sont illustrées sur des applications pratiques de prévision de consommation électrique nationale et locale.Mots-clés: Group LASSO, Estimateurs en plusieurs étapes, Modèle Additif, Prévision de charge électrique, P-Splines, Sélection de variables / French electricity load forecasting encounters major changes since the past decade. These changes are, among others things, due to the opening of electricity market (and economical crisis), which asks development of new automatic time adaptive prediction methods. The advent of innovating technologies also needs the development of some automatic methods, because we have to study thousands or tens of thousands time series. We adopt for time prediction a semi-parametric approach based on additive models. We present an automatic procedure for covariate selection in a additive model. We combine Group LASSO, which is selection consistent, with P-Splines, which are estimation consistent. Our estimation and model selection results are valid without assuming that the norm of each of the true non-zero components is bounded away from zero and need only that the norms of non-zero components converge to zero at a certain rate. Real applications on local and agregate load forecasting are provided.Keywords: Additive Model, Group LASSO, Load Forecasting, Multi-stage estimator, P-Splines, Variables selection