Artificial intelligence provides a convenient route for power grid stability assessment. Compared with simulation-based approaches, artificial intelligence can potentially save time on model development and numerical computation in stability assessment.
The ascent of renewable energy sources provides
The ascent of renewable energy sources provides the global community with a much demanded alternative to traditional, finite and climate-unfriendly fossil fuels. However, their adoption poses a set of new paradigms, out of which two interrelated aspects deserve particular attention:
- Prior to the rise of renewable energy sources, the traditional operating ecosystem involved few production entities (sources) supplying energy to consumers over unidirectional flows. With the advent of renewable options, end users (households and enterprises) now not only consume energy but have the ability to produce and supply it – hence a new term to designate them, ‘prosumers‘. As a result, energy flow within distribution grids – ‘smart grids‘ – has become bidirectional;
- Despite the increased flexibility brought in by the introduction of renewable sources and the aforementioned emergence of ‘prosumers’, the management of supply and demand in a more complex generation / distribution / consumption environment and the related economic implications (particularly the decision to buy energy at a given price or not) have become even more challenging.
Smart Grid Stability
Relevant contributions on how to tackle the requirements of such a new scenario have been offered by academia and industry over the past years. Special attention has been devoted to the study of smart grid stability.
Curated data available:
Considering the nature of the problem to be investigated and the dataset properties (as described in Section 3 below), two major objectives are proposed:
1. Pursue improvements in predictions with deep learning (Keras’ Sequential model);
2. Take the opportunity to assess the influence of deep learning architecture (number and size of hidden layers), number of epochs and the relevance of dataset augmentation.
Datasets
Predicting Smart Grid Stability with Deep Learning
Dataset comprises one power source (a centralized generation node) supplying energy to three consumption nodes. The model takes into consideration inputs (features) related to:
Features are-
|
Electrical Grid Stability Simulated Data Data Set
| Dataset contains 11 predictive attributes,1 non-predictive(p1),2 goal fields |
Wind Power Generation Forecast
| Wind Power Generation Forecast by Coupling Numerical Weather Prediction Model and Gradient Boosting Machines in Yahyalı Wind Power Plant |
Data Cleaning And Data Prep Tools Used By Our Team
The Project team will use the appropriate tools based on volume, location and nature of the client data and deliver the cleaned/formatted data with visualization or ingested in a database-whatever way a client will demand. They can also run initial POC with client suggested tools/machines to do initial QC of the data and feasibility of algorithmic solution.
Data Cleaning and Data Prep Tools used by our team
