Fast Prediction for Sparse Time Series: Demand Forecast of EV Charging Stations for Cell Phone Applications

Abstract

This paper proposes a new cellphone application algorithm which has been implemented for the prediction of energy consumption at electric vehicle (EV) charging stations at the University of California, Los Angeles (UCLA). For this interactive user application, the total time for accessing the database, processing the data, and making the prediction needs to be within a few seconds. We first analyze three relatively fast machine learning-based time series prediction algorithms and find that the nearest neighbor (NN) algorithm (k NN with k = 1) shows better accuracy. Considering the sparseness of the time series of the charging records, we then discuss the new algorithm based on the new proposed time-weighted dot product (TWDP) dissimilarity measure to improve the accuracy and processing time. Two applications have been designed on top of the proposed prediction algorithm: one predicts the expected available energy at the outlet and the other one predicts the expected charging finishing time. The total time, including accessing the database, data processing, and prediction is approximately 1 s for both applications. The granularity of the prediction is 1 h and the horizon is 24 h; data have been collected from 20 EV charging outlets.

Online Charging Scheduling Algorithms of Electric Vehicles in Smart Grid: An Overview

“…For the EV charging problem, EV charging profiles can be predicted based on the past data collected and reservations made by the EV users in advance. In general, statistical-modeling based algorithms are often applied for data prediction, e.g., artificial neural network (ANN), EV user classification, and other Machine Learning (ML)-based methods [8]. By incorporating the near future estimation, online algorithms could be designed to neglect some unrealistic worst cases and improve performance based on the partially-known future.…”

“…It is therefore important to incorporate the acquisition of data knowledge in the design of online scheduling algorithm. A promising solution is to use online/stochastic learning methods to exploit the random data to assist the decisions of EV scheduling in an iterative manner [7] [8]. In this case, however, the learning algorithm efficiency is of paramount importance, as the EV data size could be enormous and the charging scheduling is a delaysensitive application.…”

Forecasting the EV charging load based on customer profile or station measurement?

“…These algorithms are some of commonly used machine learning algorithms in different disciplines [24]. They are selected based on [25] to compare the prediction process between two types of datasets (charging record and station record).…”

Machine learning and statistical models for predicting indoor air quality

“…Time series forecasting is based on continuous or repeated measurements and is frequently used for signal detection and estimation, which has been addressed in several review papers [32][33][34] and applied in different fields including energy 35,36 and electric vehicles. 37 In indoor environments, although some models have been applied to predict IAQ, studies on the depth and breadth of the applications and on the state of the art of statistical predictions of IAQ are lacking.…”