Power System Environment Research Articles

Generating Payloads of Power Monitoring Systems Compliant with Power Network Protocols Using Generative Adversarial Networks

In the network environment of power systems, payload generation is used to construct data packets, which are used to obtain data for the security management of network assets. Payloads generated by existing methods cannot satisfy the specifications of the protocols in power systems, resulting in low efficiency and information errors. In this paper, a payload generation model, LoadGAN, is proposed by using generative adversarial networks (GANs). Firstly, we find segmentation points to cut payloads into different segment sequences using sliding window schema based on Bayesian optimization. Then, we use different payload segments to train several child generators to generate corresponding parts of a whole payload. Segment sequences generated by these generators are assembled to form a whole new payload that is compliant with the specifications of the original network protocol. Experiments on the Mozi botnet dataset show that LoadGAN achieves precise payload segmentation while maintaining a high payload effectiveness of 85.5%, which is a 40% improvement compared to existing methods.

Advanced control of double stage grid-tied three phase photovoltaic systems with shunt active power filter

This paper explores the challenges associated with the control of a two-stage three-phase electrical grid connected to a photovoltaic (PV) system. The objectives encompass: i) maximizing the available PV power, ii) controlling the DC-link voltage to a predetermined setpoint, and iii) considering that power quality has become an important measure in a distribution electrical network where different loads are connected, the third objective will mainly focus on ensuring power factor correction (PFC). To achieve these objectives, two loops of nonlinear controller are developed. In the outer loop, the duty cycle of a boost converter is controlled using a hybrid technique of backstepping technique and the perturb & observe (P&O) algorithm. In addition, the inner loop employs a hybrid automaton approach to tackle the challenges of a three-phase shunt active power filter (SAPF). The results have been verified through numerical simulation using MATLAB/Simulink power systems environment.

Probabilistic power flow based on physics-guided graph neural networks

Under the high-dimensional and nonlinear stochastic power system environment, artificial intelligence (AI) is becoming a promising alternative to the urgent demand for probabilistic power flow (PPF). However, traditional AI only learns from experiences in data and is unable to satisfy physical constraints. This may result in an undesired infeasible inference for PPF. To solve this issue, a physics-guided graph neural network (PG-GNN)-based PPF analysis method is proposed. At the outset, alternating current power flow equation is analyzed to produce gradients for connecting physical component and AI. The proposed PG-GNN then incorporates the sensitivities into the training tensor graph such that it enables in-depth physical learning. At the same time, the GNN serves to enhance generalizability in varying topology. The well-trained PG-GNN is finally leveraged to surrogate traditional power flow solver in Monte-Carlo method, such that real-time PPF is realized. Numerical tests on benchmarks demonstrate that, in unseen scenarios, the proposed method enables only little gap versus the exact baseline, but beats other rivals with over tenfold computing efficiency. Moreover, comparisons with traditional AIs manifest that our method holds better generalizability.

FEATURES OF ENSURING ELECTROMAGNETIC COMPATIBILITY OF UNINTERRUPTIBLE POWER SYSTEMS

An overview of the main structures of uninterruptible power systems is provided. The impact on internal-system and external-system electromagnetic compatibility of these devices is determined. Contemporary standards and requirements for ensuring electromagnetic compatibility of uninterruptible power systems are analyzed. Features of the structures of uninterrupted power systems such as online, offline and line interactive by the conductive path of propagation of interference are given. The main advantages of eco uninterrupted power supply are summarized. A generalized approach is proposed for the application of radiofrequency interference filters depending on the electromagnetic environment and features of uninterruptible power systems. Refined limitations on the possibilities of adjusting the basic and influence parasitic parameters of the filter links by symmetric and asymmetric propagation of conductive disturbances. The possibility of using remote control of the effectiveness of means of reducing conductive disturbances was assessed. The expediency of localization of control parameters of smart radiofrequency interference filters with the use of artificial intelligence is determined. References 10, figures 6, tables 2.

Performance analysis of different control models for smart demand–supply energy management system

Several features of innovative grid technologies can be deployed to improve the overall performance of the power system environment. This can be seen from the generation to the consumption of energy. The two-way communication of smart metering introduces the novel functionalities of the energy management system. This paper presents a practical implementation of using the intelligent metering system. It consists of implementing a nanogrid that optimally coordinates the energy from the solar panel, battery storage and utility grid to supply the end user. The developed model is validated with an optimal value of the state of charge of the distributed energy storage to maximise energy from the solar panel and battery storage while minimising the power received from the utility grid. A demand response scheme is employed to formulate the performance index of the energy management system using three optimal control models: adaptive open-loop control, adaptive closed-loop control and model predictive control schemes. The formulation of the performance index of each approach is a function of the energy flow from different resources depending on the power consumption. The three models have given different insights into the performance of the smart nanogrid, which may be used to the advantage of the grid owner or end user. Through the performance of the optimal strategies, it can be observed that energy management is ensured, and real-time monitoring of the entire system is guaranteed. The performance models facilitate the minimisation of the power from the utility, resulting in savings between 23.7% and 39.240% of the total energy demand from the end user. Besides, the system design is validated by an electrical system to form a real-world innovative nanogrid application in residential environments.

Intelligent Composite Compensation Under Load Variation in Power Transmission System.

The power transmission system is in a stressed condition due to the increasing electricity demand. This stress, exacerbated by the deregulated power system environment, necessitates an urgent additional supply to maintain system adequacy. One important initiative to alleviate the transmission burden which meets the load demand can be rectified by composite compensation scheme. This paper showcases intelligent composite compensation under varying loads, emphasizing loss minimization. The approach integrates a loss control scheme involving Distributed Generation (DG) and Optimal Reactive Power Dispatch (ORPD) with multi-DG installation termed composite compensation, employing a novel optimization technique called Integrated Cloning Accelerated Mutation Evolutionary Programming (ICAMEP). The study identifies optimal locations and sizes for composite compensation in the power transmission system, demonstrating its superiority over traditional optimization techniques namely the evolutionary programming (EP) and artificial immune systems (AIS). Results are demonstrated for four cases involving single DG, 3 DGs and composite compensation validated on IEEE 30-Bus Reliability Test System (RTS). ICAMEP is superior over EP and AIS in achieving the highest loss reduction.

Multi-Agent Reinforcement Learning for Power System Operation and Control

This study investigates the use of Multi-Agent Reinforcement Learning (MARL) to enhance the efficiency of power system operation and control. The simulated power system environment is represented as a multi-agent system, where intelligent agents are used to mimic generators and loads. The MARL framework utilizes Q-learning algorithms to allow agents to independently adjust their activities in accordance with changing operating circumstances. The resulting simulated data represents a wide-ranging power grid scenario, including buses with different generator capacity, load needs, and transmission line capacities. The findings indicate a significant improvement in the stability of the system via Multi-Agent Reinforcement Learning (MARL), since the agents’ capacity to learn and adapt enables them to quickly alter the outputs of generators and meet the needs of the load, so ensuring that voltage and frequency levels remain within acceptable limits. The MARL framework significantly improves economic efficiency by enabling actors to optimize their behaviors in order to reduce the total costs of the system. The agility of the MARL-based control method is emphasized by the decrease in response time to dynamic disturbances, as agents demonstrate quick and efficient reactions to unforeseen occurrences. The favorable results highlight the potential of MARL as a decentralized decision-making model in power systems, providing advantages in terms of stability, economic efficiency, and the capacity to respond to disruptions. Although the research uses artificial data in a controlled setting, the observed enhancements indicate the flexibility and efficacy of the MARL framework. Future research should prioritize the integration of more practical situations and tackling computational obstacles to further confirm the suitability and expandability of Multi-Agent Reinforcement Learning (MARL) in actual power systems.

A novel scheduling approach of stochastic cogeneration model in power system environment using improved civilized swarm search algorithm to reduce cost and carbon emission

This study explores a cogeneration system's optimal commitment and generation scheduling while considering power and heat demand uncertainty. The deterministic model corresponding to the Cogeneration Based Unit Commitment Problem (CBUCP) cannot express the uncertainties related to input data and energy demand. In the present work, the stochastic Multi-Objective Cogeneration Based Unit Commitment Problem (MO-CBUCP) aims to obtain the optimal generation schedule at minimum operational cost and emission, considering uncertainties in the heat and power demand. To deal with continuous and binary variables of MO-CBUCP and obtain an optimal solution, an effective combination of nature-inspired techniques such as Civilized Swarm Search Algorithm (CSSA) and Binary Particle Swarm Optimization (BPSO) is employed for the cogeneration-based test system. To improve the exploration ability of CSSA, the predator and seasonal effect has been incorporated, as the movement of particles is affected by weather changes. Improved CSSA effectively balances the exploration and exploitation during the optimization. The results of the proposed technique are compared with other optimization techniques to show efficacy. The comparative analysis shows that the cogeneration plant significantly affects operating cost and emission for the deterministic and stochastic models.

Fault Diagnosis of Shipboard Medium‐Voltage Alternating Current Power System with Fault Recording Data‐Driven SE‐ResNet18‐1 Model

The electrification trend of marine vessels has led to the rapid development of all‐electric ships. Yet the unique topology and harsh working environment of shipboard power system have posed significant challenges to its fault diagnosis. This paper addresses the research gap in fault diagnosis for shipboard medium‐voltage alternating current (MVAC) power systems and proposes a machine learning‐based fault diagnosis scheme. Signals from fault recorders before relay triggering are used as input for the neural network model. By combining the residual neural network (ResNet) with Squeeze‐and‐Excitation (SE) Block, the feature extraction capability of the network model is maximized. Utilizing the fault transient information, the proposed scheme can realize real‐time diagnosis of any large disturbance to the power system. The data set for scheme verification is established through simulation experiments on PSCAD/EMTDC platform, while model training is completed under the PyTorch framework. The experimental results show that the proposed fault diagnosis scheme can effectively discriminate all types of faults from non‐fault conditions in shipboard MVAC power system. © 2023 Institute of Electrical Engineer of Japan and Wiley Periodicals LLC.

Research on the optimal model for the evaluation of new power system investment projects based on the cloud model–DS evidence theory–TOPSIS method

AbstractConsidering that the traditional investment project evaluation system can no longer fully adapt to the characteristics of the new power system under the investment environment of the new power system, this study constructed a new power system investment project evaluation and optimization method based on the combination of the cloud model, evidence theory and the TOPSIS method. First, 16 evaluation indexes were considered based on four dimensions, namely green and low‐carbon, safe and reliable, flexible and intelligent, and economical and efficient, and the optimal evaluation index system of new power system investment projects was designed. Second, the normal cloud model was used to obtain the evaluation membership distribution of each index and turn it into evidence. Considering the conflicts between indicators and the combinational contradictions of traditional evidence theories, an improved DS evidence theory based on a game weight coefficient discount to reduce conflicting evidence was used to fuse the membership information of multiple indicators. On the basis of the evaluation results of each scheme, this study used the TOPSIS method to sort the advantages and disadvantages of each scheme. Finally, the project of planning and putting this model into operation in the 14th Five‐Year project database of a power grid enterprise was selected as an example to carry out empirical analysis, and the effectiveness and superiority of the proposed model were verified.

Power system data-driven dispatch using improved scenario generation considering time-series correlations

Reinforcement learning (RL) is recently studied for realizing fast and adaptive power system dispatch under the increasing penetration of renewable energy. RL has the limitation of relying on samples for agent training, and the application in power systems often faces the difficulty of insufficient scenario samples. So, scenario generation is of great importance for the application of RL. However, most of the existing scenario generation methods cannot handle time-series correlation, especially the correlation over long time scales, when generating the scenario. To address this issue, this paper proposes an RL-based dispatch method which can generate power system operational scenarios with time-series correlation for the agent’s training. First, a time-generative adversarial network (GAN)-based scenario generation model is constructed, which generates system operational scenarios with long- and short-time scale time-series correlations. Next, the “N-1” security is ensured by simulating “N-1” branch contingencies in the agent’s training. Finally, the model is trained in parallel in an actual power system environment, and its effectiveness is verified by comparisons against benchmark methods.

AdapSafe: Adaptive and Safe-Certified Deep Reinforcement Learning-Based Frequency Control for Carbon-Neutral Power Systems

With the increasing penetration of inverter-based renewable energy resources, deep reinforcement learning (DRL) has been proposed as one of the most promising solutions to realize real-time and autonomous control for future carbon-neutral power systems. In particular, DRL-based frequency control approaches have been extensively investigated to overcome the limitations of model-based approaches, such as the computational cost and scalability for large-scale systems. Nevertheless, the real-world implementation of DRLbased frequency control methods is facing the following fundamental challenges: 1) safety guarantee during the learning and decision-making processes; 2) adaptability against the dynamic system operating conditions. To this end, this is the first work that proposes an Adaptive and Safe-Certified DRL (AdapSafe) algorithm for frequency control to simultaneously address the aforementioned challenges. In particular, a novel self-tuning control barrier function is designed to actively compensate the unsafe frequency control strategies under variational safety constraints and thus achieve guaranteed safety. Furthermore, the concept of meta-reinforcement learning is integrated to significantly enhance its adaptiveness in non-stationary power system environments without sacrificing the safety cost. Experiments are conducted based on GB 2030 power system, and the results demonstrate that the proposed AdapSafe exhibits superior performance in terms of its guaranteed safety in both training and test phases, as well as its considerable adaptability against the dynamics changes of system parameters.

Modified Fractional Order PID Controller for Load Frequency Control of Four Area Thermal Power System

This paper presents the development of a modified Fractional Order Proportional Integral Derivative (FOPID) controller to mitigate frequency deviation in a four-area thermal power system. Change in load demand and noisy power system environment can cause frequency deviation. Reducing high-frequency deviation is very paramount in load frequency control. This is because large frequency deviation can cause the transmission line to be overloaded, which may damage transformers at the transmission level, damage mechanical devices at the generating stations and also damage consumer devices at the distribution level. The conventional PID has been widely used for this problem. However, the parameter values of the various generating units of the power system like generators, turbines and governors keep changing due to numerous on/off witching in the load side. As such, it is essential that the control strategy applied should have a good capability of handling uncertainties in the system parameters and good disturbance rejection. Fractional order PID controller is known to give a higher phase margin resulting in very good disturbance rejection, robustness to high-frequency noise and elimination of steady-state error. A four-area power system was designed, and FOPID was used as the supplementary controller to mitigate frequency deviation. Ant Lion Optimizer (ALO) algorithm was used to optimize the gains of the FOPID controller by minimizing Integral Square Error (ISE) as the objective function. Results obtained outperformed other designed methods available in the literature in terms of reducing frequency deviation, tie-line power deviation and area control error.

Construction of an economic environment scheduling system based on the multi-objective fuzzy optimization model

Abstract To integrate the combination of electric vehicles and wind power of the transmission system, a wind farm environment multi-objective transmission model considering plug-in electric vehicles was established. The fuzzy optimal scheduling model for the environment and economy target of wind farm power system considering grid interconnection of electric vehicles designed by the author has the following characteristics: A fuzzy multi-objective dynamic scheduling model for the design of wind farm power system considering grid connection of plug-in electric vehicle is established, and the original 10 systems are taken as an example for power system design. The results show that the better model shows that the electric vehicle grid connection can greatly reduce the disadvantage of wind power stochastic uncertainties of system scheduling. The model can be used under different conditions further analyzing the rationality of the model determined by the author. An improved particle swarm optimization algorithm is used to solve this problem. The model takes the environmental and economic benefits into account, which improves the efficiency of the model.

Analysis of Wireless Communication Over Electromagnetic Impulse Noise Channel

Wireless communication in power grid environment faces peculiar power system environment specific noise. Owing to its impulsive nature, the characterization of such noise is critically important and fundamentally different from the existing analysis. This paper presents a theoretical analysis of the impact of power system electromagnetic impulse noise in smart grid environment on the performance of wireless communication between the grid health monitoring devices (e.g., Phasor Measurement Units) and the local data concentrator. It uses a classical approach to the derivation of a re-parameterized impulse noise model from its characteristic function. A comparison of outage probability between the corona impulse noise (CIN)-ridden and noise-free channel is studied. The study is extended for comparison with co-channel interference (CCI) for establishing a better understanding of the power specific electromagnetic impulse noise. A modified performance metric called signal-to-pulse-noise ratio is defined and its probability distribution is derived and compared with the additive white Gaussian noise, CIN and CCI-ridden channel statistics. The physical layer wireless channel characterization analysis is extended further to study the average system throughput via Markov modeling of the channel.

Analysis of the System Impact upon Thyristor Controlled Series Capacitor Relocation Due to Changes in the Power System Environment

Owing to geographical and political influences, Korea has an independent electric power system and the highest density of electric power facilities in the world. Large-scale base power generation complexes are located in non-metropolitan coastal areas, while the most expensive combined cycle power plants are operating or under construction in the metropolitan areas, which have the largest electricity demand. It has become difficult to secure a site for power plants, and the existing power transmission network is insufficient because of the additional construction of generators in existing power generation complexes, the increase in capacity of facilities, and the rapid increase in new and renewable energy. In particular, the East Coast region has a problem of transient stability for this reason, which is being addressed in advance through power generation restrictions. In addition, TCSC (Thyristor Controlled Series Capacitor) is installed and operated to expand the capacity of existing power transmission lines and improve stability in the failures of nearby high-voltage lines until new transmission lines that take more than 10 years are installed to resolve power generation restrictions. However, after the construction of a new transmission line, the efficiency of the existing TCSC is degraded, and for efficient use, it is necessary to rearrange the installation location to utilize the optimal TCSC according to changes in the configuration of the nearby power system. Moreover, a detailed analysis is needed on whether the TCSC designed according to the existing grid configuration exhibits accurate control performance even after the relocation and whether it interferes with nearby generators. In addition to the dynamic performance based on real-time simulations, it is necessary to study the control performance and interaction for this power electronic equipment. This study verified the need to change controller parameters, the interaction effect with nearby generators for stable operation, and the system effect of TCSC relocation using the same replica controller as the actual field controller, as well as RTDS (Real Time Digital Simulation) simulating the entire power transmission system.

Frequency regulation analysis for renewable bio generated autonomous multi-microgrid using moth flame optimized fractional order controller

Microgrid is considered as an active cell for grid control and management in the modern power system environment. The load frequency control of multi-micro-grid consisting of two micro-grid connected through a tie-line is discussed in these paper. In order to achieve this, a mathematical model is proposed based on renewable energy resources with multi-load perturbations. The proposed microgrid-1 consists of Hydro, variable load, Solar Photo Voltaic (SPV), Bio Gas Turbine Generator (BGTG), Battery Energy Storage System (BESS) and while, the proposed microgrid-2 consist of Battery Energy Storage System (BESS), Solar Photo Voltaic (SPV), Hydro, Biodiesel Engine Generator (BDEG) and variable Load. During a disturbance in the system frequency the instant load sources is tackle by BESS, BDEG and BGTB. Fractional-Proportional-Integral-Derivative (FPID), Proportional-Integral-Derivative (PID) and Proportional-Integral (PI) where use to controls the load frequency of the proposed multi-micro-grid systems. The variable values (gain) of the controllers where considered as a control variable and integral square error (ISE) considered as being a fitness function of the optimization algorithm. The performance in relations of the dynamic response of the controllers are deliberate using different optimization techniques namely, Firefly algorithm (FA), Ant Lion Optimization (ALO) and Moth Flame Optimization (MFO) algorithm.

Comparison of Algorithms for the AI-Based Fault Diagnostic of Cable Joints in MV Networks

Electrical utilities and system operators (SOs) are constantly looking for solutions to problems in the management and control of the power network. For this purpose, SOs are exploring new research fields, which might bring contributions to the power system environment. A clear example is the field of computer science, within which artificial intelligence (AI) has been developed and is being applied to many fields. In power systems, AI could support the fault prediction of cable joints. Despite the availability of many legacy methods described in the literature, fault prediction is still critical, and it needs new solutions. For this purpose, in this paper, the authors made a further step in the evaluation of machine learning methods (ML) for cable joint health assessment. Six ML algorithms have been compared and assessed on a consolidated test scenario. It simulates a distributed measurement system which collects measurements from medium-voltage (MV) cable joints. Typical metrics have been applied to compare the performance of the algorithms. The analysis is then completed considering the actual in-field conditions and the SOs’ requirements. The results demonstrate: (i) the pros and cons of each algorithm; (ii) the best-performing algorithm; (iii) the possible benefits from the implementation of ML algorithms.

A review of time reversal-based methods applied to fault location in power networks

Electromagnetic time reversal (EMTR)-based methods have been applied to the problem of fault location in power networks since 2012. Over the past decade, considerable theoretical investigations have led to a continuous improvement of the EMTR method in terms of fault location accuracy and efficiency. Meanwhile, different full-scale experiments, including pilot tests, were carried out, demonstrating the applicability and robustness of the EMTR method when applied to real power-system environments. This paper presents a review of the foregoing theoretical and experimental studies. Furthermore, suggestions for future studies are propounded, along with discussing various challenging research questions that still need to be addressed.

Comparison of robust machine-learning and deep-learning models for midterm electrical load forecasting

Electrical load forecasting (ELF) is gaining importance especially due to the severe impact of climate change on electrical energy usage and dynamically evolving smart grid technologies in the last decades. In this regard, medium-term load forecasting, a crucial need for power system planning (generation optimization and outages plan) and operation control, has become prominent in particular. Machine learning and deep learning-based techniques are currently trending approaches in electrical load estimation due to their capability to model complex non-linearity, feature abstraction and high accuracy, especially in the smart power systems environment.
 In this study, several load forecasting models based on machine learning methods which comprise linear regression (LR), decision tree (DT), random forest (RF), gradient boosting, adaBoost, and deep learning techniques such as recurrent neural network (RNN) and long short-term memory (LSTM) are studied for medium-term electrical load demand forecasting at an aggregated level. Performance metric results of these analyzes are presented in detail. State-of-the-art feature selection models are examined on the dataset and their effects on these forecasting methods are evaluated. Numerical results show that forecasting performance can be significantly improved. These results are validated by the results of other studies on the subject and found to be superior.