The smart grid will allow substantial electricity savings and peak demand savings by potentially supplying utility power for direct load management, the calculation in support of competitive pricing, and even the granular data required for energy usage to be more targeted explicitly at customer needs, the processing of data and predictions for a smart grid in a building with the energy profile and occupants' profile, is challenging. This article has been suggested a Machine Learning-Based Energy-Efficient Framework to analyze the motion of occupants, deliver short-term energy forecasts, and assign renewable energy in the smart grid. Second, an indoor localization device with wireless data analysis collects occupants' profile, and the energy profile is managed by a real-time smart meter network with an electrical charge evaluation. Furthermore, the energy profile and 24-hour profile will be paired with a forecast utilizing an online machine learning framework with an analysis of data in real-time. To decrease peak demand for the primary power grid, the solar energy source is assigned to the further power grids based upon the forecast occupant movement profile and energy consumption profile. On the smart gateway network, the complete power flow with minimal computing resources and a general enabled engine can be controlled. The results of the studies on real-time datasets show that the precision of the suggested energy forecast will increase significantly when compared to the other existing methods.

中文翻译：

---

基于机器学习的智能电网节能技术

智能电网将通过潜在地为直接负载管理、支持竞争性定价的计算甚至能源使用所需的细粒度数据提供大量电力节省和峰值需求节省，以更明确地针对客户需求，处理具有能源概况和居住者概况的建筑物中智能电网的数据和预测具有挑战性。本文建议使用基于机器学习的节能框架来分析居住者的运动、提供短期能源预测以及在智能电网中分配可再生能源。其次，具有无线数据分析功能的室内定位设备收集居住者的资料，能源资料由具有电荷评估的实时智能电表网络管理。此外，能源概况和 24 小时概况将与利用在线机器学习框架进行实时数据分析的预测配对。为了降低主电网的峰值需求，太阳能源根据预测的乘员移动情况和能源消耗情况分配给其他电网。在智能网关网络上，可以控制具有最少计算资源和通用引擎的完整功率流。对实时数据集的研究结果表明，与其他现有方法相比，建议能源预测的精度将显着提高。为了降低主电网的峰值需求，太阳能源根据预测的乘员移动情况和能源消耗情况分配给其他电网。在智能网关网络上，可以控制具有最少计算资源和通用引擎的完整功率流。对实时数据集的研究结果表明，与其他现有方法相比，建议能源预测的精度将显着提高。为了降低主电网的峰值需求，太阳能源根据预测的乘员移动情况和能源消耗情况分配给其他电网。在智能网关网络上，可以控制具有最少计算资源和通用引擎的完整功率流。对实时数据集的研究结果表明，与其他现有方法相比，建议能源预测的精度将显着提高。