Rolling-horizon optimization integrated with recurrent neural network-driven forecasting for residential battery energy storage operations

Abedi, Sara; Kwon, Soongeol

doi:10.1016/j.ijepes.2022.108589

Cited by 25 publications

(15 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the market demand side, the domestic installed market is affected by many factors such as ROI, power profit, investment policy, decision preference, investment cost. Among them, the most important is the economic factor (Ma et al, 2021 ; Pierro et al, 2018 ; Soler-Castillo et al, 2021 ), the ROI composed of PV power price, government subsidies, and investment cost is the critical factor (Abedi & Kwon, 2023 ). In addition, the owner of PV power station reinvests a percentage of the profit (Guo & Guo, 2015 ), and the changed profit brought by the change of government subsidies also has an impact on the domestic installed market.…”

Section: Methodsmentioning

confidence: 99%

Can the cancellation of government subsidies alleviate the phenomenon of overcapacity in the photovoltaic module industry? From a dynamic perspective

Zhang

Zhao

Zhou

2023

Environ Dev Sustain

View full text Add to dashboard Cite

The environmental pollution problem stimulates the photovoltaic industry’s vigorous development and further promotes the prosperity of the module manufacturing industry. After the cancellation of government subsidies, how the phenomenon of overcapacity that has always existed in the module manufacturing industry will develop is one of the essential issues that we need to consider. This paper constructs a systematic framework to analyze the driving mechanism of government subsidies on overcapacity. Then, a system dynamics model is established to predict the development trend of overcapacity after the cancellation of government subsidies. The result shows that: (i) By 2030, the production capacity will exceed 600 GW in China’s photovoltaic module industry, which is about two times that of 2021. Moreover, its price and cost will drop to 0.46 yuan/W and 0.41 yuan/W, which are down 67% and 60%, respectively, compared to 2021; (ii) After the cancellation of government subsidies, the phenomenon of overcapacity will not disappear soon, and it will continue until 2030. In 2030, the production capacity utilization rate will reach 80%, and the phenomenon of overcapacity will disappear; (iii) From the perspective of production factors, the impact of the labor factor on the production capacity is minimal. In the initial stage, technology and capital factors are vital. As the industry matures, the influence of the capital factor will gradually weaken. Finally, we have put forward corresponding policy implications.

show abstract

Section: Methodsmentioning

confidence: 99%

Can the cancellation of government subsidies alleviate the phenomenon of overcapacity in the photovoltaic module industry? From a dynamic perspective

Zhang

Zhao

Zhou

2023

Environ Dev Sustain

View full text Add to dashboard Cite

show abstract

“…Rolling-horizon control is a well-established technique for tackling real-time/online control challenges in the presence of uncertainty. It has been extensively applied in the scheduling of DGs [23] and flexible loads [24]. As depicted in Fig.…”

Section: B Rolling-horizon Scheduling Of Evamentioning

confidence: 99%

Distributed Source-Load-Storage Cooperative Low-carbon Scheduling Strategy Considering Vehicle-to-grid Aggregators

Xu,

Qiu,

Zhang

et al. 2024

Journal of Modern Power Systems and Clean Energy

View full text Add to dashboard Cite

The vehicle-to-grid (V2G) technology enables the bidirectional power flow between electric vehicle (EV) batteries and the power grid, making EV-based mobile energy storage an appealing supplement to stationary energy storage systems. However, the stochastic and volatile charging behaviors pose a challenge for EV fleets to engage directly in multi-agent cooperation. To unlock the scheduling potential of EVs, this paper proposes a source−load−storage cooperative low-carbon scheduling strategy considering V2G aggregators. The uncertainty of EV charging patterns is managed through a rolling-horizon control framework, where the scheduling and control horizons are adaptively adjusted according to the availability periods of EVs. Moreover, a Minkowski-sum based aggregation method is employed to evaluate the scheduling potential of aggregated EV fleets within a given scheduling horizon. This method effectively reduces the variable dimension while preserving the charging and discharging constraints of individual EVs. Subsequently, a Nash bargaining based cooperative scheduling model involving a distribution system operator (DSO), an EV aggregator (EVA), and a load aggregator (LA) is established to maximize the social welfare and improve the low-carbon performance of the system. This model is solved by the alternating direction method of multipliers (ADMM) algorithm in a distributed manner, with privacy of participants fully preserved. The proposed strategy is proven to achieve the objective of low-carbon economic operation.

show abstract

“…The study [11] developed the rolling-horizon optimization model with a recurrent neural network-driven predicting, which is developed for interactively prediction of uncertainty and optimization of battery energy storage operations in residential smart houses in an iterative fashion. The proposed model can be used for optimizing battery energy storage operations in residential smart houses and for efficiently utilizing solar power.…”

Section: міжнародний науковий журналmentioning

confidence: 99%

Overview of the Methods and Tools for Situation Identification and Decision-Making Support in the Cyberphysical System «smart House»

Hovorushchenko¹,

ALEKSOV²,

TALAPCHUK³

et al. 2022

CSIT

View full text Add to dashboard Cite

The technology of a smart house is mostly understood as a system that combines a number of subsystems that provide comfortable living conditions for residents in the room and make it possible to significantly reduce energy costs. A house is called smart if it has a certain computer or control system for managing engineering equipment. "Smart House" should be designed so that all services can be integrated with each other with minimal costs (in terms of finances, time and effort), and their maintenance would be organized in an optimal way. The "Smart House" system should competently allocate resources, reduce operating costs and provide a clear control and management interface. Such an intelligent system should be able to recognize specific planned and emergency situations occurring in the home and respond to them (make decisions) in accordance with the given program. Therefore, today the urgent task is to recognize the situation and support decision-making in the "Smart House" cyber-physical system. The conducted overview of methods and tools for situation identification and decision-making support in the "Smart House" cyber-physical system showed that: in existing solutions, situation recognition occurs only for one of the groups of the system of managed housing functions or does not occur at all; existing solutions provide decision-making support for only one of the groups of the system of managed housing functions or do not provide it at all; the available solutions do not provide for the possibility of assessing the sufficiency of information for decision-making in the "Smart House" cyber-physical system. Therefore, there is a need to develop such methods and tools for situation identification and decision-making support in the "Smart House" cyber-physical system, which would: perform situation recognition for all 5 groups of the system of managed housing functions; provide the decision-making support for all 5 groups of the system of managed housing functions; perform an assessment of the sufficiency of information for making all decisions in the "Smart House" cyber-physical system, which will be the focus of the authors' further efforts.

show abstract

Rolling-horizon optimization integrated with recurrent neural network-driven forecasting for residential battery energy storage operations

Cited by 25 publications

References 35 publications

Can the cancellation of government subsidies alleviate the phenomenon of overcapacity in the photovoltaic module industry? From a dynamic perspective

Can the cancellation of government subsidies alleviate the phenomenon of overcapacity in the photovoltaic module industry? From a dynamic perspective

Distributed Source-Load-Storage Cooperative Low-carbon Scheduling Strategy Considering Vehicle-to-grid Aggregators

Overview of the Methods and Tools for Situation Identification and Decision-Making Support in the Cyberphysical System «smart House»

Contact Info

Product

Resources

About