Building a prototype predictive model to forecast solar panel electricity generation

-Build a predictive model.
– Automate prediction process.
– Decrease financial losses due to forecast errors.
– Provide the client with a detailed report on model accuracy and potential ways to increase the accuracy.

To achieve higher predictive model accuracy, the provided hourly generation and daily temperature data has been enriched with additional weather data and additional relevant data from different (including open ones) sources, which allowed to discover and use deeper data dependencies.
With respect to analysis results a number of predictive models of different type has been built.
Model is built by combining different machine learning algorithms, precisely:
– decision trees,
– neural networks,
– metric based algorithms.

– Discovered the features that influence the forecast result the most.
– Built a prototype predictive model.
– Analyzed viability and means to implement ML model to solve the problem, as well as the ways to improve it, and provided the client with the respective detailed report.
AM-BITS team achieved 84% model accuracy (on data from March to October 2021).

Request full cases:

Other cases: