Search results for: M. Matzner
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 2

Search results for: M. Matzner

2 Short-Term Forecast of Wind Turbine Production with Machine Learning Methods: Direct Approach and Indirect Approach

Authors: Mamadou Dione, Eric Matzner-lober, Philippe Alexandre

Abstract:

The Energy Transition Act defined by the French State has precise implications on Renewable Energies, in particular on its remuneration mechanism. Until then, a purchase obligation contract permitted the sale of wind-generated electricity at a fixed rate. Tomorrow, it will be necessary to sell this electricity on the Market (at variable rates) before obtaining additional compensation intended to reduce the risk. This sale on the market requires to announce in advance (about 48 hours before) the production that will be delivered on the network, so to be able to predict (in the short term) this production. The fundamental problem remains the variability of the Wind accentuated by the geographical situation. The objective of the project is to provide, every day, short-term forecasts (48-hour horizon) of wind production using weather data. The predictions of the GFS model and those of the ECMWF model are used as explanatory variables. The variable to be predicted is the production of a wind farm. We do two approaches: a direct approach that predicts wind generation directly from weather data, and an integrated approach that estimâtes wind from weather data and converts it into wind power by power curves. We used machine learning techniques to predict this production. The models tested are random forests, CART + Bagging, CART + Boosting, SVM (Support Vector Machine). The application is made on a wind farm of 22MW (11 wind turbines) of the Compagnie du Vent (that became Engie Green France). Our results are very conclusive compared to the literature.

Keywords: forecast aggregation, machine learning, spatio-temporal dynamics modeling, wind power forcast

Procedia PDF Downloads 198
1 Neuron Point-of-Care Stem Cell Therapy: Intrathecal Transplant of Autologous Bone Marrow-Derived Stem Cells in Patients with Cerebral Palsy

Authors: F. Ruiz-Navarro, M. Matzner, G. Kobinia

Abstract:

Background: Cerebral palsy (CP) encompasses the largest group of childhood movement disorders, the patterns and severity varies widely. Today, the management focuses only on a rehabilitation therapy that tries to secure the functions remained and prevents complications. However the treatments are not aimed to cure the disease. Stem cells (SCs) transplant via intrathecal is a new approach to the disease. Method: Our aim was to performed a pilot study under the condition of unproven treatment on clinical practice to assessed the safety and efficacy of Neuron Point-of-care Stem cell Therapy (N-POCST), an ambulatory procedure of autologous bone marrow derived SCs (BM-SCs) harvested from the posterior superior iliac crest undergo an on-site cell separation for intrathecal infusion via lumbar puncture. Results: 82 patients were treated in a period of 28 months, with a follow-up after 6 months. They had a mean age of 6,2 years old and male predominance (65,9%). Our preliminary results show that: A. No patient had any major side effects, B. Only 20% presented mild headache due to LP, C. 53% of the patients had an improvement in spasticity, D. 61% improved the coordination abilities, 23% improved the motor function, 15% improved the speech, 23% reduced the number of convulsive events with the same doses or less doses of anti-convulsive medication and 94% of the patients report a subjective general improvement. Conclusions: These results support previous worldwide publications that described the safety and effectiveness of autologous BM-SCs transplant for patients wit CP.

Keywords: autologous transplant, cerebral palsy, point of care, childhood movement disorders

Procedia PDF Downloads 401