Inspiration
India’s power grid often suffers from regional imbalances: some states generate surplus electricity while others face chronic shortages. Witnessing outages in deficit regions while surplus energy goes underutilized inspired us to design a fair, data‑driven redistribution framework. Our vision was to ensure that every unit of surplus power finds its way to where it is most needed, creating equity in access.
What it does
We built a reproducible framework that transforms India’s fragmented power landscape into a cohesive, equitable energy ecosystem, ensuring that surplus energy is not wasted but shared responsibly.
How we built it
- Data ingestion: collected state‑wise demand and generation data.
- Forecasting: applied time series models to predict demand curves.
- Surplus/deficit detection: compared forecasted demand with available supply.
- Equity algorithm: matched surplus states to deficit states, minimizing losses.
- Visualization: interactive dashboards showing demand, supply, and relief transfers. Mathematically, we framed equity as: [ \text{Relief Power}{i \to j} = \min \Big( S_i - D_i, \; D_j - S_j, \; T{i \to j} \Big) ] where [ S_i ] = supply in state [ i ], [ D_i ] = demand in state [ i ], and [ T_{i \to j} ] = transmission capacity between states [ i ] and [ j ]. ## Challenges we ran into • Data availability: inconsistent reporting across states. • Transmission constraints: limited inter‑state grid capacity. • Model calibration: ensuring forecasts were accurate despite seasonal volatility. • Equity definition: balancing efficiency with fairness in distribution. ## Accomplishments that we're proud of • Built a reproducible equity framework: We successfully designed and implemented a demand–supply balancing algorithm that matches surplus states with deficit states while respecting transmission constraints. • Accurate demand forecasting: Using advanced time series models such as Prophet, Chronos, and TimesFM, we achieved reliable short‑term demand predictions across multiple Indian states. • Visualization dashboards: We created interactive heatmaps and flow diagrams that clearly show surplus/deficit regions and interstate relief transfers, making equity transparent and actionable. • Integration of sustainability: Our framework not only balances the grid but also supports renewable integration, reducing CO₂ emissions and improving overall efficiency. • Scalable design: The system is modular, allowing future expansion to include more states, renewable sources, and policy‑driven equity indices. • Mathematical rigor: We formalized equity distribution with optimization equations, ensuring fairness and reproducibility: [ \text{Relief Power}{i \to j} = \min \Big( S_i - D_i, \; D_j - S_j, \; T{i \to j} \Big) ] where [ S_i ] = supply in state [ i ], [ D_i ] = demand in state [ i ], and [ T_{i \to j} ] = transmission capacity.
What we learned
• Energy economics: how demand and supply vary across states and seasons. • Forecasting techniques: time series models like Prophet, Chronos, and TimesFM for short‑term demand prediction. • Optimization principles: balancing transmission losses, capacity constraints, and fairness. • Visualization: building dashboards with heatmaps and flow diagrams to make equity transparent.
What's next for PowerGrid Bharat
• Expand data coverage: Integrate more granular datasets from POSOCO, SLDCs, and renewable energy sources to improve accuracy. • Refine forecasting models: Experiment with hybrid approaches combining Prophet, Chronos, and deep learning (LSTM, Transformer‑based models) for higher precision. • Equity index development: Formalize a mathematical fairness metric to quantify how equitably surplus power is redistributed: [ \text{Equity Index} = \frac{\sum_{j} \text{Relief Power}{j}}{\sum{j} \text{Deficit}_{j}} ] where Relief Power[ _j ] is the deficit met in state [ j ], and Deficit[ _j ] is the total unmet demand. • Policy integration: Collaborate with regulators to align the framework with interstate transmission policies and renewable purchase obligations. • Scalable deployment: Transition from prototype dashboards to a cloud‑based decision support system for national dispatch centers. • Simulation pilots: Run controlled simulations across selected states to validate the algorithm under real‑world constraints. • Hackathon evolution: Package the solution into an animated, story‑driven presentation that demonstrates both technical rigor and social impact.
Log in or sign up for Devpost to join the conversation.