Energy Management Big Data in Power Load Forecasting CRC Press Focus Shortform Book Program Series
Auteur : Boicea Valentin A.
This book introduces the principle of carrying out a medium-term load forecast (MTLF) at power system level, based on the Big Data concept and Convolutionary Neural Network (CNNs). It also presents further research directions in the field of Deep Learning techniques and Big Data, as well as how these two concepts are used in power engineering.
Efficient processing and accuracy of Big Data in the load forecast in power engineering leads to a significant improvement in the consumption pattern of the client and, implicitly, a better consumer awareness. At the same time, new energy services and new lines of business can be developed.
The book will be of interest to electrical engineers, power engineers, and energy services professionals.
Adrian–Valentin Boicea, a former PhD student at Politecnico di Torino, Italy, received the BS in electrical engineering and electrical power systems from the University Politehnica of Bucharest (UPB), Romania. Currently, he is a Lecturer within the Department of Electrical Power Systems at the UPB. His research interests include the distributed generation systems, energy efficiency, renewable sources, the operational research algorithms used in power engineering, as well as Big Data analysis applied in the energy sector.
Date de parution : 06-2021
13.8x21.6 cm
Thèmes d’Energy Management :
Mots-clés :
Load Forecast; Big Data; Remote Terminal Units; Load forecasting; RGB Image; Energy management; Vice Versa; Energy consumption; PMU; Deep Learning; Convolutional Layers; Power grids; RGB; Sap HANA; Ml Algorithm; Provider Core Networks; Smart City; Big Data Processing; Conditional Expectation; Big Data Concept; Efficient Energy Consumption; Small MAPE; Hash Partitioning; CNN Training; SCADA System; Non-Intrusive Load Monitoring; Convolution Layer; Data Set; IoT System; Pooling Layer
