Updated thesis

Reports/Thesis/verslag.tex

@@ -29,7 +29,26 @@
 \usepackage{subcaption}
 \usepackage{booktabs}
 
+% Electricity market
+% Generative Modeling
+% -> Quantile Regression
+% -> Autoregressive vs non autoregressive
+% -> Modellen (linear, non linear, gru)
+% -> Diffusion (1 grote)
+% Policies (globaal, hoe winst maken) Wij heel simpele, tonen dat NRV generaties nut hebben. Reinforcement learning voor complexere 
+% -> Baseline Policies
+% -> Policies based on generations (NRV is nu full day samples)
+% Waarom nuttig om toekomst te modellen
+% Results & discussion
+% -> Per model resultaten
+% -> Comparison between models
 
+% Conclusion
+
+% plot mean and std for averaged NRV over all days
+% Autoregressive models krijgen enkels voorspelde waardes voor dat kwartier, waarom niet van kwartieren erna ook? Uitleg: voor laatste kwartier van de dag, voorspelling van de dag erna nodig. Anders extra padding. 
+
+% Non autoregressive vs autoregressive. Autoregressive weet niet dat hij T+1 ... T+96 moet voorspellen. Denkt dat hij enkel T+1 voorspelt. Te overconfident in voorspellingen voor input met error.
 
 \newcolumntype{C}{>{\centering\arraybackslash}X}
 
@@ -158,6 +177,7 @@
 
 \include{sections/literature_study}
 
+% In introduction
 \section{TODO: Better title for this section}
 This thesis can be divided into two main parts. The first part focuses on modeling the Net Regulation Volume (NRV) of the Belgian electricity market for the next day. This modeling is conditioned on multiple inputs that can be obtained from Elia (TODO: add citation to the open data of Elia). The second part of the thesis focuses on optimizing a simple policy using the NRV generations for the next day. The policy tries to maximize profit by charging and discharging a battery and thereby buying and selling electricity on the market. Multiple models are trained and tested to model the NRV and compared to each other based on their profit optimization.