Competition Project · 2020

Energy Detective Building Energy Forecasting Competition
第一届"能耗侦探"建筑能耗预测竞赛

Student lead for competition operations, dataset curation, scoring infrastructure, and post-competition research analysis.

Building Energy Forecasting Competition Organization Data Infrastructure Limited-Data Setting Research Translation
📅 Feb 2020 – Dec 2020 👤 Student Lead 🏆 195 Participants · 7 Countries
195
Participants
7
Countries & Regions
89
Registered Teams
65
Institutions
56
Competing Teams
140
Valid Submissions
10
Leaderboard Updates
31
Technical Reports

📖 Project Overview

In 2020, I served as the student lead for organizing the first "Energy Detective" building energy forecasting competition. The competition was centered on a research-driven challenge: predicting the energy consumption of a new building with no historical energy data, using only limited physical description and data from 20 reference buildings.

Beyond organizing the logistics, my role was end-to-end. I built the scoring infrastructure, curated the dataset, managed communications with 195 participants across 7 countries, led the award ceremony, and contributed to the post-competition result analysis that became a conference presentation and an SCI journal paper.

Dynamic leaderboard showing submission progression throughout the competition

Dynamic leaderboard — submission progression during the competition

🌏 Who Participated

The competition attracted 195 participants from universities, research institutes, and industry companies across 7 countries and regions, including mainland China, Singapore, Germany, the United Kingdom, the United States, Australia, and Hong Kong.

Participating institutions word cloud

Participating Institutions
Word cloud (registration data)

Geographic distribution of participants

World Distribution
(195 participants · 7 regions)

💡 Why It Matters

Connecting research problems to community practice

Rather than working on a model in isolation, we translated a meaningful research problem, limited-data building energy prediction, into a structured, reproducible competition task that dozens of teams could engage with simultaneously.

A realistic, not a benchmark, challenge

The task was fully blind: no historical energy data for the target building, only limited physical specs. This is much closer to real engineering practice than leaderboard-style benchmark datasets.

Producing methodological insight, not just rankings

The post-competition analysis revealed actionable findings: summer HVAC load is more predictable than winter; feature engineering remains the key bottleneck; and white-box/black-box hybrid methods are a promising direction.

🎯 Competition Task Design

The competition focused on a limited-data forecasting setting: participants were asked to predict the 2017 annual energy consumption of a target office building. The target building had no historical energy records, only limited physical information (drawings, envelope specs, HVAC configuration). Participants could leverage:

  • Measured energy data (2015–2017) from 20 reference office buildings
  • Basic physical characteristics of all buildings
  • Measured weather data for the same period

Evaluation metric: CV-RMSE. This design required methods capable of cross-building knowledge transfer, physics-informed feature engineering, and generalization under data scarcity.

Competition task design: Predicting 2017 energy from 20 reference buildings

Competition Task Illustration: Leveraging reference building data to predict a target building's performance under data scarcity.

⚙️ My Role & Leadership

📦

Dataset & Task Design

  • Processed raw meter data and physical model specs into a publishable competition dataset
  • Architected the "limited-data" task structure and documentation
Key Highlight: Cross-building transfer dataset
📊

Infrastructure & Operations

  • Built automated scoring pipeline for CV-RMSE evaluation
  • Managed 140+ valid submissions and real-time leaderboard updates
  • Implemented data deduplication and validation protocols
Key Highlight: Automated evaluation pipeline
📢

Communications & Scaling

  • Managed public outreach: 5+ WeChat technical articles published
  • Direct communication with 195 participants from 7 countries
  • Designed all competition visual identities and awards
Key Highlight: Global community engagement
🤝

Coordination & Leadership

  • Liaised between university, sponsors, and international experts
  • Hosted and moderated the virtual Award Ceremony
  • Supervised the shortlisted team report evaluation process
Key Highlight: End-to-end event management
📝

Research Translation

  • Led the post-competition result analysis and methodological summary
  • Presented findings at the National HVAC Simulation Annual Meeting
  • First-authored SCI journal paper in Applied Energy (2022)
Impact: Top-tier Journal Publication

🔬 Key Findings from Result Analysis

Best CV-RMSE achieved: 0.67

Under fully blind conditions (no historical target data), the best submission reached a CV-RMSE of 0.67, establishing a concrete baseline for cross-building transfer in limited-data settings. (MAPE analysis pending.)

Summer is easier than winter

Summer AC energy prediction outperformed winter heating predictions consistently across methods, suggesting this is the more tractable sub-problem.

Feature engineering remains the bottleneck

Latent features, particularly building characteristics not directly available in specs, were consistently underutilized, pointing to a major open research opportunity.

White-box + black-box hybrid methods are promising

Despite their complexity, physics-informed approaches combined with data-driven models showed the most potential in this limited-data regime.

What I valued most about this project was not just that we ran a competition to completion — it was that we turned a scattered set of practical tasks (data cleaning, scoring algorithms, logistics, and reporting) into a coherent, research-facing workflow. For me, it was the first time I experienced how task definition, data organization, evaluation protocol, and community engagement are just as important to a research contribution as the model itself.