Toward Developing Genetic Algorithms to Aid in Critical Infrastructure Modeling

This paper presents the fusion of artificial intelligence (AI) learning algorithms that are genetic algorithms (GA) and conjugate gradient (CG) methods. Both methods are used to find the optimum weights for the hidden and output layers of feedforward artificial neural network (ANN) model. Each algorithm is presented in separate module and we proposed three different types of Dynamic Connection Strategies (DyConS) for combining both algorithms to improve the recognition performance of spoken Malay speech recognition. Two different GA techniques are used in this research: a mutated GA technique is proposed and compared with the standard GA technique. One hundred experiments with 5000 words are conducted using the proposed DyConS. Owing to previous facts, GA combined with ANN proved to attain certain advantages with sufficient recognition performance. Thus, from the results, it was observed that the performance of mutated GA algorithm when combined with CG is better than standard GA and CG models. Integrating the GA with feed-forward network improved mean square error (MSE) performance and with good connection strategy by this two stage training scheme, the recognition rate is increased up to 99%.

Genetic algorithms (GA) have been applied in many fields to solve multivariable, non linear optimization problems. There are lots of different GA techniques which are used to improve the performance of the algorithm. In this paper, the implementation of GA in optimization of electrical system design for offshore wind farms is proposed and several different GA techniques are investigated. The main problems of GA implementation in this field are addressed and the suitable GA techniques are proposed. The GA method is applied to a real offshore wind farm and the results are evaluated. It is concluded that the genetic algorithm is suitable for the optimization of offshore wind farm layout design as long as proper GA techniques are employed

In this paper Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) techniques has been used for active power loss minimization through optimally placing the Unified Power Flow Controller (UPFC) in the power system network. Two objective functions are taken as the indexes of the system performance; identification of suitable buses using line loss sensitivity index and minimization of active power losses by employing PSO and GA techniques. For the validation and comparison purposes of the proposed techniques, simulations are carried out on modified IEEE 14-bus power system. The results obtained shows that PSO is an easy to use, robust and fast optimization technique compared to GA.

In this paper, we present a comprehensive and in-depth investigation on the optimization of Proportional-Integral (PI) controller tuning for achieving stability and desired overshoot in the step response. The main objective of this study is to compare the effectiveness of Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) techniques in finding the optimal parameters for the PI controller. The PI controller is a widely used control algorithm that plays a crucial role in many industrial processes. Its tuning greatly affects the system's performance, particularly in terms of stability and overshoot. Therefore, finding the optimal tuning parameters is of utmost importance. To address this optimization problem, we propose the utilization of two popular metaheuristic algorithms, GA and PSO. These algorithms are known for their ability to efficiently search through large solution spaces and find near-optimal solutions. By applying these algorithms to the PI controller tuning problem, we aim to determine which technique yields better results in terms of stability and overshoot tuning. In our comparative study, we provide a detailed explanation of both GA and PSO algorithms, focusing on their working principles and mathematical formulations. We also describe how these algorithms can be applied to the PI controller tuning problem. Furthermore, we highlight the key differences between GA and PSO, shedding light on their strengths and weaknesses. To assess the performance of GA and PSO, we conduct several experiments using different benchmark functions and step response models. We measure the stability and overshoot metrics for various parameter settings obtained through GA and PSO. By thoroughly analyzing the obtained results, we draw meaningful conclusions regarding the effectiveness of each technique. Our findings demonstrate that both GA and PSO exhibit promising results in optimizing PI controller tuning. These observations provide valuable insights and guidelines for choosing the appropriate algorithm based on specific control requirements. In conclusion, this comparative study is thought to contribute to the field of control systems engineering by offering a comprehensive analysis of GA and PSO techniques in the context of PI controller tuning. By highlighting their strengths and weaknesses, it is aimed to provide researchers and practitioners with valuable information for making informed decisions when optimizing control parameters for stability and overshoot reduction purposes.

Industrial control systems (ICSs) are crucial in managing critical infrastructure, making their security a paramount concern. In recent years, their widespread adoption, together with the overall distance spanned by the critical infrastructure of industrial communication networks, have increased the complexity of the networks’ topological arrangement, increasing their structural vulnerabilities. In this scenario, deep learning models, especially those that incorporate graph-aware mechanisms, have arisen as a promising solution. This paper presents a novel centrality-and graph-aware attack detector (CGAAD) that includes nodes’ significance by centrality measures within a graph convolution network (GCN) framework to provide superior cyberattack detection performance and increase the resilience of critical ICS infrastructure. The proposed CGAAD model is in three parts. First, centrality measures are used as features for each of the nodes in the ICS graph topology. Then, a sparse-autoencoder (sparse-AE) enhances the feature representations to harness the subsequent classification step. Finally, the GCN leverages the graph structure and the enhanced features to classify dataflow between nodes as either normal or attacked. Experimental results demonstrate promising performance, reaching nearly 99% in terms of accuracy and F1-score, reducing misclassifications of both normal and attacked samples, which is crucial in ICS critical infrastructure applications.

Optimum design of structures under time-variable loadings is a difficult task. Time-dependent behavior of constraints and cost of gradients calculations could be mentioned when applying time history loadings in the optimization problems. To overcome these difficulties, the response spectra as a seismic demand are used instead of using time history acceleration in the structural modeling. In this paper, the P-Delta effects are considered in the finite-element modeling of the frames. Furthermore, many practical constraints are included in the optimization formulation according to the Iranian national building code (Standard N. 2800). The developed MATLAB-based computer program is utilized for optimization of the low, intermediate- and relatively high-rise braced and un-braced steel frames. The obtained results of sequential quadratic programing (SQP) method are compared with the results of genetic algorithm (GA) technique for guarantying the global optimal designs. Because of the inexpensive costs of SQP method in comparison with genetic algorithm technique, SQP method could be confidently applied for obtaining the global optimum designs of the steel frames.

A genetic algorithm (GA) is used to design Spectrally Modulated, Spectrally Encoded (SMSE) waveforms while characterizing the impact of parametric variation on coexistence. As recently proposed, the SMSE framework supports cognition-based, software defined radio (SDR) applications and is well-suited for coexistence analysis. For initial proof-of-concept, two SMSE waveform parameters (number of carriers and carrier bandwidth) are optimized in a coexistent scenario to characterize SMSE impact on Direct Sequence Spread Spectrum (DSSS) bit error performance. Given optimization via GA techniques have been successfully applied in many engineering fields, as well as operations research, they are viable candidates for robust SMSE waveform design. As demonstrated, the analytic SMSE framework is well-suited for parametric optimization via GA techniques.

The thresholds of (n,xn) reactions in various activation detectors are commonly used to unfold the neutron spectra covering a broad energy span, i.e. from thermal to several hundreds of MeV. The saturation activities of the daughter nuclides (i.e. reaction products) serve as the input data of specific spectra unfolding codes, such as SAND-II and LOUHI-83. However, most spectra unfolding codes, including the above, require an a priori (guess) spectrum to starting up the unfolding procedure of an unknown spectrum. The accuracy and exactness of the resulting spectrum primarily depends on the subjectively chosen guess spectrum. On the other hand, the Genetic Algorithm (GA)-based spectra unfolding technique ANDI-03 (Activation-detector Neutron DIfferentiation) presented in this report does not require a specific starting parameter. The GA is a robust problem-solving tool, which emulates the Darwinian Theory of Evolution prevailing in the realm of biological world and is ideally suited to optimise complex objective functions globally in a large multidimensional solution space. The activation data of the 27Al(n,alpha)24Na, 116In(n,gamma)116mIn, 12C(n,2n)11C and 209Bi(n,xn)(210-x)Bi reactions recorded at the high-energy neutron field of the ISIS Spallation source (Rutherford Appleton Laboratory, UK) was obtained from literature and by applying the ANDI-03 GA tool, these data were used to unfold the neutron spectra. The total neutron fluence derived from the neutron spectrum unfolded using GA technique (ANDI-03) agreed within +/-6.9% (at shield top level) and +/-27.2% (behind a 60 cm thick concrete shield) with the same unfolded with the SAND-II code.

The timetabling problem is well known to be an NP-complete combinatorial problem. The problem becomes even more complex when addressed to individual timetables of students. The core of dealing with the problem in this application is a timetable builder based on mixed direct-indirect encoding evolved by a genetic algorithm with a self-adaptation paradigm, where the parameters of the genetic algorithm are optimized during the same evolution cycle as the problem itself. The aim of this paper is to present an encoding for self-adaptation of genetic algorithms that is suitable for timetabling problems. Compared to previous approaches we designed the encoding for self-adaptation of not only one parameter or several ones but for all possible parameters of genetic algorithms at the same time. The proposed self-adaptive genetic algorithm is then applied for solving the real university timetabling problem and compared with a standard genetic algorithm. The main advantage of this approach is that it makes it possible to solve a wide range of timetabling and scheduling problems without setting parameters for each kind of problem in advance. Unlike common timetabling problems, the algorithm was applied to the problem in which each student has an individual timetable, so we also present and discuss the algorithm for optimized enrollment of students that minimizes the number of clashing constraints for students.

Critical infrastructures such as power grid, water treatment plants, chemical plants, oil and gas refineries, transportation systems, etc., are examples of large-scale cyber-physical systems. In the recent years, there has been multitude of cyberattacks on such systems such as STUXNET attack in Iran, BlackEnergy malware and ransomware attacks on power distribution systems in Ukraine, and malware attacks on German Steel plant to mention a few. Critical infrastructure security is a major area of concern for all governments. In the United States, several laboratories such as Sandia National Lab, Idaho National Lab, and National Institutes of Standards have built critical infrastructure cyber-security experimentation test-beds. These test-beds are built with industry-scale equipment from various sectors of critical infrastructures to allow researchers to detect vulnerabilities in multitude of products that are used by utility companies in their systems and to research efficacy of their remediation techniques. These test-beds also allow utilities to bring in hardware and software products for hardware/software-in-the-loop testing for vulnerability detection or cyber-security product validation. In India, there has been no such test-bed for such research and validation activities. In the interdisciplinary center for cyber-security and cyber defense of critical infrastructures (C3i) at the Indian Institute of Technology Kanpur, we are building such a facility—a first in India. We already have built a lab-scale test-bed for power distribution automation and discovered a plethora of vulnerabilities in the architecture, protocols, and widely used products in our test-bed. In this article, we first describe the lab-scale test-bed to provide an insight into the utility of such a test-bed, and then we describe our ongoing development of industry-scale test-beds.

Based on cerebellar model articulation controller (CMAC), this paper attempts to propose a new chromosome representation scheme for representing real number parameters in genetic algorithms (GAs), which is termed CMAC-based GAs. The central idea of CMAC-based GAs is that each memory unit in a CMAC network is regarded as a real-valued gene in GAs. By this way, a chromosome is represented as those memory units addressed by a specific state and each gene involves partial information about a potential solution, not a potential solution as the conventional GAs. In addition, the corresponding crossover and mutation operators are also derived for the proposed GAs. The proposed CMAC-based GAs is applied to optimize the parameters of the proportional-integral-derivative controller. Simulation results are compared with several previous findings to demonstrate the search performance of the proposed method.

The article presents the current problems of protecting Ukraine’s critical infrastructure, current threats to its security and the need to organise proper counteraction under martial law. Threats to critical infrastructure include factors that can actually or potentially harm the stability of its operation, functionality, integrity, resilience or lead to its destruction. The purpose of the article is to create an up-to-date threat model that formalises the likely impacts on Ukraine’s critical infrastructure, which will improve the effectiveness of its protection. The scientific novelty of the article is that it examines the actual needs and problematic issues of forming a modern model of threats to critical infrastructure, primarily in the context of the ongoing full-scale military aggression of the russian federation against Ukraine. Creating a threat model is defined for critical infrastructure as a necessity to ensure effective protection of its facilities. The formation of a basic threat model for critical infrastructure facilities, which should include related models of the facility, situation and intruder, is currently an important element of the algorithm for solving this problem. The basic model of threats to critical infrastructure is the framework on which the state determines who and what it needs to protect itself from at the national level. However, Ukrainian legislation currently does not provide for the need to develop a model of threats to the national critical infrastructure, which negatively affects the state of its security and resilience. The perspective measures that will contribute to both the stable functioning of critical infrastructure facilities and ensure their proper protection are outlined: enshrining in Ukrainian legislation the need to develop a model of threats to critical infrastructure, adopting regulations on standardisation of risk management processes for critical infrastructure in order to prevent threats, and more.

By 2030, forecasts suggest that urban areas will house 60 percent of the world’s population and one in every three people will live in cities with at least half a million inhabitants. Within the same time frame, the number of global megacities is expected to jump from 33 today to 43 in 2030 [1]. Underpinning these large urban areas will be an interconnected network of critical physical infrastructures reliant on Internet-connected Industrial Control Systems and susceptible to increasingly sophisticated, e.g., AI-enabled, cyber threats. In hand, the cyber threat landscape is shifting rapidly. We are seeing a sharp rise in the number of cyberattacks on critical infrastructure [2] with significant impacts cascading across multiple sectors and causing disruption to the provisioning of essential goods and services. Security scholars suggest that these impacts are not always equitable and that disruption to critical infrastructure can affect vulnerable groups differently [3], which further emphasizes the need to improve cybersecurity between critical infrastructure sectors [4]. Through structured analysis of city statistics, demographic information, cyber incidents, and current cyber policy, our presentation will articulate potential social implications of megacity growth through the lens of cyber-physical infrastructure disruption. We investigate the largest 15 megacities in the world and find that megacities continue to grow in population but not in cyber policy. We highlight recent examples of cyber-physical disruption in Mumbai and New York City with focus on implications for vulnerable populations. Our work suggests the need for future research on social responsibility regarding security of these critical infrastructure sectors and on the need for technology-focused law, policy, and regulation guidelines.

Smart grid infrastructure is one of the critical infrastructure that combines the energy and telecommunications infrastructure and Internet networks. Thus, the smart grid must operate safely and meet the information security aspects. This research is a case study in smart electricity grid as critical infrastructure. The research objective is for improvement on critical infrastructure security policies based on case studies conducted. This research was conducted with the combined quantitative and qualitative method that combines the results of the risk assessment on the research object to the opinion of experts / practitioners. Results of this research is input to policy frameworks and securing of critical infrastructure.

A comparative study on the performance of dissortative mating and immigrants-based strategies for evolutionary dynamic optimization