Programme Parameters
Advanced Postgrad
3 Days (4.5 Hrs)
Online (e-LMS)
• Prior working knowledge of the field and comfort with core tools and quantitative reasoning.
• A laptop or desktop with a stable internet connection.
• Willingness to complete assignments and the capstone project.
About This Course
The Transformer–LSTM Hybrid Forecast Engine for RE + Storage Dispatch course is a three-day, hands-on sprint from data prep to operations. Every participant receives a verified e-Certificate and e-Marksheet from the Deep Science & Technology Consortium.
🎯 Program Aim
The Transformer–LSTM Hybrid Forecast Engine for RE + Storage Dispatch course is a three-day, hands-on sprint from data prep to operations.
📋 Course Objectives
1. Put AI Enablement techniques to work on real datasets and case studies.
2. Build a defensible project you can showcase to supervisors, reviewers, or employers.
👥 Who Should Enroll?
• Master's and senior undergraduate students specializing in AI Enablement
• R&D engineers and working professionals applying AI Enablement in industry
• Academics and educators building research or teaching capacity in AI Enablement
🚀 Key Learning Outcomes
• Tangible, reproducible AI Enablement work to show supervisors or employers.
• A verified e-Certificate of competency and e-Marksheet from the Deep Science & Technology Consortium.
💎 What You'll Gain
Live & Recorded Sessions
Lifetime access to class recordingse-Certificate on Completion
Cryptographically verified credentialPost-Programme Support
Direct access to mentors & councilHands-On Experience
Notebooks, real-world code & datasetsCurriculum Outline
Data Preparation & Hybrid Model Fundamentals
Understand signals and horizons for solar/wind, net load, and price in intraday/day-ahead scenarios. • Apply time-aware data splits and engineer features (lags/rolls, weather look-ahead, plant metadata, calendar). • Define metrics like RMSE/sMAPE and multi-horizon pinball loss; design persistence baselines. • Grasp the hybrid concept: Transformer for exogenous weather and LSTM for plant history with late fusion.
Advanced Hybrid Model Training & Calibration
Explore Transformer-LSTM architecture details including sequence lengths, encoder–decoder attention, LSTM history streams, fusion, and multi-task heads. • Implement training hygiene practices: scaling, scheduled sampling, dropout/weight decay, gap handling, and early stopping. • Integrate uncertainty quantification: quantile heads, ensembles, and conformal calibration for P10/P50/P90 outputs. • Perform rolling-origin backtests for evaluation; analyze error by regime and hour.
Forecast-driven Storage Dispatch with MPC
Construct comprehensive battery models including SoC bounds, power limits, efficiency, degradation proxies, and reserves. • Implement optimization using rolling-horizon Model Predictive Control (MPC) with forecast ensembles. • Define optimization objectives: arbitrage, ramp smoothing, and peak shaving. • Understand operational considerations: DA/RT alignment, penalties, and fail-safes for inaccurate forecasts.
KPI Dashboard & Operationalization
Track key performance indicators (KPIs) such as cost savings, reserve compliance, curtailment avoided, and VFF (Value of Forecast). • Build time-aligned SCADA+weather datasets with time-aware splits. • Engineer features; establish persistence/LSTM baselines. • Ensure training hygiene and uncertainty calibration.
Technical Specifications
| Parameter | Requirement |
|---|---|
| Covered Tool / Platform | Python |
| Covered Tool / Platform | SCADA |
| Covered Tool / Platform | Weather Data |
| Covered Tool / Platform | Machine Learning Libraries |
Frequently Asked Questions
Scholar Feedback & Reviews
Based on 0 scholar submissions
Rating Breakdown
No verified reviews published yet. Be the first to share your academic experience.
Leave Scholar Feedback
Your rating will help prospective scholars. Ratings below 3 stars are routed privately to the faculty mentor for immediate response.
