## 1. Introduction

Driven by the need for cheap, sustainable, and clean sources of energy, renewable energy resources (RES), in particular wind and solar energies are being deployed increasingly across many countries [

1]. High penetration of wind and solar energies poses some operational challenges, affecting system stability, reliability, and economics [

2]. These challenges can be categorized into two main groups: (i) those associated with the decrease of system inertia [

3]; and (ii) those associated with the intrinsic variability and uncertainty of RES [

4]. In particular, island grids and microgrids, where RES penetration tends to be high, are more prone to negative impacts of RES variability and low system inertia [

5]. In view of these challenges, numerous techniques have been proposed in the literature to alleviate the impact of high RES penetration. These include methods pertaining to enhancing the prediction accuracy of RES [

6,

7,

8] and techniques pertaining to the use of energy storage systems (ESS) [

9,

10], in particular battery energy storage systems (BESS) [

11].

RES prediction techniques are categorized into three major methods [

12]: (i) numerical weather prediction (NWP) models [

13]; (ii) data-driven approaches [

6]; and (iii) hybrid physical and statistical models [

14]. NWP models are based on atmospheric science, utilizing differential equations derived from physical laws, in particular the first law of thermodynamics [

15]. These are difficult to construct and are usually used for long-time forecasting, as they exhibit a poor performance for short-term prediction. In addition, NWP models need both meteorological and topological information which adds to the complexity of their operation. On the other hand, statistical models ingest historical data to predict future RES output typically for short time-intervals ahead. Statistical techniques can be mainly categorized into linear and nonlinear methods. Amongst the linear models, autoregressive integrated moving average models (ARIMA) [

16], Kalman Filter [

17], and support vector machines (SVM) [

18] are the most popular techniques. Nonlinear models include neural network approaches such as multi-layer perceptrons and recurrent neural networks [

19,

20,

21]. Finally, hybrid models include approaches that use NWP-based predictions as part of the input for statistical techniques [

22].

ESS have two main applications in renewable-penetrated grids and microgrids: (i) to enhance system dynamic performance [

11,

23]; and (ii) to shift the RES output to reduce energy cost and emissions [

24]. The latter application is the focus of this paper. For example, a multi-pass dynamic programming technique is proposed in [

25] for optimal dispatch of BESS in a utility-scale grid. A linear programming model is formulated in [

26] for peak net load management and demand charge minimization in a grid-connected PhotoVoltaic (PV)-BESS hybrid.

A price-based method is introduced in [

27] to calculate the optimal dispatch of ESS considering short-term power exchange and expected imbalance penalties of a wind farm in a utility-scale grid. A cooperative stochastic optimal energy scheduling technique is discussed for a grid of microgrids in Chapter 9 of [

28]; the method is based on the probability distribution of RES forecasting error and is shown to yield superior results compared to centralized techniques. These methods, along with numerous other techniques discussed in the literature, demonstrate the positive impact of ESS on economics of renewable-penetrated grids. However, BESS high investment cost and mediocre life cycle remain a major concern for grid operators, highlighting the significance of proper power and energy sizing [

29].

Several techniques have been proposed in the literature for BESS sizing for a variety of applications [

30]. These can be generally classified into three main categories: (i) analytical methods [

31,

32]; (ii) linear programming methods [

33,

34]; and (iii) nonlinear heuristic methods [

35,

36]. Analytical methods perform a series of simulations on varying variables of interest, in this case BESS power and energy capacity, to calculate the key performance metrics. The variables that yield highest performance metrics are selected as optimal. Analytical methods are usually amongst the most effective techniques given their flexibility for performance criteria and operational constraints. However, these methods can be computationally intensive depending on the number of simulations and time resolution [

30]. Linear programming optimization methods formulate an explicit objective function intended to maximize the performance metrics. While these methods are computationally efficient and relatively easy to solve, they cannot account for nonlinear elements of BESS sizing problem, such as cycling aging. Finally, nonlinear heuristics methods can account for nonlinear constraints of optimization; however, they may converge to non-optimal or locally optimal solutions. On top of the aforementioned method-specific drawbacks, all of these methods suffer from the trade-off between time resolution and results accuracy. This issue will be further discussed in

Section 4.

Considering the aforementioned discussion, this paper aims to reveal the potential to improve the economics of renewable-penetrated grids through mitigation of RES variability, particularly in the context of energy scheduling. Thus, the City of Summerside data from 2016 to 2018 is leveraged to reveal the significant potential for reducing energy cost in such systems. Located in Prince Edward Island (PEI), Canada, Summerside is the second largest city in the province and operates the only municipally-owned electric utility in PEI with a peak load of 28 MW [

37]. Prior to 2009, the city imported dominant portion of electrical energy from NB Power, with the rest being supplied by local diesel generators. Since 2009, the city has installed 12 MW of wind turbine capacity, introducing Canada’s first municipally owned and operated wind farm [

37]. Thus, in 2017, around 25% of the 137.5 TWh electrical demand was met by the wind farm; the rest was mostly imported from NB Power.

Summerside Electric imports energy from NB power in hourly intervals and the power must be scheduled 20 min ahead for the next interval. Thus, the city pays a commitment rate for the scheduled power. However, the intra-interval surplus of power is exported to NB power at a real-time rate lower than the commitment rate, and the deficit is imported at a rate much higher than the commitment rate. As a result, the accuracy of scheduled import plays a significant role in the overall price of imported power from NB power. With a wind power penetration as high as 100%, wind variations have a significant impact on the Summerside Electric power exchange with NB power. Thus, in 2018, Summerside Electric signed a memorandum of understanding (MOU) with BluWave-ai to enhance the energy import scheduling and control.

The work presented here shares some findings of the collaboration between BluWave-ai and Summerside Electric, and also proposes a novel data-driven approach for BESS sizing for energy scheduling applications. The discussion, methods, and findings presented in this paper are twofold. First, actual data is leveraged to demonstrate the effectiveness of state-of-the-art time series energy predictors in mitigating energy scheduling inaccuracies. Second, the outcome of the time series prediction analysis is used to propose a novel BESS sizing study for energy scheduling purposes. Considering the aforementioned drawbacks of current BESS sizing approaches, the proposed probabilistic method accounts for intra-interval variations of generation and demand, thus mitigating the trade-off between time resolution and accuracy. In addition, as part of the sizing study, a BESS management strategy to minimize energy scheduling inaccuracies is proposed, and is then used to obtain the optimal BESS size. The paper also presents quantitative analyses of the impact of both the energy predictors and the BESS on the supplied energy cost using actual data of the Summerside Electric grid. Thus, the paper contributions are as follows:

Leveraging a relatively large island grid’s actual data to reveal the potential of state-of-the-art time series prediction techniques, in particular for wind energy. Note that, due to commercial IP confidentiality, the details of the prediction engine cannot be revealed; however, general procedures for enhancing RES prediction accuracy is discussed using actual data.

Proposing a data-driven approach toward BESS sizing for energy balancing purposes. Using actual data, a novel probabilistic approach is proposed that accounts for intra-interval variations, thus enhancing the accuracy of BESS sizing. In general, the proposed method mitigates the trade-off between time resolution and accuracy; as a result, increasing the computation time-interval would have a less significant negative impact on accuracy of the results. Hence, such a method would also alleviate computational burden of analytical methods for BESS sizing. To the knowledge of the author, this is the first time such an approach is proposed in the literature.

Proposing an optimal BESS energy management based on the presented data-driven approach.

Quantitative analysis of wind-BESS impact on energy cost using a large amount of actual data.

The rest of this paper is as follows:

Section 2 introduces Summerside Electric grid and provides some operation details.

Section 3 presents the procedure and results for wind prediction improvement using artificial intelligence (AI) prediction techniques. Note that, as part of the MoU, BluWave-ai has also developed load predictors for Summerside Electric. However, for the sake of brevity, the results of load predictors are only briefly mentioned in

Section 3.

Section 4 proposes a data-driven BESS sizing method for Summerside grid and similar systems.

Section 5 analyzes the economics of wind-BESS integration into island grids and microgrids.

Section 6 provides brief conclusions and future work.