Power quality challenges and urban microgrid based grid resiliency: Case of Niamey City electrical grid

In general cases, the weakness of the national electric grid is due to overloading, infrastructures aging, high temperatures, bad weather and cyber risks. In such systems, the interruptions of electricity supply can take several hours to days. The smartness of the Modern electrical networks and the using of grid-tied microgrids are an important means to improve their resilience. But, to perform strong and powerful resiliency of the grid, it is necessary to develop strong background and experiences of the weakness analyzing and detection. The development of real time analyzing tools based on deep learning and data science can help for more security and savings of the power supply. In this paper, a methodology of grid weakness analyzing is presented. It is based on long term real data collected, more than ten years, from the electrical company of Niger (Nigelec). The IEEE Std 1366 (TM)-2012 indexes and the statistical based methodology called "Beta Method" are applied to the data to identify the outlying performance of the utility. Then, the interest of the Deep learning for real-time weakness analysis and resiliency improving is introduced. Also, thanks to the laboratory experimental tests, a methodological approach of the training algorithm criteria and decision laws estimation is presented. These tests consider the main defaults that can induce a loss of power supply and the grid disconnection. The data driven models, based on informational and analytical methods, are necessary for real time assessment and improving of the grid resiliency.