Demand Forecasting in Smart Grids

Abstract

Data analytics in smart grids can be leveraged to channel the data downpour from individual meters into knowledge valuable to electric power utilities and end‐consumers. Short‐term load forecasting (STLF) can address issues vital to a utility but it has traditionally been done mostly at system (city or country) level. In this case study, we exploit rich, multi‐year, and high‐frequency annotated data collected via a metering infrastructure to perform STLF on aggregates of power meters in a mid‐sized city. For smart meter aggregates complemented with geo‐specific weather data, we benchmark several state‐of‐the‐art forecasting algorithms, including kernel methods for nonlinear regression, seasonal and temperature‐adjusted auto‐regressive models, exponential smoothing and state‐space models. We show how STLF accuracy improves at larger meter aggregation (at feeder, substation, and system‐wide level). We provide an overview of our algorithms for load prediction and discuss system performance issues that impact real time STLF. © 2014 Alcatel‐Lucent.

A scaling law for short term load forecasting on varying levels of aggregation

“…Other work also rely on small datasets and show similar results as in [25]. In [26] the authors aggregate up to 1000 customers for one hour ahead forecasting and provide a qualitative rationale for the effect. In [27] the authors demonstrate an empirical plot of normalized root mean squared error against number of customers and show it decreases.…”

Smart grid and the prospects of electricity demand forecast in Brazilian distribution system

“…It is possible to highlight classical methodologies such as linear regression models (Regression models), Linear time seriesbased methods including the ARMA model, autoregressive integrated moving average (ARIMA) model, auto regressive moving average with external inputs (ARIMAX) model among others [15]. Also can highlight a second group, related to artificial intelligence methods that address and try to cope with the nonlinear characteristics of the historical data, for example SVM (Support Vector Machine) and NN (Neural Network) [16].…”

Monitoring Stakeholder Behaviour for Adaptive Model Generation and Simulation: A Case Study in Residential Load Forecasting

“…Literature on energy models for load forecasting is extremely rich [7], [8]. Most studies adopt a top-down approach in modelling energy consumers to forecast demand on the basis of aggregated load level.…”