Native lessons and source materials

An EMS based on Linear Programming

In this section, we present the basics of the Linear Programming (LP) approach for a household Energy Management System (EMS).

docs/advanced_math_model.md

Configuration file

In this section, we will explain all parameters used by EMHASS.

docs/config.md

Deferrable load thermal model

EMHASS supports defining a deferrable load as a thermal model.

docs/thermal_model.md

Demand / capacity charge on peak grid import

Make EMHASS shave your peak grid import (the kW demand / capacity charge many utilities bill on top of energy) in the same optimization that minimizes energy cost — no core changes, no second solver. You set one config key to your tariff's demand rate; EMHASS adds a peak-power term to the objective and spreads deferrable load to hold the single highest import point down. Optionally you f…

docs/cookbook/tariff_demand_charge.md

EMHASS & EMHASS-Add-on differences

Users will pass parameters and secrets into EMHASS differently, based on what method your running emhass. (Add-on, Docker, Python)

docs/differences.md

EV charging as a deferrable load

EMHASS treats an EV charger as a windowed deferrable load: a fixed energy amount that must be delivered before some end time, with charging power up to the charger's rated nominal power. The optimizer then chooses when in the available window to charge.

docs/study_cases/ev.md

Introduction

EMHASS (Energy Management for Home Assistant) is an optimization tool designed for residential households. The package uses a Linear Programming approach to optimize energy usage while considering factors such as electricity prices, power generation from solar panels, and energy storage from batteries. EMHASS provides a high degree of configurability, making it easy to integrate with Hom…

docs/intro.md

Introduction

EMHASS is a Python module designed to optimize your home energy interfacing with Home Assistant.

README.md

Main Core Concepts: The Basics

EMHASS is the "brain" of your energy system. While Home Assistant sees what is happening now, EMHASS looks at the future (forecasts) to decide what should happen to save you the most money.

docs/main_core_concepts.md

MPC orchestration via Node-RED

Drive EMHASS naive-MPC optimization from a Node-RED flow on any cadence, recomputing runtime parameters per call. Transport-agnostic on the EMHASS side; you pick any sensor source (Modbus, MQTT, HA bridge, manufacturer API) for the inputs. After completing this recipe, your Node-RED instance posts a fresh MPC request every tick and your downstream consumers (smart-home controllers, dashb…

docs/cookbook/transport_nodered_mpc_orchestration.md

The machine learning forecaster

Starting with v0.4.0, a new forecast framework is proposed within EMHASS. It provides a more efficient way to forecast the power load consumption. It is based on the skforecast module that uses scikit-learn regression models considering auto-regression lags as features. The hyperparameter optimization is proposed using Bayesian optimization from the optuna module.

docs/mlforecaster.md

The machine learning regressor

Starting with v0.9.0, a new framework is proposed within EMHASS. It provides a machine learning module to predict values from a CSV file using different regression models.

docs/mlregressor.md

Thermal battery for heat pump optimization

EMHASS supports modeling thermal batteries for heat pump systems with thermal mass storage. This is useful when you have a heat pump with underfloor heating or a radiator system with a thermal storage medium like a concrete slab or water-based thermal mass.

docs/thermal_battery.md

🔥 Thermal Integration

docs/section_thermal.md