Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Ce mémoire de fin d'étude expose une méthodologie d'analyse de base de donnée visant à extraire via des données receuillie par un fournisseur d'énergie (Total) des informations jugé pertinente quand au calcul du potentiel HVAC dans le secteur tertiaire.

Ingénierie, informatique & technologie > Ingénierie civile

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

This master thesis subject addresses the question of what is the best forecasting method to implement in the context of the prediction of renewable energy production, to protect assets from oversupply. The growing scientific field of Deep Learning has a great potential to be exploited to achieve this goal. This works is composed of different parts. First part introduces the goal that we want to be pursued. The second part interrogates what what are the tools needed to accomplish the goal and defines the context on which the comparison will be performed. The third part is a comparison of the models considering a default forecasting goal . The fourth part is a discussion on what might be the most relevant metric considering the main goal. From this we define two metrics, Coverage and MASE and we finally perform in fifth part a comparison using metrics and loss that have been introduced .
The answer to the question of what is the better forecasting model in the defined context between all the tested models, the model that provides the better results, in terms of Coverage and MASE, is definitely the model MQCNN, which outperforms for the two metrics considered all the other presented models. MQCNN model is followed by MQRNN, DeepAr and SimpleFeedForward.

artificial intelligence --- machine learning --- forecasting --- time series forecasting --- probabilistic forecasting --- deep learning --- forecasting models --- renewable energy --- renewable energy production --- model comparison --- Ingénierie, informatique & technologie > Sciences informatiques

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

It has been heard, seen, and shown that EV uptake is rapidly increasing. However, the main exponential growth is still tocome during the 2025-2035 period. For the expected adoption to happen, early adopters first have to be convinced. Asthey are open to innovation and have above average financial liquidity, the EV uptake will normally be reached. But forthe early majority to adopt EV, public charging will be necessary as the main proportion of these customers will be livingin cities and not own a parking spot.The main factor making early adopters and the majority of would-be consumers hesitate is the range anxiety. Rangeanxiety will be solved by developing a reliable charging infrastructure. However, 4 scenarios appear, the infrastructurecould be public or semi-public and could use either slow or fast charging technology. Due to different possibilities andrapid changes on the market, the need to identify and understand the key factors influencing the attractiveness for a privatecompany to invest in a (semi-)public infrastructure is clear.In this paper, a comprehensive method will be developed to analyze different business opportunities in the objective todetermine and highlights the current best investments. The method includes an economical, technical, legal and practicalpart to analyze the entirety of the project. The main focus is in the economical part where a method to calculate theexpected volume of charge and the sensitivity of the cases on the parameters of interests are developed. After havinganalyzed current, fictive and disruptive business opportunities, the main conclusions can be drawn. The volume of energysold and the spread between the sourcing and selling prices are the most important parameters, however, their importancevary with the technology of the charger. Volume is more important for fast charging whereas slow charging depends moreon the selling price, which reduces the risk for the company investing. The potential need of a transformer is also animportant parameter to consider, as it is particularly costly compared to the charger itself. Public fast charging is stillnot viable and semi-public fast charging is interesting and the investment decision will depend on the site location andthe need for a transformer. Public slow charging is the best investment choice, bringing the higher rate of return in theshortest period of time thanks to lower investments. Moreover, investing now would mean securing good locations andvaluable experience for the future. Wireless charging is very promising; Engie could easily compete on the market thanksto its client proximity and capabilities if invested quickly enough, via EVBox or acquisitions in wireless charging. Thereal game changer on the market will be Dynamic Wireless Charging, but technology still needs important cost reductionbefore it becomes widespread.

EV, Public charging --- Ingénierie, informatique & technologie > Ingénierie électrique & électronique