[vc_row row_type=”3″ blox_image=”21772″ align_center=”aligncenter” page_title=”page-title-x” blox_dark=”true” parallax_speed=”8″][vc_column]

---

---

[vc_column_text]

Predicting the
power consumption

[/vc_column_text]

---

---

[/vc_column][/vc_row][vc_row][vc_column width=”1/4″]

---

---

[/vc_column][vc_column width=”1/2″]

---

[vc_column_text]Germany’s one of the largest power supply company with its own infrastructure and electrical power distribution network.[/vc_column_text]

---

[/vc_column][vc_column width=”1/4″][/vc_column][/vc_row][vc_row][vc_column width=”1/3″][vc_single_image image=”21716″ img_size=”550×350″][/vc_column][vc_column width=”1/3″][vc_single_image image=”21331″ img_size=”550×350″][/vc_column][vc_column width=”1/3″][vc_single_image image=”21323″ img_size=”550×350″][/vc_column][/vc_row][vc_row][vc_column]

---

[vc_column_text]

About this project

[/vc_column_text][vc_row_inner][vc_column_inner width=”1/2″][vc_column_text]

Project description:

Using the environmental characteristics and historical data of power consumption on the substations we have created the stacked machine learning model, which predicts a day ahead load on power substations. We have designed a dedicated model for each substation and provided ready to use the implementation of a forecasting system.

[/vc_column_text][/vc_column_inner][vc_column_inner width=”1/2″][vc_column_text]

Technologies:

• Prophet, Decision Trees, LSTM, PyTorch, scikit-learn.

[/vc_column_text][/vc_column_inner][/vc_row_inner]

---

[/vc_column][/vc_row]