openenv.yaml

name: gridmind-rl
version: 1.0.0
description: |
  GridMind-RL: Industrial Load-Shaping and Demand-Response Environment.
  An RL environment simulating a real-world building energy management system.
  Control HVAC, thermal storage, and schedule batch jobs in response to
  stochastic time-of-use prices and grid stress events.

author: LOKyu Team
tags:
  - openenv
  - reinforcement-learning
  - energy
  - demand-response
  - continuous-control
  - discrete-control

server:
  host: "0.0.0.0"
  port: 7860
  protocol: http

schemas:
  observation:
    type: object
    properties:
      indoor_temperature:
        type: number
        description: Current building/process temperature (°C)
      thermal_storage_level:
        type: number
        minimum: 0.0
        maximum: 1.0
        description: Thermal storage tank level (0.0=empty, 1.0=full)
      process_demand:
        type: number
        description: Current process industrial power demand (kW)
      current_price:
        type: number
        description: Real-time electricity price ($/kWh)
      grid_stress_signal:
        type: number
        minimum: 0.0
        maximum: 1.0
        description: Utility signal for DR urgency (0=normal, 1=critical)
      carbon_intensity:
        type: number
        description: Grid carbon intensity (gCO2/kWh)
      hour_of_day:
        type: integer
        minimum: 0
        maximum: 23
        description: Hour of the day for time-aware scheduling
      batch_queue:
        type: array
        items:
          type: integer
        description: List of pending batch jobs (values are deadline slot indices)
      cumulative_cost:
        type: number
        description: Total energy cost incurred so far this episode ($)
      step:
        type: integer
        minimum: 0
        maximum: 95
        description: Current episode step index (0–95); 96 steps = 24 hours at 15-min resolution
      building_id:
        type: integer
        description: Building identifier for multi-building federation

  action:
    type: object
    required:
      [
        "hvac_power_level",
        "thermal_charge_rate",
        "batch_job_slot",
        "load_shed_fraction",
      ]
    properties:
      hvac_power_level:
        type: number
        minimum: 0.0
        maximum: 1.0
        description: Fraction of max HVAC power to apply (0.0-1.0)
      thermal_charge_rate:
        type: number
        minimum: -1.0
        maximum: 1.0
        description: Thermal storage charge (+) or discharge (-) rate
      batch_job_slot:
        type: integer
        minimum: 0
        maximum: 4
        description: Which time slot to schedule the next batch job (0=now, 1-4=defer)
      load_shed_fraction:
        type: number
        minimum: 0.0
        maximum: 0.5
        description: Fraction of non-critical load to shed during grid stress (0.0-0.5)
      building_id:
        type: integer
        description: Building identifier for multi-building federation

  reward:
    type: number
    description: Dense multi-component reward (cost, optional temperature/grid/carbon/deadlines) task-gated to match objectives.

tasks:
  - id: 1
    name: "Cost Minimization"
    description: "Minimize total energy cost over a 24-hour episode with no process constraints."
    difficulty: "easy"
    weights:
      cost: 1.0
  - id: 2
    name: "Constrained Temperature Management"
    description: "Minimize cost while keeping indoor temperature within ±2°C of setpoint at all times."
    difficulty: "medium"
    weights:
      cost: 0.6
      temperature: 0.4
  - id: 3
    name: "Full Demand-Response with Batch Scheduling"
    description: "Minimize cost, maintain temperature, respond to grid stress events, schedule all batch jobs, and minimize carbon."
    difficulty: "hard"
    weights:
      cost: 0.28
      temperature: 0.20
      grid_response: 0.20
      batch_deadline: 0.12
      carbon: 0.20

endpoints:
  health:
    path: /health
    method: GET
  ping:
    path: /ping
    method: GET
  reset:
    path: /reset
    method: POST
  step:
    path: /step
    method: POST
  state:
    path: /state
    method: GET
  grade:
    path: /grade
    method: GET
  replay:
    path: /replay
    method: GET
  tasks:
    path: /tasks
    method: GET
  metrics:
    path: /metrics
    method: GET