grid-aware-energy-load-shifter
Grid-aware energy load shifter for Home Assistant. Reads real-time electricity prices (TOU, time-of-use, dynamic pricing), solar production forecasts, battery state of charge, and consumption data from Home Assistant. Schedules deferrable household loads (EV charging, HVAC pre-conditioning, pool pump, dishwasher, laundry, water heater) to cheapest rate windows. Calculates cost savings, optimizes solar self-consumption, and supports virtual power plant (VPP) demand response signals. Works with Nordpool, ENTSO-e, Tibber, Octopus Energy, Amber Electric, and any utility rate plan worldwide. Built for distributed energy resource (DER) optimization and residential demand-side management.
- License 许可
- MIT
- 最近更新
- 2026-06-07
- Stars
- ★ 0
- Forks
- 1
01 前言 Front Matter
- name
- grid-aware-energy-load-shifter
- metadata
- { "openclaw": { "tags": [ "energy", "home-assistant", "load-shifting", "time-of-use", "solar", "battery-storage", "demand-response", "vpp", "ev-charging", "smart-home", "DER", "grid-optimization" ], "emoji": "⚡", "requires": { "env": [ "HA_URL", "HA_TOKEN" ] } } }
- description
- Grid-aware energy load shifter for Home Assistant. Reads real-time electricity prices (TOU, time-of-use, dynamic pricing), solar production forecasts, battery state of charge, and consumption data from Home Assistant. Schedules deferrable household loads (EV charging, HVAC pre-conditioning, pool pump, dishwasher, laundry, water heater) to cheapest rate windows. Calculates cost savings, optimizes solar self-consumption, and supports virtual power plant (VPP) demand response signals. Works with Nordpool, ENTSO-e, Tibber, Octopus Energy, Amber Electric, and any utility rate plan worldwide. Built for distributed energy resource (DER) optimization and residential demand-side management.
03 SKILL.md 正文
Grid-Aware Energy Load Shifter
Shift heavy residential loads to the cheapest electricity hours using Home Assistant energy data.
Quick Start
# Find all energy-related entities in HA
python3 {baseDir}/scripts/ha_bridge.py discover
# Get a full energy dashboard snapshot (prices, solar, consumption, batteries)
python3 {baseDir}/scripts/ha_bridge.py energy-summary
# Turn on the EV charger
python3 {baseDir}/scripts/ha_bridge.py call-service switch/turn_on --entity-id switch.ev_charger
Connection
Two paths to reach Home Assistant:
- MCP (preferred): If the HA MCP server is configured, use
mcporter call homeassistant.<tool>directly. - REST API: Use
python3 {baseDir}/scripts/ha_bridge.py. RequiresHA_URLandHA_TOKENenvironment variables.
Security
Required credentials:
| Variable | Description |
|---|---|
HA_URL |
Home Assistant base URL (e.g. http://homeassistant.local:8123) |
HA_TOKEN |
Home Assistant Long-Lived Access Token |
Least-privilege recommendations:
- Create a dedicated Home Assistant user account for this skill (e.g.
openclaw-energy) - Generate a Long-Lived Access Token from that account only
- Limit the account's entity access to energy-related entities if your HA setup supports entity-level permissions
- Test with read-only commands first (
discover,energy-summary) before enabling device control
Domain allowlist: The call-service command restricts actions to energy-related domains only: switch, automation, script, climate, water_heater, input_boolean, input_number, number. All other domains (e.g. lock, alarm_control_panel) are blocked with exit code 2.
Commands
| Command | What it does | Example |
|---|---|---|
discover |
List all energy entities | ha_bridge.py discover |
energy-summary |
One-shot dashboard (prices + consumption + solar + storage) | ha_bridge.py energy-summary |
status <entity> |
Read a single entity's state and attributes | ha_bridge.py status sensor.electricity_price |
call-service <d/s> |
Call an energy-related HA service (restricted to allowed domains) | ha_bridge.py call-service switch/turn_on --entity-id switch.ev_charger |
history <entity> |
Get state changes over last N hours | ha_bridge.py history sensor.grid_import --hours 24 |
All commands output JSON to stdout.
Load-Shifting Workflow
Follow these steps when asked about energy optimization:
- Discover available energy entities: run
discoverorenergy-summary - Read prices: Check pricing entities' state and attributes — look for:
- Hourly price arrays in
today/tomorrow/prices_today/ratesattributes price_levelattribute (CHEAP / NORMAL / EXPENSIVE)- Current vs. average price comparison
- Hourly price arrays in
- Identify deferrable loads: Find
switch.*entities for schedulable devices (EV charger, pool pump, dishwasher, washer/dryer, water heater) - Find the cheapest window: Scan hourly prices for the contiguous N-hour block with the lowest sum (N = estimated run time of device)
- Execute: Call
switch/turn_onat the optimal time, orautomation/triggerif the user has an existing automation
Interpreting Price Data
Different integrations expose prices differently:
- Hourly arrays (Nordpool, ENTSO-e, Octopus): Read
today/tomorrowattributes → find cheapest hours - Price level (Tibber): Read
price_level→ act when CHEAP or VERY_CHEAP - Real-time (Amber Electric): Read 5-minute pricing → shift loads immediately when cheap
- Utility meter tariffs: Read
sensor.*_peakvssensor.*_offpeak→ user's HA automations switch tariffs at configured times - Static TOU: Read
current_priceattribute → compare against historical average
Cost Savings Estimate
When recommending a shift, show estimated savings:
savings = (current_rate - cheapest_rate) × device_power_kw × run_duration_hours
Solar Self-Consumption
If solar sensors exist, align loads with peak production:
- Read
sensor.forecast_solar_*orsensor.solcast_*for today's forecast - Shift loads to hours with highest expected production
- This avoids grid import entirely — savings = full retail rate × kWh shifted
HVAC Pre-Conditioning
HVAC is the largest residential load (40-50% of electricity). Pre-cool or pre-heat during cheap/solar hours so the home coasts through expensive peak periods:
- Read
climate.*entities for current HVAC mode and setpoint - During cheapest window: lower cooling setpoint by 2-3F (pre-cool) or raise heating setpoint by 2-3F (pre-heat)
- During peak window: raise cooling setpoint by 2-3F to coast on thermal mass
- Savings estimate: 1.5-3 kW shifted × price differential × hours
Water Heater Scheduling
Electric water heaters (4.5 kW typical) are ideal deferrable loads:
- Find
switch.water_heaterorwater_heater.*entities - Heat during cheapest/solar window to full temperature
- Turn off during peak hours (tank maintains temperature for 4-6 hours)
- Savings estimate: 4.5 kW × price differential × 3-4 hours/day
Battery Arbitrage
If home battery entities exist (sensor.battery_soc, sensor.powerwall_*, sensor.enphase_*):
- Read current state of charge and charge/discharge rate limits
- Charge from grid during cheapest hours (or from solar)
- Discharge to home during peak price hours to avoid grid import
- Advanced: If battery supports grid export and VPP enrollment, discharge to grid during extreme price events ($2,000+/MWh)
- Savings estimate: battery_capacity_kwh × (peak_rate - valley_rate)
Demand Response / VPP Integration
For homes enrolled in utility demand response or virtual power plant programs:
- Read demand response signal entities (if available via HA integration)
- When DR event active: shed non-critical loads, pre-cool/pre-heat, discharge battery
- Estimate DR payment: kW reduced × event duration × program rate
Entity Reference
For detailed entity patterns across providers, read: energy_entities.md
04 同仓库更多 Skills
crowd-prompting
A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.
ceaser
Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir/UltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).
ceaser-send
Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir/UltraHonk zero-knowledge proofs.
dilemm-ai
Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).
moldium
Post and manage content on the Moldium blog platform. Triggered by "post to Moldium", "write a blog post", "publish an article", etc.
arxiv-paper-reviews
Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date/category/interest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http://weakaccept.top:8000/.