Since the beginning of this century, there has been a growing body of research and developments supporting the participation of energy storage systems (ESS) in the emission reduction mandates. However, regardless of these efforts and despite the need for an accelerated energy transition, we have yet to see a practical framework for operational carbon accounting and credit trading for energy storage systems. In this context, this paper proposes an emission performance credits (EPCs) framework that allows ESS, down to the prosumer level, to participate in the carbon market. Thus, a mechanism is proposed, for the first time, to calculate the grid's real-time marginal emission intensity (MEI). The MEI is then used to optimize the cumulative operational emission of ESS through carbon-aware dispatch. Consequently, the framework tracks the operational emissions and converts them into EPCs, which are then sold to regulated entities under compliance programs. Simulation results support the potential of ESS, regardless of their size, to participate in the broader carbon mitigation objectives.

This work introduces the category of Power System Transition Planning optimization problem. It aims to shift power systems to emissions-free networks efficiently. Unlike comparable work, the framework presented here broadly applies to the industry's decision-making process. It defines a field-appropriate functional boundary focused on the economic efficiency of power systems. Namely, while imposing a wide range of planning factors in the decision space, the model maintains the structure and depth of conventional power system planning under uncertainty, which leads to a large-scale multistage stochastic programming formulation that encounters intractability in real-life cases. Thus, the framework simultaneously invokes high-performance computing defaultism. In this comprehensive exposition, we present a guideline model, comparing its scope to existing formulations, supported by a fully detailed example problem, showcasing the analytical value of the solution gained in a small test case. Then, the framework's viability for realistic applications is demonstrated by solving an extensive test case based on a realistic planning construct consistent with Alberta's power system practices for long-term planning studies. The framework resorts to Stochastic Dual Dynamic Programming as a decomposition method to achieve tractability, leveraging High-Performance Computing and parallel computation.

Forecasting load in power transmission networks is essential across various hierarchical levels, from the system level down to individual points of delivery (PoD). While intuitive and locally accurate, traditional local forecasting models (LFMs) face significant limitations, particularly in handling generalizability, overfitting, data drift, and the cold start problem. These methods also struggle with scalability, becoming computationally expensive and less efficient as the network's size and data volume grow. In contrast, global forecasting models (GFMs) offer a new approach to enhance prediction generalizability, scalability, accuracy, and robustness through globalization and cross-learning. This paper investigates global load forecasting in the presence of data drifts, highlighting the impact of different modeling techniques and data heterogeneity. We explore feature-transforming and target-transforming models, demonstrating how globalization, data heterogeneity, and data drift affect each differently. In addition, we examine the role of globalization in peak load forecasting and its potential for hierarchical forecasting. To address data heterogeneity and the balance between globality and locality, we propose separate time series clustering (TSC) methods, introducing model-based TSC for feature-transforming models and new weighted instance-based TSC for target-transforming models. Through extensive experiments on a real-world dataset of Alberta's electricity load, we demonstrate that global target-transforming models consistently outperform their local counterparts, especially when enriched with global features and clustering techniques. In contrast, global feature-transforming models face challenges in balancing local and global dynamics, often requiring TSC to manage data heterogeneity effectively.

Wholesale electricity markets are designing marketparticipation models for hybrid resources that consist of energy storage and generation. This paper investigates the strategic behavior under two commonly proposed market-participation models of a hybrid resource that consists of solar and energy storage. The first is co-located hybrid resource, wherein the solar and energy storage submit separate offers. The second is integrated hybrid resource, wherein the solar and energy storage provide a single integrated offer and the market operator treats the resource as a single unit. We employ a bi-level stochastic optimization where the upper-level determines the hybrid resource's offers, and the lower-level represents market clearing by the market operator under different uncertain operating conditions. The model is applied to a simple example and to a real-world case study that is based on Alberta's electricity system. Results demonstrate that in most cases the two market-participation models are comparable. Co-located hybrid resource yields slight hybrid-resource- and generator-profit increases and offsetting social-welfare losses compared to integrated hybrid resource.

Transmission line loss forecasting is an important power system forecasting task, yet, existing methods often overlook qualitative operational data such as scheduled outages, which directly impact network topology and losses. This paper introduces a newframework that integrates scheduled outage reports with a two-stage cluster-based refinement solution to enhance forecasting accuracy. First, we process and utilize outage data in a way that preserves its temporal and contextual relevance, using Natural Language Processing (NLP) technique. This addresses a key gap in prior works that relies solely on quantitative inputs. Next, the proposed framework employs an initial baseline model in the first stage, followed by cluster-refinement using submodels trained on grouped data patterns. The proposed framework is applied to 24 hour ahead forecasts of transmission losses on an IEEE-118 bus test system, and in Alberta, Canada.We compare the results to benchmark methods from existing state-of-the-art transmission loss forecasting models. Our findings indicate that the proposed framework offers an accurate forecasting solution, outperforming the benchmark techniques. Moreover, these results highlight the value of integrating qualitative information into forecasting models for more accurate and reliable predictions.

The lack of meteorological forecast data has increased the inaccuracy of output power forecasting in distributed photovoltaic systems. Especially, for newly built distributed sites across regions, modeling based on data-driven methods is limited by insufficient historical data. Therefore, a domain adversarial temporal network (DATN) based transfer learning (TL) framework is proposed, which contains two main modules, power temporal forecaster and domain classifier. Among them, the domain classifier considering the hidden layer weights of long short-term memory network is designed to reduce the distribution mismatch between source and target domains. The DATN employs a TL strategy of cross-domain adversarial pretraining with target-specific prediction tuning. In four cross-regional transfer experiments, the effects of domain adaptation methods and transfer strategies are compared. The breakthrough is that the transfer effect on different target data volumes is analyzed for the first time. The results prove that the proposed transferable framework DATN consistently performs best.

In this paper, we carry out behind-the-fence (BTF) generation forecasting using a new decomposition framework called batched decomposition framework. Here, BTF is framed as a particular structuring of the behind-the-meter (BTM) problem, where power is produced at generation and industrial facilities for internal loads rather than being supplied directly to the grid. BTF forecast is important for power system operators as it aids planning and decision making. This study employs a novel decomposition framework that effectively manages the non-linearity of BTF data while preventing the information leakage issues commonly found in traditional decomposition approaches. To assess the effectiveness of the proposed batched decomposition framework, we tested it on forecasting 24 hours ahead BTF for two Canadian provinces, Alberta and Quebec. The proposed method demonstrates high forecasting accuracy, comparable to the traditional decomposition method, while also avoiding information leakage and ensuring the practicability of the solution. Additionally, the results of the proposed method is benchmarked against various state of the art models using various error metrics. The batched decomposition method was shown to outperform the benchmarks for both test cases.

The identification and segmentation of responsive electricity customers have been formulated here as a binary time series clustering (TSC) problem. The assumption of a stationary environment in kernel methods can complicate the mapping of non-stationary time series data to a high-dimensional feature space, leading to a degradation in the performance of kernel K-means clustering. Hence, a similarity-based non-linear TSC is proposed to capture consumers’ reactions to demand response (DR) signals. K-means with Dynamic Time Warping (DTW) is employed as a nonlinear TSC approach, and to extend it beyond standard sample-to-centroid comparisons, a similarity matrix is suggested in place of raw time series, enabling sample-to-sample comparisons. It is based on distance and correlation matrices ensembling one-to-many and two-to-two comparisons to map original data to the similarity space. By analyzing consumption data from the Low Carbon London project, we demonstrate the effectiveness of our approach in identifying responsive consumers with different responsive levels.

This article proposes a multistage investment planning framework for the fleet transition problem, with a particular focus on the capacity of the electric fleet's aggregated battery to generate revenue for the fleet owner through self-use or third-party provision of electricity energy services. The proposed approach considers the purchase costs, salvage revenues, operational expenses, investments in charging infrastructure, and revenue opportunities derived from the electricity energy services offered by the electric fleet. An illustrative insight into potential revenue opportunities of an electric fleet for behind-the-meter and grid ancillary services is first provided. Subsequently, using a food retailer as a case study, this research evaluates how these auxiliary services can impact the dynamics of fleet transitions. This article also explores the influence of the electricity market on strategic planning and examines the optimal prioritization process between bidirectional chargers and electric commercial vehicle (ECV) investments. Lastly, we highlight how the ancillary energy services can lower the total cost of ownership (TCO) for fleet owners and accelerate the transition to electric fleets.

Electricity price spikes are the most important characteristic of the electricity price time series. Operationally, they result from various stresses in the power system or the strategic bidding behavior of market participants. These high prices are important as they represent economic opportunities in the form of profits and savings. Theoretically, price spikes are defined as prices that exceed a threshold over a typically short duration. This definition serves as the basis for several established modeling approaches in the literature. In general, the threshold component determines the design of a price spike model, often overlooking the duration aspect. Therefore, this paper presents a simple yet informative model to quantify the duration of electricity price spikes using historical price data from different market jurisdictions. We approach the problem through the lens of survival analysis, a widely used technique for evaluating time-to-event data. Specifically, we use the Kaplan–Meier (KM) estimator, which enables a nonparametric evaluation of the survival (duration) of price spikes over time. We refer to this as the price spike duration model.

This paper proposes a hybrid actor-critic framework for the optimal operation of a phase-changing soft open point (PCSOP) in an unbalanced distribution network. The framework combines algorithmic features of off-policy reinforcement learning and imitation learning. The reinforcement learning component comprises a policy-guiding module based on the PCSOP physics and an adaptive dynamic experience replay buffer. The policy-guiding module facilitates the agents navigation of the complex action space of the PCSOP. The dynamic experience replay accelerates agent training by leveraging expert demonstrations through imitation learning. As part of the design process, the paper also proposes a data-driven linearization of operational power losses in PCSOPs to enhance the convergence of nonlinear AC optimal power flow calculations without compromising accuracy. The proposed framework was trained and tested on a modified three-phase IEEE-33 bus and the multiphase IEEE-123 bus test feeders. Results demonstrate the superiority of our framework compared to three different methods, including the conventional nonlinear AC optimal power flow.

The increasing penetration of behind-the-meter (BTM) distributed energy resources (DERs) in the electricity grid will reduce the utilities’ net demand and increase customers’ profits through reduced electricity bills and compensation for excess generation via mechanisms such as net-metering credits. To recover lost revenue, distribution utilities, as asset operators—and retailers, as energy procurement entities, are often compelled to raise electricity prices. This, in turn, further incentivizes DERs adoption, potentially leading to a feedback loop of rising rates and declining demand that threatens the long-term financial sustainability of traditional utility models. In this context, there is a gap for innovative retailer business models in the era of increasing DERs. This paper focuses on identifying the dynamics underlying retail market operations and business sustainability in the era of increasing DERs. Accordingly, this paper proposes a dynamic retail market model that captures the interdependencies of market components and processes through non-linear causal relationships and feedback loops. This enables retailers to investigate their long-term business performance in prosumer-penetrated networks. Additionally, this work develops an integrated operation and planning framework for the techno-economic analysis and decision modeling of retailers, utilities, and customers in the retail market paradigm. Using the developed framework, this work further proposes two alternative retailer business models that enhance retailers’ long-term business sustainability and customers’ economic viability. Analytical studies evaluate the business models and present recommendations to ensure the financial sustainablility. The results demonstrate that the proposed subscription-based models can successfully mitigate the adverse financial effects of widespread DERs adoption and ensure long-term system stability.

The integration of wind energy into the power grid has been on the rise in recent years, with wind energy becoming an increasingly important source of electricity. However, the intermittency of wind energy output, particularly regarding the wind power ramps, can pose challenges for the power grid and its operators. Wind power ramps refer to the rate at which wind energy output increases or decreases. The first step in analyzing and modeling wind power ramp events is detecting them. This work consists of categorizing different ramp detection techniques and making a comparison between them.

In this article, we introduce emissions response, the widespread use of real-time emissions factors in electricity grids as a signal for a dynamic response to facilitate decarbonization and system efficiency. Many articles and publications have suggested dynamic approaches to addressing systemwide emissions, reducing emissions through time-sensitive consumption, and aiding in the adoption of renewable and low-emissions technologies. With emissions response, we combine, broaden, and formalize these concepts as effective means of encouraging and regulating the energy transition with benefits to grid systems at large as well as individual stakeholders in generation, consumption, and storage. We provide an overview where real-time emissions factors serve as a metric toward grid efficiency, recognizing and promoting technologies that provide long-term stability along with technologies driving decarbonization.

This paper proposes a load management platform to help industrial and commercial electricity customers assess the feasibility of demand charge management through battery aggregation of commercial and passenger Electric Vehicles (EVs). While electric fleet vehicles primarily serve logistical purposes, they can also contribute to energy services as long as these additional functions do not compromise their primary role. In this paper, as a part of the operation planning model, a new time-indexed vehicle routing formulation compatible with energy management equations is developed to allow fleet owners to simultaneously schedule their logistics and energy management systems. The operation planning model also considers the passenger EVs owned by a load entity and its staff and prepares them for energy services by handling their charge and discharge. Two illustrative case studies are employed to demonstrate the advantage of the proposed operation planning model over an available baseline. Additionally, for larger benchmarks, Column Generation and Branch-and-Price techniques is employed to decompose the large instances into smaller, more manageable problems for efficient solving.

This paper proposes a novel four-stage time aggregation method that can extract the underlying structure of years of historical renewable energy data. As opposed to the conventional time aggregation approaches, the proposed method starts with finding the best pair matches between patterns from one year to the next using Minimum Bipartite Graph Matching. The proposed method can capture the typical structure of patterns by taking into account the inter-annual relationships between observations collected from different years. The proposed method is evaluated by both data-based and model-based criteria. Regarding the former, we examine the quality of representative periods from different aspects such as the mean, standard deviation, maximum hourly ramp up/down, annual duration curve, and annual ramp duration curve. For the model-based evaluation, we consider a unit commitment problem in a modified IEEE 24-bus system consisting of an energy storage unit. We evaluate the methods in replicating the annual operational cost, wind energy curtailment, and energy throughput of energy storage. We evaluate the methods on three out-of-sample data sets to show the effectiveness of the proposed method in generalizing the clusters rather than over-fitting them to the in-sample observations.

Recent advancements in Artificial Intelligence (AI), particularly in the field of Natural Language Processing (NLP) and Large Language Models (LLMs), have opened up new avenues for processing qualitative data. This development is particularly interesting for the power system sector as it has an enormous amount of untapped qualitative data. Traditionally, decision-making in this sector have predominantly relied on quantitative data. However, qualitative data such as textual information hold untapped potential. These data can provide valuable insights and act as decision support tools in various power system tasks, including forecasting. The challenge however lies in effectively processing these qualitative data for specific tasks, such as power system forecasting. In this paper, we propose an approach to address this challenge. We perform sentiment analysis using LLMs on system operator comments from the Alberta Interconnected Electric System. The underlying idea is that these sentiments can reflect the state or ‘emotions’ of the power system network at any given moment and serve as useful signals for carrying out forecasting. We transform these sentiments into time series data and incorporate them as an additional feature for training a transmission loss forecasting model. Notably, we demonstrate that integrating NLP into transmission line loss forecasting is of value. We carried out experiments using three model classes, statistical, machine learning and deep learning. Depending on the forecasting model class and experiment type, we observe a forecast accuracy improvement of 2-3 percent across board. Overall, this research extends traditional forecasting methodologies by harnessing the power of NLP. We showcase its potential to enhance models and its practical relevance in power systems.

Power system operation and planning decisions for lithium-ion battery energy storage systems are mainly derived using their simplified linear models. While these models are computationally simple, they have limitations in how they estimate battery degradation, either using the energy throughput or the Rainflow method. This article proposes a hybrid approach for lithium-ion battery system modeling suitable for use in power system studies that enhances representation of battery degradation at a reasonable computational cost. The proposed hybrid model combines a physics-based model for improved degradation estimates with a simple and linear energy reservoir model commonly used to represent a battery storage system. The advantage of constructing the battery model with this vision is that it allows its smooth integration into the mixed-integer optimization frameworks. The proposed model is evaluated using both power- and energy-based use cases from the electrical grid. The simulations demonstrate that degradation could be reduced by 45% compared to other modeling strategies while generating the same level of operation profits. The net result of using the proposed hybrid model could be an extended lifespan through better informed planning and operating decisions for energy storage assets.

Various faults can occur during the operation of PV arrays, and both the dust-affected operating conditions and various diode configurations make the faults more complicated. However, current methods for fault diagnosis based on I-V characteristic curves only utilize partial feature information and often rely on calibrating the field characteristic curves to standard test conditions (STC). It is difficult to apply it in practice and to accurately identify multiple complex faults with similarities in different blocking diodes configurations of PV arrays under the influence of dust. Therefore, a novel fault diagnosis method for PV arrays considering dust impact is proposed. In the preprocessing stage, the Isc-Voc normalized Gramian angular difference field (GADF) method is presented, which normalizes and transforms the resampled PV array characteristic curves from the field including I-V and P-V to obtain the transformed graphical feature matrices. Then, in the fault diagnosis stage, the model of convolutional neural network (CNN) with convolutional block attention modules (CBAM) is designed to extract fault differentiation information from the transformed graphical matrices containing full feature information and to classify faults. And different graphical feature transformation methods are compared through simulation cases, and different CNN-based classification methods are also analyzed. The results indicate that the developed method for PV arrays with different blocking diodes configurations under various operating conditions has high fault diagnosis accuracy and reliability.

This research proposes an investigative experiment employing binary classification for short-term electricity price spike forecasting. Numerical definitions for price spikes are derived from economic and statistical thresholds. The predictive task employs two tree-based machine learning classifiers and a deterministic point forecaster; a statistical regression model. Hyperparameters for the tree-based classifiers are optimized for statistical performance based on recall, precision, and F1-score. The deterministic forecaster is adapted from the literature on electricity price forecasting for the classification task. Additionally, one tree-based model prioritizes interpretability, generating decision rules that are subsequently utilized to produce price spike forecasts. For all models, we evaluate the final statistical and economic predictive performance. The interpretable model is analyzed for the trade-off between performance and interpretability. Numerical results highlight the significance of complementing statistical performance with economic assessment in electricity price spike forecasting. All experiments utilize data from Alberta’s electricity market.