Battery energy storage system load shifting control based on real time load forecast and dynamic programming

Bao, Guangqing; Lü, Chao; Yuan, Zhaohui; Lu, Zongxiang

doi:10.1109/coase.2012.6386377

Cited by 47 publications

(20 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In case of mixed integer optimization problems for the BESS's operation, some solving procedures have been proposed in the literature based on dynamic programming (DP) [9,19,20]. However, DP handles discrete variables, thus requiring a discretization so that it also can deal with continuous variables (e.g., the battery's charge level); obviously, the required computational time increases when the discretization is thinner.…”

Section: A Day-ahead Schedulingmentioning

confidence: 99%

Demand response and energy storage systems: An industrial application for reducing electricity costs. Part I: Theoretical aspects

Carpinelli

Khormali

Mottola

et al. 2014

2014 International Symposium on Power Electronics, Electrical Drives, Automation and Motion

View full text Add to dashboard Cite

In this paper, the benefits that can be derived from the installation of an energy storage system in an industrial facility are analyzed, and an optimal control strategy of the storage system is proposed. The proposed control strategy is based on a two-step procedure and aims at (i) reducing the electricity costs sustained by an industrial customer that provides demand response and (ii) satisfying technical constraints for the maximization of the efficiency and lifecycle of the storage system. The procedure was performed based on two different time periods, i.e., day ahead and very short time. The day-ahead scheduling evaluates the peak value of the power that the facility must request from the grid and the periods in which the battery is allowed to charge and discharge; the very short-time control evaluates the battery's charging/discharging power to minimize costs. This paper reports the theoretical aspects of the optimization models for the two-step procedure, whereas the companion paper "Part II: numerical applications" proposes the results of numerical applications of the proposed approach on an actual industrial facility.

show abstract

Section: A Day-ahead Schedulingmentioning

confidence: 99%

Demand response and energy storage systems: An industrial application for reducing electricity costs. Part I: Theoretical aspects

Carpinelli

Khormali

Mottola

et al. 2014

2014 International Symposium on Power Electronics, Electrical Drives, Automation and Motion

View full text Add to dashboard Cite

show abstract

“…The authors in [15] solve a similar problem to peak demand with a BESS by using a mixture of regression methods for load profile forecasting and dynamic programming (DP) for optimal action selection, where action refers to buying and storing energy. Although the results of this paper are impressive, there are many limitations which arise from their solution framework for this task.…”

Section: Introductionmentioning

confidence: 99%

“…In addition, the DP algorithm described within requires discretization of the battery capacity, thereby prohibiting a fully flexible, continuous energy storage system. Decreasing the time step interval and capacity discretization provides additional fine-grained control, but as DP grows polynomial in the problem size this quickly becomes computationally intractable [15], thereby restricting the flexibility of this solution methods. Finally, DP requires an explicit objective function for optimization, and as discussed previously, this is not available for our task as we are not interested in solely peak shifting, but also in energy consumption and utility bill reduction.…”

Section: Introductionmentioning

confidence: 99%

Optimal Peak Shifting of a Microgrid Load Based on Deep Q-Learning Network

Al‐Gabalawy

Hosny

2020

Preprint

View full text Add to dashboard Cite

Abstract Background: Peak periods are a result of consumers generally using electricity at similar times and periods as each other, for example, turning lights on when returning home from work, or the widespread use of air conditioners during the summer. Without peak shifting, the grid’s system operators are forced to use peaked plants to provide the additional energy, the operation of which is incredibly expensive and dangerous to the environment due to their high levels of carbon emissions.Methods: Battery storage system (BSS) has been used to allow for the purchase the energy during oﬀ-peak periods for later use, with the primary objective of achieving peak shifting, is explored. In addition, reduction in energy consumption and the lowering of consumer’s utility bills are also sought, making this a multi-objective optimization problem. Reinforcement learning methods are implemented to provide a solution to this problem by finding an optimal control policy which defines when is best to purchase and store energy with the objectives in mind.Results: This achieves over a 20% reduction in energy consumption and consumers’ energy bills, as well as achieving perfect peak shifting, thereby removing peaking plants from the equation entirely. This result was obtained using a simulator that the author has developed specifically for this task, which handles the model training, testing, and evaluation process. Secondly, the development of a novel technique, automatic penalty shaping, was also found to be crucial to the success of the learned model. This technique enabled the automatic shaping of the reward signal, forcing the agent to pay equal attention to multiple individual signals, a necessity when applying reinforcement learning to multi-objective optimization problems. The policy does, however, attempt to overcharge the battery about 7% of the time, and promising methods to address this has been proposed as a direction for future research.Conclusion: The aim of this task was to verify that reinforcement learning is a suitable solution method to the peak demand problem. That is, can reinforcement learning be used in conjunction with a BSS to purchase energy at oﬀ-peak periods, in order to ﬂatten the energy requirement profile of consumers. Such an achievement would prevent the grid’s system operators from needing to use peaked plants to provide additional energy during peak periods, lowering carbon emissions and energy prices for the consumer. This peak-shifting would allow the grid’s system operators to be able to more easily predict electricity demand, thereby reducing their need to generate more energy than necessary, again lowering the tariﬀs for energy for the consumer. Secondary aims of directly reducing the energy consumption and utility bills were also sought, making this a multi-objective optimization problem. The used data, in conjunction with the created simulator which performs the full training and testing phases of the models, to find an optimal policy using the deep Q-network (DQN) and Proximal Policy Optimization (PPO) reinforcement learning algorithms. Finally, the proposed algorithm is able to achieve perfect peak shifting, a reduction in the monthly utility bill by 21% and also a reduction in energy consumption by 23%, achieving all of the aims of the task.

show abstract

“…Moreover, according to reference [7], battery energy storage systems have excellent records and are used for decades in power systems, highlighting overall economic viability with focus on capital and operating cost over the Battery Electric Energy System (BESS) lifetime. Reference [8] presents a real-time control strategy of BESS, based on load forecast and dynamic programming methods upon stating that BESS load shifting performance is determined by the availability of accurate load curves and optimization approaches. Reference [5] demonstrates exemplary embodiments of ESSs which have been historically activated with a certain periodicity, for example, for power system load leveling, frequency regulation, arbitrage, peak load shaving and/or integration of renewable power generation.…”

Section: Introductionmentioning

confidence: 99%

On the estimation of an optimum size of Energy Storage System for local load shifting

Park

Knazkins

Sevilla

et al. 2015

2015 IEEE Power &Amp; Energy Society General Meeting

View full text Add to dashboard Cite

This paper presents an algorithm for determining an optimum size of Energy Storage System (ESS) via the principles of exhaustive search for the purpose of local-level load shifting including peak shaving (PS) and load leveling (LL) operations in the electric power system. An exhaustive search method is employed to perform the ESS capacity (QESS) and power (PESS) optimization. The sizing process involves two distinct steps. In the first step the search for a feasible ESS parameter space in which the requirements of PS and LL are fulfilled and in the second step the search for an optimum point in the feasible space with respect to the cost benefit. Finally, the search is expanded to find a set of storage capacity, QESS and peak power limits, P limit 's for each month, in order to perform the load shifting throughout a one year. To validate the ESS size optimization, an appropriate model is created for time-domain simulations. The model consists of variable load, a simple state-space ESS model and a rule-based controller which operates the ESS using a set of rules. A number of time-domain simulations were performed to validate the correctness of the ESS size optimization. It appears that the proposed optimization algorithm produces results that meet the requirements in the peak shaving and load leveling operations.Index Terms-Energy Storage Systems, planning for storage, rule-based controller, power system analysis, load shifting.

show abstract

Battery energy storage system load shifting control based on real time load forecast and dynamic programming

Cited by 47 publications

References 13 publications

Demand response and energy storage systems: An industrial application for reducing electricity costs. Part I: Theoretical aspects

Demand response and energy storage systems: An industrial application for reducing electricity costs. Part I: Theoretical aspects

Optimal Peak Shifting of a Microgrid Load Based on Deep Q-Learning Network

On the estimation of an optimum size of Energy Storage System for local load shifting

Contact Info

Product

Resources

About