Industrial cyber-physical systems face escalating vulnerabilities from operational anomalies and cyberattacks threatening critical infrastructure. This article presents an integrated framework combining deep learning-based anomaly detection, multiclass event classification, and authenticated encryption for real-time PMU data streams. A BiLSTM-transformer autoencoder achieves 97.79% anomaly detection accuracy with 62% fewer false positives and 90% fewer false negatives than baseline methods such as (e.g., simple autoencoder, LSTM). A BiLSTM-transformer classifier distinguishes six event types normal operation, equipment failures, line outages, generation outages, load changes, and cyber-induced bad data—with 98.27% accuracy across all classes. ChaCha20-HMAC-SHA256 authenticated encryption successfully mitigates 100% of simulated man-in-the-middle (MITM) and replay attacks, demonstrating 8.00 bits entropy, near-zero correlation ($\rho \approx 0$), and statistical indistinguishability. The NVIDIA Jetson Orin Nano validate deployment feasibility also facilitates GPU-accelerated multistream processing for substation-scale implementations. Evaluation of adversarial robustness indicates an accuracy of 86% under fast gradient sign method and projected gradient descent assaults, with adversarial training diminishing susceptibility by 63.5% . The architecture exhibits scalability and practical relevance for industrial cyber-physical security.

Publisher Copyright: © 2013 IEEE.

The integration of renewable energy resources and electric vehicle (EV) fleets with community microgrids (CMG) has increased fluctuations in net load. To address this and ensure safe operation, tapping into demand-side flexibility capacities in local electricity markets (LEM) is essential. Hence, this article presents a multilevel methodology for settling energy and flexibility markets among CMGs, utilizing the potential of Internet-of-Things-enabled appliances (IoT-EA), thermostatically-controlled loads (TCLs), and EVs in smart residential buildings (SRB) to enhance system performance. At level 1, SRBs are modeled using the virtual energy storage system (VESS) concept. Level 2 involves CMG scheduling, and at level 3, the distribution system operator settles the energy and flexibility markets using an adaptive alternating direction method of multipliers (ADMM) algorithm. Strong duality theory (SDT) and Karush-Kuhn-Tucker (KKT) conditions form a mathematical program with equilibrium constraints (MPEC) where market prices are variable for all participants. By unlocking the potential of SRBs, the proposed framework reduces flexibility market costs by 49.67%, network losses by 24.1%, and improves the voltage profile. The results confirm that the proposed market clearing mechanism ensures market efficiency and protects CMGs' privacy.

Accurate and practical load modeling plays a critical role in the power system studies including stability, control, and protection. Recently, wide-area measurement systems (WAMSs) are utilized to model the static and dynamic behavior of the load consumption pattern in real-time, simultaneously. In this article, a WAMS-based load modeling method is established based on a multi-residual deep learning structure. To do so, a comprehensive and efficient load model founded on combination of impedance-current-power and induction motor (IM) is constructed at the first step. Then, a deep learning-based framework is developed to understand the time-varying and complex behavior of the composite load model (CLM). To do so, a residual convolutional neural network (ResCNN) is developed to capture the spatial features of the load at different location of the large-scale power system. Then, gated recurrent unit (GRU) is used to fully understand the temporal features from highly variant time-domain signals. It is essential to provide a balance between fast and slow variant parameters. Thus, the designed structure is implemented in a parallel manner to fulfill the balance and moreover, weighted fusion method is used to estimate the parameters, as well. Consequently, an error-based loss function is reformulated to improve the training process as well as robustness in the noisy conditions. The numerical experiments on IEEE 68-bus and Iranian 95-bus systems verify the effectiveness and robustness of the proposed load modeling approach. Furthermore, a comparative study with some relevant methods demonstrates the superiority of the proposed structure. The obtained results in the worst-case scenario show error lower than 0.055% considering noisy condition and at least 50% improvement comparing the several state-of-art methods.

The papers in this special section focus on demand response applications in cloud computing technologie.s The use of distributed energy resources for self-generation and self-consumption along with Information and Communications Technologies and the Internet of Things is rapidly increasing the ability of the consumers and prosumers to actively engage with the electric energy system. Sustained consumer and prosumer engagement in demand response programs has been identified as a key factor in future electric energy systems, especially with a high penetration of renewable energy sources. This engagement has allowed demand-side resources to play a larger role in energy and reserve markets, whether by generating, storing or participating in demand response programs through increased flexibility, towards the consumer-driven energy transition. However, in real life, there is still a long way to go until demand response solutions take off and become entirely integrated into the daily life of the consumers, thus utilizing their full potential. Stronger engagement of consumers and prosumers is needed, as well as more flexibility services for system operation, benefiting Smart Grid developments.

The concept of smart cities has emerged as an ongoing research in recent years. In this case, there is a proven association between the smart cities and the smart devices, which have caused the power systems to become more flexible, controllable and detectable. Along with these promising results, many disputes have been generated over the cyber-attacks as unpredictable destructive threats, if not properly repelled, which could seriously endanger the power system. With this in mind, this paper explores a novel stochastic virtual assignment (SVA) method based on a directed acyclic graph (DAG) approach, where the essential data of the system sections are broadcasted decentralized through the data blocks, as a worthwhile step to deal with the cyber attacks’ risk. To do so, an additional security layer is added to the data blocks aiming to enhance the security of the data against the long lasting data sampling by virtually assigning the hash addresses (HAs) to the data blocks, which are randomly changed based on a stochastic process. The basic network architecture is based on a Provchain structure as a new framework to constantly monitor data operation. Two pivotal strategies also represented to deal with the energy and time needed for the HAs generation process, which have improved the proposed method. In this paper, the proposed security framework is implemented in a smart city environment to provide a secure energy transaction platform. Results show the authenticity of this model and demonstrate the effectiveness of the SVA method in decreasing the successful probability of cyber threat, increasing the time needed for the cyber attacker to decrypt and manipulate the data block.

The incorporation of the reconfiguration into the expansion planning of smart distribution networks is addressed in this paper, in which the potential of distributed energy resources and demand response (DR) are modeled. The system of systems (SoS) architecture is employed to model the strategy of a distribution company (DISCO), a private investor (PI), and a DR provider (DRP). The SoS is an efficient modeling architecture to model the behavior of independent and autonomous systems with distinct objective functions who are able to share some data and work together. The aim of the DISCO is to upgrade the system with the optimal cost and reliability, whereas the PI and DRP want to maximize their profit. The DISCO should try to persuade the PI to install DGs (Distributed generations) by offering the guaranteed purchasing prices. Furthermore, the DRP is a market player who can negotiate with the DISCO to sign a contract to sell the purchased DR capacities from the customers. The uncertainties of the DISCO problem is handled by using the chance-constraint method, but the PI and DRP use the conditional value at risk method to model their uncertainties. Finally, to solve the proposed model, the multiobjective optimization algorithm is employed.

Microgrids are faced with various uncertainty resources, which may put their reliable and beneficial bidding strategy at risk. In the literature, to handle the uncertainties, distinctive methodologies from fuzzy to stochastic techniques have been implemented widely. However, they dominantly suffer from dependency to the uncertainty models and are highly computational. In this paper, to overcome the challenges, a new approach based on information gap decision theory (IGDT) is proposed to provide a promising risk-managing bidding strategy. The uncertainties are modeled effectively without relying on the model in both robust and opportunistic frameworks. The problem is formulated as an effective multiobjective optimization problem considering the impacts of different uncertainties. Normal boundary intersection technique is utilized to generate evenly distributed Pareto Frontier. Analyzing the IGDT-based numerical results, applied to a test microgrid over a 24-h time horizon, verifies the effectiveness of the proposed bidding strategy structure confronting to the severe uncertainties.

Industrial and commercial electricity customers have significant potential in providing flexibility for power systems through diverse demand response (DR) programs. However, the industrial and commercial potential of DR is not yet completely understood, especially regarding the emerging and advanced technologies associated with the smart grid. Advances in smart meter technology that allow monitoring and controlling responsive loads in real time will also be key enablers of DR potential. It can be more complex to implement DR for industrial loads if compared to residential loads mainly due to the reliability management that is more vital for industrial plants. Hence, this paper aims at providing a comprehensive review of the most recent advances on industrial and commercial DR. On this basis, this survey first presents the potential and technologies of DR in industrial and commercial sectors. Then, the existing models of DR in the mentioned sectors are presented. The presence of industrial and commercial DR in electricity markets is also investigated. Finally, the main positive and beneficial aspects, as well as challenges and barriers of industrial and commercial DR, are investigated.

The eleven papers in this special section focus on the industrial and commercial potential of demand response (DR). Customers from this non-residential market base have great potential in providing flexibility for power systems through diverse demand response (DR) programs. Intelligent energy management can be carried out with DR in industrial and commercial facilities, especially if onsite control, information, and communication technologies are available, enabling also the inherent automation capabilities of heating, ventilation, and air conditioning systems. In the dawn of the Smart Grid era, with increasing distributed generation and the conversion of traditionally passive consumers to newly active energy players in the market, DR is being effectively considered for outage management and network reinforcement deferral.

An optimal placement of protective devices could increase the reliability and quality level of a distribution network. An innovative mixed-integer nonlinear programming model is proposed in this paper to find the type, optimal siting, and number of protective devices to be accurately installed in distribution networks. The customer outage and protective devices costs are considered to derive a value-based reliability equation. To ensure the effectiveness of the proposed formulation economic and technical constraints is considered. Further, this paper aims at aiding decision-makers in providing appropriate protective device allocation by minimizing the expected interruption cost index. Case studies are employed to demonstrate the reliability optimization of a test network and a typical real-size network in which the several cost constraints and protection schemes are assumed to extract the results. Accuracy and effectiveness of the proposed method are assessed and sensitivities analysis is carried out.

The Stochastic nature of wind power can cause insufficiency of supply in electrical systems. Applying an energy storage system can alleviate the impact of wind power forecast error on power systems performance and increase system tolerance against deficiency of supply. This paper attempts to investigate a new unit commitment (UC) problem based on the cost-benefit analysis and here-and-now (HN) approach for optimal sizing of battery banks (BBs) imicrogrids (MGs) with wind power systems. To solve this problem, particle swarm optimization is used to minimize the total cost and maximize the total benefit. In this paper, 12 scenarios have been considered in the presence of BBs and without them in 2 operating modes: 1) stand-alone mode and 2) grid-connected mode. Using the HN approach, the uncertainty of wind power is applied as a constraint in these operating modes. The mathematical formulations related to the HN approach in MGs and its combination in a UC problem are presented in detail for optimal sizing of BBs. Simulation results show that the best sizes of BBs and the scheduling of distributed generations would be entirely different when the accessibility of wind power is taken into consideration by applying HN approach to the proposed probabilistic UC problem.

The concept of electricity markets in the deregulated environment generally refers to energy market and reactive power market is not paid attention as much as it deserves to. However, reactive power plays an important role in distribution networks to improve network conditions such as voltage profile improvement and loss reduction. Plug-in electric vehicles (PEVs) are mobile sources of active and reactive power, capable of being participated in energy market, and also in reactive power market without battery degradation. Active and reactive powers are coupled through the ac power flow equations and branch loading limits, as well as PEVs and synchronous generators capability curves. This paper presents a coupled energy and reactive power market in the presence of PEVs. The objective function is threefold, namely offers cost (for energy market), total payment function (for reactive power market), and lost opportunity cost, all to be minimized. The effectiveness of the proposed coupled energy and reactive power market is studied based on a 134-node microgrid with and without PEV participation.

This paper presents a multiobjective probabilistic model for the placement of phasor measurement units (PMUs) in electrical power networks. The proposed model simultaneously optimizes two objectives functions: 1) minimizes the number of PMUs; and 2) maximizes the expected value of system's redundancy (or minimizes the unobservability of the system). Incorporating the impact of zero-injection buses, an efficient formulation is used to evaluate the probability of unobservability of buses resulted from line outages and PMU loss. The extracted formulation is based on the mixed integer linear programming (MILP) framework, which is efficiently solvable by high-performance commercial solvers. This multiobjective optimization problem (MOP) is solved by augmented epsilon-constraint and weighting approach. Accordingly, two new indices are introduced to compare these two multiobjective methods. Finally, the ultimate solution among the Pareto front is recognized using a fuzzy decision-making process. The IEEE 57-bus test system is used to examine the effectiveness of the proposed frameworks.