A Novel Load Forecasting Model for Automatic Fault Clearance in Secondary Distribution Electric Power Grid using an Extended-Multivariate Nonlinear Regression

Smart grid is an emerging platform adopted by many electric power utility companies to enhance proper service delivery as well as cost-effective operations. Automatic Fault Detection and Clearance (AFDC) is a part of intelligent technology initiatives established on Tanzania’s grid aiming at detecting, managing, and handling fault with little or without human intervention. Being one of the components of AFDC, the Load Forecasting agency plays important role in feeding restoration and distributed energy resource agencies. Forecasting load demand profile in the AFDC requires a robust mechanism for accommodating both fault-based and random-walk situations. Unfortunately, existing LF mechanisms do not address these two issues robustly. Therefore, this research work aims to propose an AFDC-based LF (LF-AFDC) model whose time series data is characterized by random-walk distribution. Firstly, we establish design requirements using focus group discussion and literature review. Secondly, iterative validation is conducted to assess the suitability of the proposed LF mechanism in the intended context. Thirdly, the core forecasting part of the mechanism is achieved using the extended Multivariate Nonlinear Regression (e-MNLR) model. Findings indicate the capability of the proposed model to forecast the next load profile from the given fault-date, fault-time, restoration duration, Gross-Domestic Product (GDP), number of customers, and population information. Furthermore, the designed e-MNLR seems to outperform the ANN, SVM, LSTM, and MNLR models.