scholarly journals Improving Load Forecasting of Electric Vehicle Charging Stations Through Missing Data Imputation

Energies ◽  
2020 ◽  
Vol 13 (18) ◽  
pp. 4893
Author(s):  
Byungsung Lee ◽  
Haesung Lee ◽  
Hyun Ahn
Keyword(s):  
Power System ◽  
Load Forecasting ◽  
Imputation Method ◽  
Forecasting Model ◽  
System Operation ◽  
Power System Operation ◽  
Forecasting Accuracy ◽  
Electric Vehicle Charging ◽  
Ev Charging ◽  
Imputation Approach

As the penetration of electric vehicles (EVs) accelerates according to eco-friendly policies, the impact of electric vehicle charging demand on a power distribution network is becoming significant for reliable power system operation. In this regard, accurate power demand or load forecasting is of great help not only for unit commitment problem considering demand response but also for long-term power system operation and planning. In this paper, we present a forecasting model of EV charging station load based on long short-term memory (LSTM). Besides, to improve the forecasting accuracy, we devise an imputation method for handling missing values in EV charging data. For the verification of the forecasting model and our imputation approach, performance comparison with several imputation techniques is conducted. The experimental results show that our imputation approach achieves significant improvements in forecasting accuracy on data with a high missing rate. In particular, compared to a strategy without applying imputation, the proposed imputation method results in reduced forecasting errors of up to 9.8%.

Study on Power Load Forecasting Method Based on Ant Colony Optimization

2014 ◽  
Vol 543-547 ◽  
pp. 733-736
Author(s):  
Yan Yi Fu ◽  
Li Xu
Keyword(s):  
Power System ◽  
Load Forecasting ◽  
Forecast Model ◽  
Electric Load ◽  
System Operation ◽  
Power System Operation ◽  
Combination Forecast ◽  
Power Load ◽  
Forecasting Method ◽  
Scientific Prediction

Load forecasting is one of the important working of the power system, which plays a very significant role in various departments of power system operation. Load accurate scientific prediction can make power decision-making departments economically and reasonably to adjust generator, power line, which makes it more reasonable. This paper introduces the optimal combination forecast model, and organically combine with several electric load forecasting models by the weight, come to more accurate results, with higher prediction accuracy, and the relative error is small, it has some practical value.

scholarly journals Integrating Electric Vehicles into Power System Operation Production Cost Models

2021 ◽  
Vol 12 (4) ◽  
pp. 263
Author(s):  
Jose David Alvarez Guerrero ◽  
Bikash Bhattarai ◽  
Rajendra Shrestha ◽  
Thomas L. Acker ◽  
Rafael Castro
Keyword(s):  
Power System ◽  
Electric Vehicles ◽  
Production Cost ◽  
Peak Load ◽  
System Operation ◽  
Power System Operation ◽  
Power System Operations ◽  
Battery Capacity ◽  
Coordinated Charging ◽  
Ev Charging

The electrification of the transportation sector will increase the demand for electric power, potentially impacting the peak load and power system operations. A change such as this will be multifaceted. A power system production cost model (PCM) is a useful tool with which to analyze one of these facets, the operation of the power system. A PCM is a computer simulation that mimics power system operation, i.e., unit commitment, economic dispatch, reserves, etc. To understand how electric vehicles (EVs) will affect power system operation, it is necessary to create models that describe how EVs interact with power system operations that are suitable for use in a PCM. In this work, EV charging data from the EV Project, reported by the Idaho National Laboratory, were used to create scalable, statistical models of EV charging load profiles suitable for incorporation into a PCM. Models of EV loads were created for uncoordinated and coordinated charging. Uncoordinated charging load represents the load resulting from EV owners that charge at times of their choosing. To create an uncoordinated charging load profile, the parameters of importance are the number of vehicles, charger type, battery capacity, availability for charging, and battery beginning and ending states of charge. Coordinated charging is where EVs are charged via an “aggregator” that interacts with a power system operator to schedule EV charging at times that either minimize system operating costs, decrease EV charging costs, or both, while meeting the daily EV charging requirements subject to the EV owners’ charging constraints. Beta distributions were found to be the most appropriate distribution for statistically modeling the initial and final state of charge (SoC) of vehicles in an EV fleet. A Monte Carlo technique was implemented by sampling the charging parameters of importance to create an uncoordinated charging load time series. Coordinated charging was modeled as a controllable load within the PCM to represent the influence of the EV fleet on the system’s electricity price. The charging models were integrated as EV loads in a simple 5-bus system to demonstrate their usefulness. Polaris Systems Optimization’s PCM power system optimizer (PSO) was employed to show the effect of the EVs on one day of operation in the 5-bus power system, yielding interesting and valid results and showing the effectiveness of the charging models.

Issues for Power System Operation for Future Renewable Energy Penetration

2011 ◽  
Vol 131 (8) ◽  
pp. 670-676 ◽  
Author(s):  
Naoto Yorino ◽  
Yutaka Sasaki ◽  
Shoki Fujita ◽  
Yoshifumi Zoka ◽  
Yoshiharu Okumoto
Keyword(s):  
Renewable Energy ◽  
Power System ◽  
System Operation ◽  
Power System Operation

scholarly journals Load forecasting of refrigerated display cabinet based on CEEMD–IPSO–LSTM combined model

Open Physics ◽  
2021 ◽  
Vol 19 (1) ◽  
pp. 360-374
Author(s):  
Yuan Pei ◽  
Lei Zhenglin ◽  
Zeng Qinghui ◽  
Wu Yixiao ◽  
Lu Yanli ◽  
...  
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Time Series Data ◽  
Load Forecasting ◽  
Series Data ◽  
Forecasting Model ◽  
Combined Model ◽  
Forecasting Accuracy ◽  
Forecasting Method ◽  
Consumption Reduction

Abstract The load of the showcase is a nonlinear and unstable time series data, and the traditional forecasting method is not applicable. Deep learning algorithms are introduced to predict the load of the showcase. Based on the CEEMD–IPSO–LSTM combination algorithm, this paper builds a refrigerated display cabinet load forecasting model. Compared with the forecast results of other models, it finally proves that the CEEMD–IPSO–LSTM model has the highest load forecasting accuracy, and the model’s determination coefficient is 0.9105, which is obviously excellent. Compared with other models, the model constructed in this paper can predict the load of showcases, which can provide a reference for energy saving and consumption reduction of display cabinet.

Advanced teaching method for learning power system operation based on load flow simulations

2021 ◽  
Author(s):  
Andrés Honrubia‐Escribano ◽  
Raquel Villena‐Ruiz ◽  
Estefanía Artigao ◽  
Emilio Gómez‐Lázaro ◽  
Ana Morales
Keyword(s):  
Power System ◽  
Teaching Method ◽  
Load Flow ◽  
System Operation ◽  
Power System Operation ◽  
Flow Simulations ◽  
Advanced Teaching

scholarly journals Architectural and functional classification of smart grid solutions

2019 ◽  
Vol 2 (S1) ◽  
Author(s):  
Friederike Wenderoth ◽  
Elisabeth Drayer ◽  
Robert Schmoll ◽  
Michael Niedermeier ◽  
Martin Braun
Keyword(s):  
Smart Grid ◽  
Power Systems ◽  
Power System ◽  
Power Distribution ◽  
Hierarchical Architecture ◽  
Distribution Grid ◽  
Active System ◽  
System Operation ◽  
Power System Operation

Abstract Historically, the power distribution grid was a passive system with limited control capabilities. Due to its increasing digitalization, this paradigm has shifted: the passive architecture of the power system itself, which includes cables, lines, and transformers, is extended by a communication infrastructure to become an active distribution grid. This transformation to an active system results from control capabilities that combine the communication and the physical components of the grid. It aims at optimizing, securing, enhancing, or facilitating the power system operation. The combination of power system, communication, and control capabilities is also referred to as a “smart grid”. A multitude of different architectures exist to realize such integrated systems. They are often labeled with descriptive terms such as “distributed,” “decentralized,” “local,” or “central." However, the actual meaning of these terms varies considerably within the research community.This paper illustrates the conflicting uses of prominent classification terms for the description of smart grid architectures. One source of this inconsistency is that the development of such interconnected systems is not only in the hands of classic power engineering but requires input from neighboring research disciplines such as control theory and automation, information and telecommunication technology, and electronics. This impedes a clear classification of smart grid solutions. Furthermore, this paper proposes a set of well-defined operation architectures specialized for use in power systems. Based on these architectures, this paper defines clear classifiers for the assessment of smart grid solutions. This allows the structural classification and comparison between different smart grid solutions and promotes a mutual understanding between the research disciplines. This paper presents revised parts of Chapters 4.2 and 5.2 of the dissertation of Drayer (Resilient Operation of Distribution Grids with Distributed-Hierarchical Architecture. Energy Management and Power System Operation, vol. 6, 2018).

Sign in / Sign up

Export Citation Format

Share Document