Application of time-series and Artificial Neural Network models in short term load forecasting for scheduling of storage devices

Ahmed, Kazi Main Uddin; Ampatzis, M.; Nguyen, Phuong H.; Kling, W.L.

doi:10.1109/upec.2014.6934761

Cited by 16 publications

(19 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The time‐series modelling considering ARIMA and multiplicative decomposition for STLF was described in [9]. In the presence of big dataset, an ANN‐based STLF scheme is employed in [10]. An exponential smoothing model is used in [11] for MTLF in the presence of demand response programs.…”

Section: Literature Reviewmentioning

confidence: 99%

Genetic algorithm‐based non‐linear auto‐regressive with exogenous inputs neural network short‐term and medium‐term uncertainty modelling and prediction for electrical load and wind speed

Jawad

Ali

Khan

et al. 2018

J. eng.

View full text Add to dashboard Cite

Section: Literature Reviewmentioning

confidence: 99%

Genetic algorithm‐based non‐linear auto‐regressive with exogenous inputs neural network short‐term and medium‐term uncertainty modelling and prediction for electrical load and wind speed

Jawad

Ali

Khan

et al. 2018

J. eng.

View full text Add to dashboard Cite

“…Sedangkan data per bulan dari tahun 2011 sampai dengan 2016 sebagai dasar dalam menentukan formula perhitungan. Batas kewajaran persentase MAPE sebesar 10% [15], [16], [17].…”

Section: Kataunclassified

Penentuan Target Pajak Kendaraan Bermotor Di Provinsi Bali Menggunakan ARIMA Dan Algoritma Genetik

Widhura¹,

Sudarma²,

Hartati³

2018

JTE

View full text Add to dashboard Cite

Bali Regional Income Board is a regional organization tasked with determining the amount of local tax revenue target for the next fiscal year. Currently still done manually in accordance with existing upgrading trends from previous years. So it needs to be done in way that can be measured and accurate forecasting. In recent studies, it shows that forecasting by combining conventional and artificial intelligence (hybrid) methods results in better forecasting accuracy. By that reason, the writer tries to forecast the target of revenue from Motor Vehicle Tax (PKB and BBNKB), which contribute 70% to Bali Province income by combining ARIMA method and Genetic Algorithm. The data used consisted of five groups: yearly and new Vehicles that have linear data types, and as Reverse Names, Entrance Mutations and Output Mutations that have non-linear data types. Each data group consisted of PKB and BBNKB, where it’s monthly realization data from 2011 to 2016 used to be training data and realization data for 2017 as test data. The Combined forecasting mechanism is performed using ARIMA to forecast linear data and using Genetic Algorithms for non-linear data. As a benchmark for combined forecasting using ARIMA and Genetic Algorithms, forecasting using ARIMA and Genetic Algorithms independently is used for all data types (linear and nonlinear). Testing is done by comparing data of forecasting result with that 3 different methods for year 2017 with data realization year 2017. Then the error percentage is counted using MAPE. From the test results obtained for ARIMA MAPE value of 3.63, Genetic Algorithm 4.72 and combined ARIMA and Genetic Algorithm of 1.13. Thus, the result of forecasting with combination ARIMA and Genetic Algorithm have the best result and then used to forecasting target of PKB for 2018 and so on

show abstract

“…The time series modeling is explained in terms of ARIMA and multiple analyses for SOTLF [50]. In the presence of a large data set, an artificial neural network (ANN)-based SOTLF model is used in [51,52]. In [53,54], an ANN-based Levenberg-Marquardt (LM) backpropagation (BP) algorithm for SOTLF and METLF is used.…”

Section: Introductionmentioning

confidence: 99%

A Deep Learning Method for Short-Term Dynamic Positioning Load Forecasting in Maritime Microgrids

Mehrzadi

Terriche

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

The dynamic positioning (DP) system is a progressive technology, which is used in marine vessels and maritime structures. To keep the ship position from displacement in operation mode, its thrusters are used automatically to control and stabilize the position and heading of vessels. Hence, the DP load forecasting is already an essential part of DP vessels, which the DP power demand from the power management system (PMS) for thrusting depends on weather conditions. Furthermore, the PMS is used to control power generation, and prevent power failure, limitation. To perform station keeping of vessels by DPS in environmental changes such as wind, waves, capacity, and reliability of the power generators. Hence, a lack of power may lead to lower DP performance, loss of power, and position, which is called shutdown. Therefore, precise DP power demand prediction for maintaining the vessel position can provide the PMS with sufficient information for better performance in a complex decision-making process for the DP vessel. In this paper, the concept of deep learning techniques is introduced into DPS for DP load forecasting. A Levenberg–Marquardt algorithm based on a nonlinear recurrent neural network is employed in this paper for predicting thrusters’ power consumption in sea state variations due to challenges in power generation with the relative degree of accuracy by combining weather parameter dependencies as environmental disturbances. The proposed method evaluates with three traditional forecasting methods through a set of practical real-time DP load and weather parametric data. Numerical analysis has shown that with the proposed method, the future DP load behavior can be predicted more accurately than that obtained from the traditional methods, which greatly assists in operation and planning of power system to maintain system stability, security, reliability, and economics.

show abstract

Application of time-series and Artificial Neural Network models in short term load forecasting for scheduling of storage devices

Cited by 16 publications

References 12 publications

Genetic algorithm‐based non‐linear auto‐regressive with exogenous inputs neural network short‐term and medium‐term uncertainty modelling and prediction for electrical load and wind speed

Genetic algorithm‐based non‐linear auto‐regressive with exogenous inputs neural network short‐term and medium‐term uncertainty modelling and prediction for electrical load and wind speed

Penentuan Target Pajak Kendaraan Bermotor Di Provinsi Bali Menggunakan ARIMA Dan Algoritma Genetik

A Deep Learning Method for Short-Term Dynamic Positioning Load Forecasting in Maritime Microgrids

Contact Info

Product

Resources

About