Data on Smart Home Energy Flow Optimization Time Series from Practical Case Studies

This dataset provides a comprehensive representation of the energy flows, component states, and control variables of a residential smart home equipped with photovoltaic (PV) generation, a battery energy storage system (BESS), a ground source heat pump (GSHP), deferrable appliances (DAs), and an electric vehicle (EV) smart charger (SC). The data originate from a one-year simulation performed with a 15-minute time resolution, reproducing the realistic operation of a single-family dwelling connected to the distribution grid.

For a better reading of results, datetime array has been set to 2025.

The dataset is structured into four folders, each corresponding to one of the simulated case studies discussed in "Smart home energy flow optimization, a practical case study",. Energy Conversion and Management: X, https://doi.org/10.1016/j.ecmx.2025.101340:

-Baseline (woEMS): reference scenario without any Energy Management System (EMS), where no flexibility services are considered.
-Self-Consumption (sc): optimization promoting local utilization of PV generation by minimizing energy imported from the grid.
-Smoothing (sm): optimization aiming to minimize squared temporal variations in grid exchange, producing smoother profiles.
-Baseline Profile Matching (bp): optimization minimizing deviations from a flat baseline energy profile, encouraging balanced daily exchanges.

Each folder includes time-series data in JSON format, describing for every 15-minute time step:

- Active power flows between the grid and smart home subsystems.
- Input variables such as external temperature, thermal demand, load availability, and user constraints.
- State variables including state of charge (SoC) of batteries, tank temperature, and appliance cycle states.

A complete mapping between symbols, variable names, and data columns is provided in the included README file.
All files use consistent naming conventions and physical units to facilitate integration, comparison, and reuse. Diagnostic figures and quick visualizations can be generated using the provided Python and MATLAB scripts (plotSmartHomeData.py and plotSmartHomeData.m), which reproduce main power trajectories and component state trends over a selected time horizon.

This dataset can be used for benchmarking, model validation, and data-driven research in residential energy management, grid flexibility assessment, and smart home optimization. It provides a reproducible, high-resolution framework suitable for the training and testing of optimization algorithms and machine learning models for predictive EMS development.

本数据集全面刻画了配备光伏（PV）发电系统、电池储能系统（BESS）、地源热泵（GSHP）、可延迟负载（DAs）与电动汽车（EV）智能充电器（SC）的住宅智能家居的能量流动、组件状态与控制变量。该数据集源自一项时长一年、时间分辨率为15分钟的仿真实验，复刻了接入配电网的单户住宅的真实运行工况。

为便于结果解读，本次仿真的时间戳数组已设置为2025年时段。

本数据集分为四个文件夹，分别对应《"Smart home energy flow optimization, a practical case study"》（发表于*Energy Conversion and Management: X*，DOI: 10.1016/j.ecmx.2025.101340）中讨论的四项仿真案例研究：
- 基准工况（无能源管理系统（EMS））：未配置任何能源管理系统（EMS）且未考虑任何灵活性服务的参考场景。
- 自发自用（sc）：通过最小化电网购电量以提升光伏就地消纳水平的优化工况。
- 功率平滑（sm）：以最小化电网交互功率的时域波动平方为目标的优化工况，可生成更平滑的功率曲线。
- 基准曲线匹配（bp）：以最小化与平坦基准能耗曲线的偏差为目标，鼓励实现每日电网交互平衡的优化工况。

每个文件夹均包含JSON格式的时序数据，以15分钟为步长记录以下内容：
- 电网与智能家居各子系统间的有功功率交互数据。
- 输入变量，包括环境温度、热负荷需求、负载可用状态与用户约束条件。
- 状态变量，包括电池荷电状态（SoC）、储水箱温度与家电运行周期状态。

数据集附带的README文件中提供了符号、变量名与数据列名的完整对应关系。所有文件均采用统一的命名规范与物理单位，便于数据集成、对比与复用。可通过附带的Python与MATLAB脚本（plotSmartHomeData.py与plotSmartHomeData.m）生成诊断图表与快速可视化结果，用于复现选定时间范围内的主要功率变化曲线与组件状态趋势。

本数据集可用于住宅能源管理、电网灵活性评估与智能家居优化领域的基准测试、模型验证与数据驱动研究。其提供了可复现的高分辨率框架，适用于面向预测型能源管理系统开发的优化算法与机器学习模型的训练与测试。