This study introduces a sophisticated supervised machine learning method for electric theft detection utilizing a customized Histogram Gradient Boosting (HGB) algorithm. Comprehensive preprocessing, including imputation, normalization, outlier management, and resampling, ensures the timeseries data is accurately prepared for analysis. The SMOTEENN algorithm corrects class imbalances, preparing the data for the feature optimization stage where crucial features are selected and extracted. The HGB algorithm, enhanced through Bayesian optimization, is central to the training process, resulting in a model that precisely classifies electricity consumption patterns as genuine or fraudulent. The robustness of the model is assessed against other recognized boosting methods, such as Adaptive Boosting (ADB), Gradient Boosting Decision Tree (GBDT), and LightGBM, alongside various ensemble and traditional machine learning models. Utilizing key performance metrics like accuracy, F1 score, and AUC for validation, the proposed model yields very promising results, with a 93% accuracy, 95% F1 score, and 98% AUC, outperforming the comparison group under similar dataset and hyperparameter conditions. This underscores the model’s potential as a highly accurate tool for combating electricity theft within an advanced metering infrastructure (AMI).

Presents a graph-learning framework that fuses energy, mobility, and environmental indicators to benchmark innovation ecosystems across U.S. metros.

This article presents a data-driven framework for policy-oriented benchmarking and catalyzation of innovation productivity across 65 U.S. metropolitan areas. The study achieves a high level of research rigor by integrating multiple complementary analytical modules and systematically validating results through robust statistical and diagnostic tests. Specifically, the methodological design synthesizes three components: First, a multifeature selection pipeline that combines random forest, select K-best, and recursive feature elimination to ensure statistically reliable identification of innovation determinants; second, kernel principal component analysis with parameterized kernel functions optimized to capture complex nonlinear interdependencies among innovation factors; and third, a particle swarm optimization-enhanced gradient boosting machine that delivers exceptional predictive accuracy (R2 = 0.984, RMSE = 358.0) while demonstrating minimal overfitting (R2 differential between training and testing = 0.016). Rigor is further reinforced through systematic residual analysis and comprehensive sensitivity analysis, which together provide robust validation of the framework's reliability. These diagnostics reveal significant regional disparities in innovation performance relative to model predictions, with striking counterintuitive results. Several metropolitan areas substantially outperform expectations through strategic ecosystem alignment and policy coherence, while others exhibit considerable innovation deficits despite apparent structural advantages. Sensitivity analysis identifies STEM education infrastructure as the most influential driver of innovation, challenging conventional policy assumptions. The empirically validated framework equips engineering managers and policymakers with actionable, quantitative insights for designing targeted interventions, allocating resources effectively, and transforming underperforming regions into resilient innovation ecosystems through evidence-based strategies.

Innovation is a fundamental driver of economic growth, regional competitiveness, and societal well-being. Nonetheless, its benefits remain unevenly distributed, with many regions, so called "innovation deserts," struggling to translate potential into productivity due to systemic barriers and limited insight into the drivers of innovation. Motivated by this disparity, this article presents a novel data-driven framework for analyzing and benchmarking innovation productivity across the U.S. counties, identifying key determinants that drive regional innovation performance. The study covers over 3,200 U.S. counties and includes 108 attributes spanning innovation outputs, demographics, education levels, STEM participation, internet connectivity, business sizes, and economic indicators. The framework comprises three integrated modules: (1) a hybrid feature selection mechanism combining random forest importance scores with mutual information criteria; (2) a nonlinear dimensionality reduction module employing kernel-based principal component analysis; and (3) a particle swarm optimized XGBoost model (PSO-XGBoost) enabling sensitivity analysis and scenario-based forecasting. The framework demonstrates superior predictive performance (R² > 0.81) compared to five state-of-the-art boosting algorithms, offering policymakers interpretable, actionable insights for evidence-based regional innovation development.

To avoid serious disturbances in both smart grids and traditional utility grids due to overloads, the balance between electricity generation and load demand must be optimally maintained. To achieve this, accurate electricity load forecasting offers necessary tools for energy suppliers and stakeholders to increase their profitability from renewable energy resources and meet the ever-growing electricity demand. However, despite extensive research efforts, the nonlinear dynamics of power system and complex load data continue to challenge the forecasting accuracy. This paper presents a novel stacked ensemble framework that integrates, adaptive boosting (AdaBoost), light gradient boosting machine (LGBM) and multi-layer perceptron (MLP) as initial learners, with the Kolmogorov-Arnold Network (KAN) as a meta-learner for short-term electric load forecasting (STLF). The proposed framework generates meta-data from the outputs of the initial learners, which are then used by KAN to produce final predictions. The KAN utilizes learnable, spline-based activation functions, which allow for dynamic adaptation to complex and nonlinear load patterns. Additionally, a fusion-based feature selection (FFS) technique, incorporating grey correlation analysis (GCA) and ReliefF, is developed to capture both correlation-based and instance-based feature importances. This ensures adaptability of the framework to data dimensionality and enhances accuracy. Experimental validation on the ISO-NE dataset demonstrates that the proposed framework achieves better prediction accuracy and reduced error metrics compared to existing advanced frameworks, while showing a modest increase in training time over multiple forecast horizons.

Electricity theft (ET) is a critical contributor to non-technical losses (NTLs) that significantly threaten the efficiency and reliability of power grids, leading to increased power wastage and financial losses. Despite the development of various artificial intelligence (AI)-based machine learning (ML) and deep learning (DL) approaches for electricity theft detection (ETD), existing methods often exhibit limitations in memorization and generalization, mainly when applied to large-scale electricity consumption datasets characterized by high variance, missing values, and complex nonlinear relationships. These challenges can result in models needing high variance and bias, reducing their effectiveness in accurately predicting electricity theft cases. To address these limitations, we propose a three-layer framework that employs a stacking ensemble model to combine the benefits of both ML and DL algorithms. During the first stage of data preprocessing, missing data is imputed through data interpolation, while the normalization is done through min–max scaling. To solve the high-class imbalance problem prevalent in most real-world datasets, we combine borderline synthetic minority oversampling techniques and near-miss undersampling strategies. In the final layer of our proposed ETD framework, we employ four ML base and five meta-classifiers. The outputs of base classifiers are aggregated and passed to a meta-classifier, where we evaluate recurrent neural networks (RNN) and convolutional neural network (CNN) as potential meta-classifiers. The RNN are long short-term memory (LSTM), gated recurrent unit (GRU), Bi-directional LSTM (Bi-LSTM) and Bi-directional GRU (Bi-GRU), respectively. Experimental outcomes show that the proposed Bi-GRU better achieves accuracy enhancement of detection in general than meta-classifiers and other state-of-the-art models used for ETD.

Neural networks have been widely used for electricity theft detection recently. However, their decision-making process is often not transparent, which limits the understanding of the basis for their decisions. To address this limitation, this letter proposes an explainable electricity theft detection method with gradient-weighted class activation mapping (Grad-CAM). Specifically, Grad-CAM is extended to generate fraud scores by computing the gradient-based importance of input features, highlighting suspicious activities. Simulation results show that the proposed Grad-CAM can provide accurate and reliable decision rationale. Compared with Shapley additive explanations and local interpretable model-agnostic explanations, the balanced detection score of the proposed Grad-CAM increased by 13.38% and 72.53%, respectively.

This paper addresses the challenge of maximizing power extraction in offshore wind energy systems through the development of an enhanced maximum power point tracking (MPPT) control strategy. Offshore wind energy is inherently intermittent, leading to discrepancies between power generation and electricity demand. To address this issue, we propose three advanced control algorithms to perform a comparative analysis: sliding mode control (SMC), the Integral Backstepping-Based Real-Twisting Algorithm (IBRTA), and Feed-Back Linearization (FBL). These algorithms are designed to handle the nonlinear dynamics and aerodynamic uncertainties associated with offshore wind turbines. Given the practical limitations in acquiring accurate nonlinear terms and aerodynamic forces, our approach focuses on ensuring the adaptability and robustness of the control algorithms under varying operational conditions. The proposed strategies are rigorously evaluated through MATLAB/Simulink 2024 A simulations across multiple wind speed scenarios. Our comparative analysis demonstrates the superior performance of the proposed methods in optimizing power extraction under diverse conditions, contributing to the advancement of MPPT techniques for offshore wind energy systems.

The role of electricity theft detection (ETD) is critical to maintain cost-efficiency in smart grids. However, existing ETD methods cannot efficiently handle the sheer volume of data now available, being limited by issues such as missing values, high variance and non-linearity. An integrated infrastructure is also required for synchronizing diverse procedures in electricity theft classification. To help address such problems, a novel ETD framework is proposed that combines three distinct modules. The first module handles missing values, outliers, and unstandardised electricity consumption data. The second module employs a newly proposed hybrid class balancing approach to deal with highly imbalanced datasets. The third module utilises an improved artificial neural network (iANN) based classification engine, to predict electricity theft cases accurately and efficiently. We propose three distinctive mechanisms, including hyper-parameters tuning, regularization and skip connections, to improve the performance of standard ANN to handle more complex classification tasks using smart meter (SM) data. Furthermore, various structures of iANN are investigated to improve the generalization and function fitting capabilities of the final classification. Numerical results from real-world energy usage datasets confirm that the proposed ETD model has superior performance compared to existing machine learning and deep learning methods, and can effectively be applied to industrial applications.

The role of electricity theft detection (ETD) is critical to maintain cost-efficiency in smart grids. However, existing methods for theft detection can struggle to handle large electricity consumption datasets because of missing values, data variance and nonlinear data relationship problems, and there is a lack of integrated infrastructure for coordinating electricity load data analysis procedures. To help address these problems, a simple yet effective ETD model is developed. Three modules are combined into the proposed model. The first module deploys a combination of data imputation, outlier handling, normalization and class balancing algorithms, to enhance the time series characteristics and generate better quality data for improved training and learning by the classifiers. Three different machine learning (ML) methods, which are uncorrelated and skillful on the problem in different ways, are employed as the base learning model. Finally, a recently developed deep learning approach, namely a temporal convolutional network (TCN), is used to ensemble the outputs of the ML algorithms for improved classification accuracy. Experimental results confirm that the proposed framework yields a highly-accurate, robust classification performance, in comparison to other well-established machine and deep learning models and thus can be a practical tool for electricity theft detection in industrial applications.

Everything goes down if you do not have power: the nancial sector, re neries and water. The grid underlies the rest of the countrys critical infrastructure. This thesis focuses on four speci c problems to balance demand-supply gap with higher reliability, e ciency and economical operation of the modern power grid. The rst part investigates the economic dispatch problem with uncertain power sources. The classic economic dispatch problems seek thermal power generation to meet the demand most e ciently. However, this project exploits two di erent power sources such as wind and solar power generation into the standard optimal power ow framework. The stochastic nature of renewable energy sources (RES) is modeled using Weibull and Lognormal probability density functions. The system-wide economic aspect is examined with additional cost functions such as penalty and reserve costs for under and overestimating the imbalance of RES power outputs. Also, a carbon tax is imposed on carbon emissions as a separate objective function to enhance the contribution of green energy. The calculation of best power dispatch is proposed using a cost function.

The second part investigates demand-side management (DSM) strategies to min imize energy wastage by changing the time pattern and magnitude of utility load at the consumer side. The main objective of DSM is to atten the demand curve by encouraging end-users to shift energy consumption to o-peak hours or to con sume less power during peak times. It is more appropriate to follow the generation pattern in many cases instead of attening the demand curve. It becomes more challenging when the future grid accommodates the penetration of distributed en ergy resources in a greater manner. In both scenarios, there is an ultimate need to control energy consumption. E ective DSM strategies would help to get an accu rate balance between both ends, i.e., the supply-side and demand-side, e ectively reducing power demand peaks and more e cient operation of the whole system.

The gap between power demand and supply can be balanced if power peak loads are minimized. The third part of the thesis then focuses on modeling the con sumption behavior of end-users. For this purpose, a novel arti cial intelligence and machine learning-based forecasting model is developed to analyze big data in the smart grid. Three modules namely feature selection, feature extraction and classi cation are proposed to solve big data problems such as feature redundancy and high dimensionality to generate quality data for classi er training and better prediction results.

The last part of this thesis investigates the problem of electricity theft to minimize non technical losses and power disruptions in the power grid. Electricity theft with its many facets usually has an enormous cost to utilities compared to non-payment because of energy wastage and power quality problems. With the recognition of the internet of things (IoT) technologies and data-driven approaches, power utilities have enough tools to combat electricity theft and fraud. An integrated framework is proposed that combines three distinct modules such as data preprocessing, data class balancing and nal classi cation to make accurate electrical consumption theft predictions in smart grids.

The result of our solution to balance the electricity demand-supply gap can pro vide helpful information to grid planners seeking to improve the resilience of the power grid to outages and disturbances. All parts of this thesis include extensive experimental results on case studies, including realistic large-scale instances.

In Smart Grids (SG), Electricity Theft Detection (ETD) is of great importance because it makes the SG cost-efficient. Existing methods for ETD cannot efficiently handle data imbalance, missing values, variance and non-linear data problems in the smart meter data. Therefore, an effective integrated strategy is required to address underlying issues and accurately detect electricity theft using big data. In this work, a simple yet effective approach is proposed by integrating two different modules, such as data pre-processing and classification, in a single framework. The first module involves data imputation, outliers handling, standardization and class balancing steps to generate quality data for classifier training. The second module classifies honest and dishonest users with a Support Vector Machine (SVM) classifier. To improve the classifier’s learning trend and accuracy, a Bayesian optimization algorithm is used to tune SVM’s hyperparameters. Simulation results confirm that the proposed framework for ETD significantly outperforms previous machine learning approaches such as random forest, logistic regression and SVM in terms of accuracy.

This work focuses on implementing the optimal power flow (OPF) problem, considering wind, solar and hydropower generation in the system. The stochastic nature of renewable energy sources (RES) is modelled using Weibull, Lognormal and Gumbel probability density functions. The system-wide economic aspect is examined with additional cost functions such as penalty and reserve costs for under and overestimating the imbalance of RES power outputs. Also, a carbon tax is imposed on carbon emissions as a separate objective function to enhance the contribution of green energy. For solving the optimization problem, a simple and efficient augmentation to the basic grey wolf optimization (GWO) algorithm is proposed, in order to enhance the algorithm's exploration capabilities. The performance of the new augmented GWO (AGWO) approach, in terms of robustness and scalability, is confirmed on IEEE-30, 57 and 118 bus systems. The obtained results of the AGWO algorithm are compared with modern heuristic techniques for a case of OPF incorporating RES. Numerical simulations indicate that the proposed method has better exploration and exploitation capabilities to reduce operational costs and carbon emissions.

Electricity load forecasting has always been a significant part of the smart grid. It ensures sustainability and helps utilities to take cost-efficient measures for power system planning and operation. Conventional methods for load forecasting cannot handle huge data that has a nonlinear relationship with load power. Hence an integrated approach is needed that adopts a coordinating procedure between different modules of electricity load forecasting. We develop a novel electricity load forecasting architecture that integrates three modules, namely data selection, extraction, and classification into a single model. First, essential features are selected with the help of random forest and recursive feature elimination methods. This helps reduce feature redundancy and hence computational overhead for the next two modules. Second, dimensionality reduction is realized with the help of a t-stochastic neighbourhood embedding algorithm for the best feature extraction. Finally, the electricity load is forecasted with the help of a deep neural network (DNN). To improve the learning trend and computational efficiency, we employ a grid search algorithm for tuning the critical parameters of the DNN. Simulation results confirm that the proposed model achieves higher accuracy when compared to the standard DNN.

Today's electricity grid is rapidly evolving, with increased penetration of renewable energy sources (RES). Conventional Optimal Power Flow (OPF) has non-linear constraints that make it a highly non-linear, non-convex optimisation problem. This complex problem escalates further with the integration of RES, which are generally intermittent in nature. In this article, an optimal power flow model combines three types of energy resources, including conventional thermal power generators, solar photovoltaic generators (SPGs) and wind power generators (WPGs). Uncertain power outputs from SPGs and WPGs are forecasted with the help of lognormal and Weibull probability distribution functions, respectively. The over and underestimation output power of RES are considered in the objective function i.e. as a reserve and penalty cost, respectively. Furthermore, to reduce carbon emissions, a carbon tax is imposed while formulating the objective function. A grey wolf optimisation technique (GWO) is employed to achieve optimisation in modified IEEE-30 and IEEE-57 bus test systems to demonstrate its feasibility. Hence, novel contributions of this work include the new objective functions and associated framework for optimising generation cost while considering RES; and, secondly, computational efficiency is improved by the use of GWO to address the non-convex OPF problem. To investigate the effectiveness of the proposed GWO-based approach, it is compared in simulation to five other nature-inspired global optimisation algorithms and two well-established hybrid algorithms. For the simulation scenarios considered in this article, the GWO outperforms the other algorithms in terms of total cost minimisation and convergence time reduction.

In this paper, an artificial neural network (ANN) based methodology is proposed to forecast electricity load and price. The performance of an ANN forecast model depends on appropriate input parameters. Parameter tuning of ANN is very important to increase the accuracy of electricity price and load prediction. This is done using mutual information and decision tree. After selecting best features for forecasting, these features are given to forecasting engine working on principles of recurrent neural network (RNN). For simulations, dataset is taken from national electricity market (NEM), Australia. Results show that the methodology has increased the accuracy of electricity load and price forecast. Whereas, the error rate of forecasting is lower than the other models for electricity load and price.

Optimal power flow (OPF) problem has become more significant for operation and planning of electrical power systems because of the increasing energy demand. OPF is very important for system operators to fulfill the electricity demand of the consumers efficiently and for the reliable operation of the power system. The key objective in OPF is to reduce the total generating cost while assuring the system limitations. Due to environmental emission, depletion of fossil fuels and its higher prices, integration of renewable energy sources into the grid is essential. Classical OPF, which consider only thermal generators is a non-convex, non-linear optimization problem. However, incorporating the uncertain renewable sources adds complexity to the problem. A metaheuristic algorithm which solves the OPF problem with renewable energy sources is to be implemented on a modified IEEE 30-bus system.

Smart grid provides an opportunity for customers as well as for utility companies to reduce electricity costs and regulate generation capacity. The success of scheduling algorithms mainly depends upon accurate information exchange between main grids and smart meters. On the other hand, customers are required to schedule loads, respond to energy demand signals, participate in energy bidding and actively monitor energy prices generated by the utility company. Strengthening communication infrastructure between the utility company and consumers can serve the purpose of consumer satisfaction. We propose a heuristic demand side management model for scheduling smart home appliances in an automated manner, to maximize the satisfaction of the consumers associated with it. Simulation results confirm that the proposed hybrid approach has the ability to reduce peak-to-average ratio of the total energy demand and reduce the total cost of the energy without compromising user comfort.

The purpose of this paper is to study the theocratical work for a new type of wind power system. This wind system, called Wing oscillating coil rod pendulum system. This is a small prototype that generates low current and voltage. This system is a new type of wind turbine, to generate energy by using wind. One of the main elements of this system is a copper coil pendulum with flapping wing attached to it which oscillates at a low frequency when wind strikes it. The wind blowing kinetic energy compels the pendulum to oscillate, so the kinetic energy of wind is converted into oscillating energy of pendulum. The oscillating energy is then converted into electrical energy by using a semicircle shaped permanent magnet, which is placed under the coil rod pendulum. Theocratical construction and electrical design of wing oscillating coil rod pendulum system is discussed in this paper.