Back to Projects

Team Name:

GAC


Team Members:


Evidence of Work

GAC - Renewalytics

Project Info

Team Name


GAC


Team Members


Randika , Achala Chathuranga Aponso

Project Description


Renewalytics: Powering Tomorrow, Optimizing Renewable Energy Site Selection for a Sustainable Australia

Description:
Renewalytics is a data-driven solution designed to address the challenge of optimizing renewable energy site selection across Australia. Using data from the Network Map Renewables website, along with public datasets, Renewalytics identifies optimal locations for renewable energy projects. The model balances crucial factors such as energy output potential, grid connectivity, environmental sustainability, and land use, ensuring efficient site placement with minimal environmental and societal impact.

The algorithm integrates geographical data, renewable energy potential, and existing infrastructure to deliver accurate recommendations. It analyzes multiple variables to provide a comprehensive view that facilitates informed decision-making, promoting a sustainable and efficient energy future. Renewalytics offers a technically sound approach while prioritizing ecological preservation and seamless integration into the existing energy grid.

This innovative solution ensures that stakeholders in the renewable energy sector have clear and actionable insights to support Australia’s transition to renewable energy, helping to meet national sustainability goals and enhance energy infrastructure for the future.


Evidence of Work

Video

Team DataSets

Rosetta - Network map

Description of Use Dataset Description and Usage 1. Dataset: Network Map Renewables July 2024 (Points) Description: This dataset provides spatial data related to renewable energy projects across Australia. Each data point represents a renewable energy site, including details about the location, type of technology used, and coordinates. The dataset is particularly useful for identifying existing renewable energy projects and assessing their proximity to other infrastructure. Key Columns: Coordinates: Contains the latitude and longitude of each renewable energy site. Site Name: The name of the renewable energy project. Technology Type: The type of technology used at the site, such as solar, wind, or other renewable sources. Other attributes: Additional site-related details like project capacity, ownership, or date of installation (if available). Usage in the Model: The dataset's geographical information (latitude, longitude) is used to create spatial points for the renewable energy sites. These points are visualized on a map using Folium. The technology type is used for identifying and categorizing renewable energy sites based on their source of power (e.g., solar, wind). The site name provides context to the renewable energy sites and serves as a descriptive identifier when displaying results. 2. Dataset: Network Map Solar Panels September 2024 Description: This dataset provides spatial data regarding the placement and installation of solar panels across Australia. It includes polygons representing the areas covered by solar panels, giving a comprehensive view of solar energy distribution. Key Columns: geometry: Contains polygon data representing the areas where solar panels are installed. This helps in visualizing solar power coverage across different regions. Other attributes: Additional information on the solar panel systems, such as installation date, capacity, and confidence level of the data accuracy. Usage in the Model: The geometry column is used to visualize solar panel areas on a map, providing insights into areas already covered by solar energy. The spatial data from the dataset helps in understanding how widespread solar panel installations are and how they can contribute to the total renewable energy potential in the region. 3. Generated Data for Mock Fields Since the provided datasets do not contain all necessary fields required for the optimization model, the following columns are generated with mock data: Proximity_to_Infrastructure: Represents the proximity of each renewable energy site to important infrastructure, such as roads, urban centers, or industrial areas. This is crucial for evaluating how easily the site can be connected to existing infrastructure. Environmental_Impact: Measures the environmental sensitivity of each renewable energy site. A lower score indicates a lesser impact on the environment. This helps in minimizing ecological disturbances when selecting optimal sites. Energy_Potential: Estimates the energy generation potential of each site based on factors such as solar radiation and wind speed. High-potential sites are prioritized for renewable energy development. Grid_Connectivity: Calculated based on the distance to the nearest grid location (e.g., substations, transmission lines), as integrating renewable energy into the grid is a critical factor for project success. Usage in the Model: These fields are used as part of the multi-criteria decision-making (MCDM) model to evaluate each site's suitability for renewable energy projects. Normalization of these criteria allows the model to fairly compare different sites, and a composite score is generated to rank the sites based on their overall performance across the criteria. Usage of the Datasets in the Project Geospatial Analysis and Visualization: Both datasets (Renewables and Solar Panels) are used to generate a map of Australia showing the distribution of renewable energy projects and solar panel installations. The Folium library is used for this visualization, allowing users to interact with the map and explore site details. Optimization Model: The key objective of the project is to select the best locations for renewable energy projects in Australia. This is achieved through two optimization models: Linear Programming: Evaluates each site based on its proximity to infrastructure, environmental impact, energy potential, and grid connectivity. The model ranks the sites and selects the top candidates for renewable energy projects. Genetic Algorithm (GA): This advanced algorithm further optimizes the selection by simulating the process of natural selection, evolving the best solutions over multiple iterations. Results Reporting: The output of the model is a ranked list of the top renewable energy sites based on a composite score that weighs multiple factors. This report is saved as a CSV file for easy analysis and submission. Summary of Use The provided datasets are critical for both visualizing and optimizing the selection of renewable energy sites. The geospatial information allows us to understand the distribution of renewable energy resources, while the generated data fields enable the model to evaluate each site against critical factors such as infrastructure proximity, environmental impact, and energy potential.

Data Set

Challenge Entries

Renewable Energy Site Selection Model

How can we optimally position renewable energy projects across Australia to maximize efficiency, minimize environmental impact and integrate seamlessly into the existing grid?

Go to Challenge | 7 teams have entered this challenge.