报告题目：基于机器学习和数据挖掘的智能用电数据处理系统

报告人：蒋磊 博士

时间：12月15日 19：00—21：00

地点：河南大学金明校区曾宪梓楼东侧508会议室

报告摘要：The management of electricity system in home environments plays an important role in generating energy consumption and improving efficiency of energy usage. At present, nonintrusive appliance load monitoring (NIALM) techniques are the most effective approach for estimating the electrical power consumption of individual appliances. This paper presents our contributions in intelligent electrical appliance detection and recognition in home environment. The contributions are consisted of two parts. First, an automatic edge symbol detection (ESD) is developed to detect power load event for the event detection in NIALM, this new transient detection approach can help the system locate all the load events (switch on and switch off) precisely. Second, a modified power appliance disaggregation technique based on power harmonic features and deep learning is presented. The novel method proposed is suitable for general power load classification and disaggregation, and is mainly carried out by combining support vector machines with various power features using the PCA concept. Experiments on real world data have demonstrated higher recognition accuracy and faster computational speed of the approach, and illustrated the effectiveness for distinguishing different loads. It has higher recognition accuracy and faster computational speed. The experimental results of the new load events detection and power decomposition technique on real date are presented with promising results.

报告人简介：蒋磊，博士，2009年毕业于郑州大学计算机系，后于2010赴澳洲攻读IT博士学位，并在期间担任澳洲联邦科学与工业研究组织能源部实习研究员，主要研究领域为非侵入式电器监控，信号识别，智能楼宇等。参加了包含“建筑物供暖通风和空调”、“智能交通系统的功能选择”、“未来电网旗舰计划”等在内的由政府、澳洲联邦科学与工业研究院和纽卡斯尔大学等资助的重大项目，发表多篇国际期刊和会议论文。多次去往欧，澳，中进行学术交流，并发表重要演讲。他也是澳华科技协会 ASTA，EII 等科技组织的会员，IET Generation, Transmission & Distribution, IEEE Transactions on Industrial Informatics 等国际期刊的评审。2014年加入澳洲慧衍创投，主导和参与慧衍创投的多起投资案例，总投资额超3200万元。2016年和团队共同开发“能源互联网用电负荷智能管理系统”（软件+硬件）进入终试阶段；17年加入中国电科院 “用电负荷智能感知技术”研发项目组；同多家国内企业进行国际技术交易，包括智能电网终端设备、电力储能方案、氢燃料电池、矿山智能设备等项目，交易总额超过百万元，技术总价值超过三千万元；帮助多家境外高科技公司（区块链、线上国际教育、国际科技金融服务等）在中国落地及业务在中国市场的开拓；主办及承办多次国内外科技创新交流活动及会议。

热忱欢迎广大感兴趣的师生积极参与！

主办单位：

河南省智能网络理论与关键技术国际联合实验室

河南大学软件学院