The deployment of smart meters in modern electricity grids enables real-time monitoring and control. However, this makes advanced metering infrastructure (AMI) vulnerable to cyber threats that can affect both utilities and consumers. This paper introduces a multi-stage iterative intrusion detection framework that combines SVM-based anomaly detection, timed fault propagation graph (TFPG) analysis, and behavioral scoring. In Stage I, the SVM identifies anomalies and sends suspicious data to Stage II, where the TFPG evaluates temporal dependencies and causal relationships and compares them with predefined attack patterns. Finally, in Stage III, the risk and severity of detected intrusions are measured in real time. The results show that the SVM achieves $94.05-94.14 \%$ accuracy and stable macro-F1 scores above 0.94 in five classes. These classes include denial of service, false data injection, RAM exhaustion, CPU overload, and normal operation. The results show that attacks are accurately detected. Effective risk-based responses also enhance the overall resilience of the smart grid.

Corrective maintenance is performed after a failure in power distribution systems to restore service as quickly as possible. Although increasing the number of maintenance crews and depots improves reliability, it leads to significant investment costs. This paper proposes a dynamic planning model for the optimal deployment of maintenance crews in power distribution systems to minimize operational and investment costs along with interruption costs. The planning problem is computationally complex due to nonlinearity, a large solution space, and uncertainties related to service requirements. To tackle the issue of intractability in real-world systems, this paper proposes applying the Benders Decomposition approach to decompose the problem into a master problem and a sub-problem, both formulated in the mixed-integer linear programming format. The master problem determines the number and locations of depots to minimize depot-related costs and outage durations caused by crew travel time. The sub-problem optimizes the number of maintenance teams assigned to each depot to minimize delays due to maintenance crew unavailability. To demonstrate the applicability of this model, it is implemented on a real large-scale power distribution system. Simulation results show that the total system cost in the optimized case can be reduced by 29.25% compared to the current non-optimal state.

Although hydrogen-based technologies, micro-hydro turbines, and waste heat recovery units offer significant economic value in achieving zero-carbon integrated energy systems and reducing energy losses, they have been underutilized. This paper introduces an optimization model for integrating a multi-carrier energy system-including electricity, heat, natural gas, water, and hydrogen-while incorporating zero-carbon and waste heat recovery technologies. The proposed model determines the optimal type and number of fuel cells, organic Rankine cycle (ORC) units for waste heat recovery, electrolyzers, micro-hydro turbines, natural gas-fired combined heat and power units, natural gas-fired boilers, transformers, desalination units, and various energy storage systems. A scenario-based framework, formulated as a mixed-integer linear programming (MILP) problem, is used to consider uncertainties related to energy demands over the planning horizon. Furthermore, a data mining technique is employed to select a representative subset of scenarios, reducing computational complexity without compromising solution quality. The proposed model is examined on a real multi-carrier microgrid to demonstrate the economic and environmental benefits of incorporating clean hydrogen-and hydro-based devices, with an emphasis on ORC technology. Numerical results show that this approach reduces total system cost by 5.73% and carbon emissions by 16.94% compared to conventional models. All device types considered in this study are commercially available, providing a realistic and practical foundation for future deployment.

Cyber-physical power systems are vulnerable to cyber-attacks, especially false data injection attacks (FDIAs). FDIAs against distribution system state estimation (DSSE), which alter state estimation (SE) by changing meter readings, have received researchers' attention in recent years. A common defense against FDIAs in the literature is the use of labeled data to train classifiers as FDIA detectors. However, this approach's performance can be limited by the highly imbalanced nature of FDIA datasets. The black box characteristics of the machine learning models can make them hard to trust and adopt in important applications. Hence, we propose an innovative explainable artificial intelligence (XAI)-enhanced ensemble-based detection and localization model that leverages convolutional neural networks (CNNs) and support vector machine (SVM). The ensemble model uses SVM to merge various spatiotemporal CNNs' outputs. Training these CNNs on under-sampled subsets of the majority class and using their ensemble addresses class imbalance. This paper leverages XAI to enhance the interpretability of the detection process and improve localization accuracy. The localization process uses the outputs of an XAI technique, gradient-weighted class activation mapping, to aid the majority-voting-based localization ensemble model. Our model can also detect FDIAs during the distribution feeder's topology changes. Extensive simulations on IEEE 13-bus and IEEE 123-bus feeders prove the proposed under-sampling-based detection approach as an alternative to prevalent over-sampling methods like generative adversarial networks (GANs), offering a novel solution to class imbalance challenges. The paper also provides a comprehensive analysis of the proposed spatiotemporal model's performance, demonstrating its superiority over temporal CNNs.

This study explores strategies to de-risk renewable energy investments in project finance (PF) deals, primarily focusing on enhancing the prosperity of such deals by mitigating default risk. The success of PF deals is intricately linked to ensuring reliable future revenues, and by addressing default risk, the overall viability of the agreement is significantly improved. The primary objective of this research is to introduce a financial instrument leveraging credit default swaps (CDS) and to delineate its pricing methodology. The effectiveness of this financial instrument is demonstrated through its application to a 10 MW solar photovoltaic power plant project. The study reveals that the instrument efficiently transfers default risk to a protection seller at an affordable cost, showcasing the impact of using the instrument on the levelized cost of electricity (LCOE) for different leverage ratios. This outcome augments the viability of PF deals and mitigates the risks associated with long-term financing, particularly in high-leverage scenarios. Additionally, a comprehensive sensitivity analysis is conducted, examining the impact of default probability and the financial instrument price under varying financial leverage ratios, power purchase agreement (PPA) prices, and tax rates. The insights derived from this analysis provide valuable information for banks, investors, solar power plant developers, and policymakers, enabling them to make more reliable decisions in their decision-making processes.

Defending against false data injection attacks (FDIAs) in cyber-physical power systems is crucial. Detection in power distribution systems is complex due to load variations, uncertainties, and fewer meters. Defense strategies include model-driven and data-driven approaches, but model-based methods can trigger false alarms due to threshold setting issues. The current research proposes a novel data-driven method to address threshold setting issues in detecting and localizing FDIAs in power distribution systems. First, a dataset is created by recording estimated measurement values using an unscented Kalman filter and weighted least squares across various attack scenarios. These estimated measurements are then fed into a deep artificial neural network (ANN) for binary classification to detect attacks. The output, along with the estimated measurements, is used by another ANN to localize the corrupted meter zone. This deep learning-based approach improves threshold setting over the common chi-square method. Results show that the proposed deep learning method for FDIA detection and localization outperforms a recently proposed ensemble of shallow models. The area under the curve value increases by about 5% with lower training time. The approach is also effective against previously unseen attack strategies and different feeder topologies.

Accurate forecasting of net energy consumption in Multi-Carrier Energy Systems (MCES) is essential for effective resource management and economic planning. Accordingly, Machine Learning (ML) and Deep Learning (DL) methods are applied for energy forecasting, but often rely on individual methods, especially with complex datasets. This frequently results in reduced generalizability and robustness, making accurate forecasting with complex datasets more difficult. This paper presents an ensemble model of ML, DL, and statistical methods that are stacked with a meta-learner to forecast net energy consumption in an MCES. In the proposed model, advanced preprocessing techniques, such as cyclical feature encoding and feature ranking using eXtreme Gradient Boosting, are employed to enhance the model’s robustness against complex features. The results show that the proposed model achieves the lowest error metrics with a Mean Absolute Percentage Error of 9.8% and 17.6%, compared to individual methods at the hourly and daily horizons, respectively. By reducing the energy forecasting error, the model lowers operating costs, with an economic evaluation demonstrating a reduction of approximately 8% to 23% in energy costs during peak hours. Overall, the proposed model outperforms individual methods and provides more accurate and robust net energy forecasting for MCES.

Residential electrical load forecasting is considered essential for the planning and operation of electricity distribution systems. However, due to the unpredictable and fluctuating behavior of households and the complexity of datasets in this field, accurate load forecasting is often challenging. Additionally, the task of meeting electricity demand during household peak loads has been identified as a major challenge for modern power systems. This article uses a class-based approach for load forecasting to differentiate between on-peak, mid-peak, and off-peak areas of electrical load consumption. For each class, short-term electric load forecasting is performed using an ensemble model based on statistical, Machine Learning (ML), and Deep Learning (DL) methods. For these three methods, feature engineering uses encoding cyclical features to capture periodic patterns, incorporating the eXtreme Gradient Boosting (XGB) model to identify and rank influential features affecting load consumption. Within each class, the most accurate method is selected based on the performance metrics. Analysis of Variance (ANOVA) test is also employed to assess the reliability of the results through multiple runs. The results indicate that the DL method achieves higher accuracy in the on-peak class, the ML method performs better in the mid-peak class, and the statistical method yields the best results in the off-peak class. In the final forecast of electric load, it has been seen Mean Absolute Percentage Error (MAPE) of the proposed model is 2.4, 1, and 0.6

Fault management involves actions to restore interrupted customers as quickly as possible after a fault occurrence, which is facilitated by optimal switch placement. However, the switch optimization problem requires significant computational effort because of the nonlinearity and the large search space. Hence, the problem may be interactable for large-scale power distribution systems. This paper proposes a machine learning-based proxy to determine the optimal number and location of switches in real-world power distribution systems, including manual and automatic switches. The objective function comprises equipment costs and reliability indices, including the system average interruption frequency index (SAIFI), the system average interruption duration index (SAIDI), and the energy not supplied (ENS) index. The proposed model is a stacked ensemble model, in which convolutional neural network (CNN)-based models serve as base learners to capture complex and spatial information from their input data. The input data for the base learners are optimally selected by explainable artificial intelligence (XAI) tools from a large feature set of candidate installation points. The metamodel combines the base learners' predictions to determine the optimal points for installing switches and is a fully connected artificial neural network. This paper uses the Bayesian optimization algorithm to optimally construct the stacked ensemble model. We validate the proposed model alongside state-of-the-art learning-based and mathematics-based models using a real power distribution system. The simulation results demonstrate that the proposed model outperforms the state-of-the-art models in terms of computational complexity and optimality.

The service restoration of system after the occurrence of high-impact events is one of the aspects of power system resiliency. Microgrids (MGs) and distributed generations (DGs) make opportunities for the fast restoration. The sequential service restoration (SSR) problem based on MGs has been defined to determine the switching sequence and restorable load in each time step. In this article, a probabilistic SSR focusing on multimaster MGs is proposed in a mixed-integer linear programming format incorporating system dynamic constraints. The restoration time is minimized in addition to the maximization of the restored load in the weighted sum framework, where the optimal weights are obtained by the fuzzy decision-making method. The spherical simplex unscented transformation is used to handle system uncertainties. The proposed method is examined on the modified IEEE 123-node test feeder. The results show that the restoration based on multimaster MGs improves the ratio of the restored load amount to the restoration time by more than 35% in comparison with the existing restoration methods, which are based on single-master MGs. Furthermore, the adopted control scheme for master DGs is validated through a dynamic simulation of the SSR process obtained from the optimization problem.

Power distribution systems are equipped with switching devices, including fault interrupter switches (FISs) and load break switches (LBSs), to facilitate fault management and enhance operational efficiency. Recent research has ignored power flow constraints and focused only on reliability improvement to determine the optimal resting state, number, and location of FISs (e.g., circuit breakers and fuses) and LBSs. This paper contributes to the advancement of reliable power distribution systems by proposing a multi-objective optimization model for the optimal deployment of switching devices, considering power flow constraints. The proposed model aims to minimize the costs associated with installing new switching devices, the cost of interruptions, and the voltage drop at load points under normal and post-fault conditions. The optimization problem is described in a linear format to reduce the problem's complexity. The proposed model is examined on a standard test system and a real power distribution system. The simulation results demonstrate that applying the proposed model may lead to a 21 % improvement in voltage profile without a significant increase in the cost of interruptions compared to existing reliability-oriented models.

Monitoring modern power distribution systems through state estimation (SE) is crucial for optimizing grid operation and ensuring reliability. However, SE is vulnerable to stealth false data injection attacks (FDIAs). Stealth FDIAs can evade conventional bad data detection algorithms, leading to operator misjudgments and erroneous decisions. FDIA misidentifications, i.e., false alarms and undetected FDIAs, have distinct monetary and operational consequences. Even within each type of misidentification, these consequences can vary based on factors like meter location, customer type, and sustained energy not supplied (ENS). This paper, therefore, proposes consequence-driven cost functions to quantify the monetary impact of FDIA misidentifications in the SE. The proposed method explicitly accounts for system topology, customer type, and ENS. The proposed approach is model-agnostic and can operate with any anomaly detection method. We use an autoencoder (AE) as a sample anomaly detection method to illustrate the proposed consequence-driven framework. The AE is trained on FDIA-free data to reconstruct normal meter behavior. Deviations are then passed to the largest normalized residual (LNR) test for detection and localization, enabling a detailed evaluation of FDIA misidentification costs. Additionally, an optimization formulation is introduced to adjust the LNR thresholds for each meter, minimizing the total misidentification cost. Simulations use IEEE 13-bus and 123-bus test feeders. Results show that optimal thresholds can reduce FDIA misidentification costs by up to 66 %. This offers a consequence-driven alternative to the accuracy-based metrics commonly used in the literature. It also provides a better fit for the complex, cyberphysical nature of power systems.

Estimating distribution transformers’ hourly load profiles is important for planning and operation. However, many transformers have no real-time monitoring due to the sparsity of smart meters. This paper estimates the transformer load profiles using smart meter data, billing records, and GIS mapping of customers to the transformers. First, customers’ smart meter readings are pre-processed and normalized. Discrete wavelet transform (DWT) is utilized to extract features. The features from DWT are then grouped into typical load profiles (TLPs) using k-means clustering. To allocate a TLP to customers without smart meters, k-nearest neighbor is used, which utilizes monthly energy consumption, seasonal and monthly share of consumed energy, and, if applicable, share of energy received based on customers’ tariff. Next, the TLPs are scaled using customers’ monthly energy consumption and are aggregated to reconstruct the hourly transformer loads. The performance of the method using real data is evaluated, and it shows that the mean absolute percentage error is under 10%.

This study proposes a novel Supply Chain Finance scheme (CG-RS), integrating credit guarantees (CG), and revenue-sharing contracts (RS). We analyze a three-party Stackelberg game between a capital-constrained retailer, supplier, and bank. We derived equilibrium strategies under both monopolistic and competitive bank markets to investigate the impact of the CG-RS scheme on the financial performance of each party. From the numerical analysis, we find that all parties can benefit from the CG-RS scheme by mitigating default risk and aligning incentives. The supplier’s guarantee coefficient and the retailer’s initial capital significantly influence the scheme’s outcomes, while the revenue-sharing proportion plays a crucial role in balancing interests. Our findings suggest that the CG-RS scheme offers a promising solution for addressing capital constraints and enhancing supply chain performance.

This research develops a sustainable supply chain model for time-varying deteriorating items with customers’ credit period, customers’ credit amount, promotional efforts, and selling price-dependent demand. The model incorporates joint policies of promotional cost-sharing, three-level trade credit financing, and carbon tax. Under three-level trade credit financing, the supplier and the wholesaler offer some credit periods to the wholesaler and the retailer, respectively. As a result of this opportunity, the retailer allows customers to delay the payment of some portion of the total purchased amount. Here, shortages are assumed to occur in the form of partial backorder. The main objective of this investigation is to minimize the carbon emissions and maximize the joint profit of the retailer and the wholesaler simultaneously. To achieve this, the model is formulated as a Signomial Geometric Programming problem and solved efficiently using a global optimization method. The performance of the developed model and solution method is evaluated through several numerical examples and sensitivity analysis, providing valuable managerial insights. The computed results reveal that the optimal selling price varies depending on the nature of deterioration rates. Constant functions result in higher prices compared to linear and three-parameter Weibull functions. Coordination strategy and promotional cost-sharing policy among supply chain partners are shown to impact profits positively. Additionally, the wholesaler's credit period is a crucial factor influencing pricing decisions, logistics operations, and carbon emissions. The findings further demonstrate that extending the wholesaler's credit period under a carbon tax policy leads to a 26% increase in total joint profit, a 10% decrease in the wholesaler's carbon emissions, and a 21% decrease in the retailer's carbon emissions.

Today, wind and solar energy sources have opened their place in the power system due to their environmental appeal. With the presence of these renewable energy sources (RESs), forecasting net load (NL) and its ramp are of huge importance owing their fundamental role in evaluating and improving the flexibility of the power grid. However, it is challenging to analysis flexibility and NL ramps using NL forecasts due to the uncertainty of RESs. Furthermore, the surge in the number of electric vehicles (EVs) as notable electricity consumers, and how their charging strategy can affect the NL curve are matters of concern. Most NL forecasting and flexibility analyses overlook the concurrent integration of wind and solar sources. Moreover, the impact of controlled EVs charging on grid flexibility remains largely unexplored. Existing studies also fail to assess the proper combination of wind and solar energy sources for future flexibility needs. This paper presents a framework for forecasting NL and detecting ramps with the simultaneous presence of EVs and RESs to investigate the impact of controlled charging of EVs on flexibility. Investigating charging of EVs as a solution is delved deeply in this paper to reduce NL ramps and improve flexibility. The numerical results show that controlled EVs charging may lead to 3% ramp reduction and 52% increment in the system flexibility. This paper also proposes to forecast and find the proper combination of RESs for the next years, leading to a 75% increment in the system flexibility compared to the business as usual RESs penetration.

The number and location of switching devices (e.g., circuit breakers and sectionalizers) should be optimally determined in power distribution systems to reduce system interruptions and associated costs. However, existing mathematical optimization algorithms, such as classic and metaheuristic methods, cannot solve the optimal switch placement problem for large-scale systems. In this paper, a scalable model is proposed based on machine learning methods to determine the optimal number and location of switching devices according to system conditions. This paper proposes employing ensemble learning methods and explainable artificial intelligence tools to build an accurate data-driven model. Consequently, power distribution operators can determine the optimal number and location of circuit breakers, remote-controlled sectionalizers, and manual switches in large-scale systems without mathematical optimization algorithms. To validate its accuracy and scalability, the proposed model and a classic-based model are implemented on a real power distribution system in Fars province. The numerical results demonstrate that the proposed data-driven model can find a solution close to the globally optimal solution quickly, using a limited range of system data.

The penetration of distributed energy resources (DERs) has changed the role of a consumer to a prosumer, i.e., producer and consumer. This new role provides the opportunity for peer-to-peer(P2P) energy trading. In this paper, a three-stage iterative framework is proposed to clear the price and quantity of trading in P2P markets while addressing price and DER uncertainties by the Monte Carlo simulation (MCS) method. Initially, bids and offers of customers are determined by implementing an advanced satisfaction-based home energy management system (HEMS) at each home. Subsequently, the market operator prioritizes bids and offers according to the amount of customers’ participation in the market. Finally, the P2P market is cleared by application of the alternating direction method of multipliers (ADMM), and the market clearing prices (MCPs) are determined. MCPs are used as a parameter to repeat the three stages, and the procedure is redone until the stopping rule is met. The proposed method's effectiveness has been investigated in communities with 8, 50, and 100 prosumers. Results indicate a 69.51 % cost reduction in a smart energy community with 50 homes through P2P energy market participation. The proposed market clearing method is compared with the common mid-market rate (MMR) and Stackelberg game methods and demonstrates over 25 % reduction in community costs.

The fault management process is facilitated by equipping power distribution systems with automated devices, especially remote-controlled switches (RCSs). Although RCS plays a key role in improving the system's reli-ability, it imposes significant investment, installation, and maintenance costs. Hence, RCSs should be optimally located in distribution feeders for the highest profit. In previous works, reliability-oriented mathematical opti-mization models have been formulated to reach this goal. However, the number of test solutions exponentially grows with the problem size to find the globally optimal solution. This paper uses machine learning to propose a scalable and easy-to-implement model for optimal switch placement in real power distribution systems. At first, the features of candidate points for installing RCSs are introduced. Then, a learning model is applied to deeply explore the relationship between these features and optimal locations for installing RCSs. After training, the learning-based surrogate model directly determines the optimal RCS placement strategy in real power distri-bution systems by leveraging knowledge gained from past experiences. Simulation results demonstrate that the proposed surrogate model is approximately 29 times faster than the integer programming-based mathematical model, without a significant loss of accuracy, when implemented on a modified 11 kV network connected to Bus 4 of the Roy Billiton test system. This paper also employs explainable artificial intelligence (XAI) tools to select the most important features, where the Hamming loss is decreased by approximately 5%.

Examining the structure of dependence between financial assets and the effects of their Co-movement is one of the important issues in financial markets. The corresponding copula is one of the most computationally convenient ways to describe the dependency structure. This paper examines regime change probability and the best copula model between Bitcoin and six other assets from 2018 to 2021. First, using the ARMA-GARCH model, the marginal distribution functions for all assets and residuals are calculated. Then, by using the obtained residuals, 11 models of copula and six models of combined Copula with Markov switching were implemented. The model that has the best function for constructing combined distribution functions is selected. Finally, the regime probabilities each time are calculated from the best-fitted model. The results show that in the study period, for Bitcoin-Ethereum, Bitcoin-Cardano, and Bitcoin-Gold pairs MS-CT, for BitcoinBinance coin and Bitcoin-Ripple pairs MS-CRG and MS-CN for Bitcoin-Oil pair have the best performance. Furthermore, the probabilities of regime change between each asset at each time were calculated and described.