A Data Mining-Based Dynamical Anomaly Detection Method for Integrating with an Advance Metering System

Building operations consume 30% of total power consumption and contribute 26% of global power-related emissions. Therefore, monitoring, and early detection of anomalies at the meter level are essential for residential and commercial buildings. This work investigates both supervised and unsupervised approaches and introduces a dynamic anomaly detection system. The system introduces a supervised Light Gradient Boosting machine and an unsupervised autoencoder with a dynamic threshold. This system is designed to provide real-time detection of anomalies at the meter level. The proposed dynamical system comes with a dynamic threshold based on the Mahalanobis distance and moving averages. This approach allows the system to adapt to changes in the data distribution over time. The effectiveness of the proposed system is evaluated using real-life power consumption data collected from smart metering systems. This empirical testing ensures that the system's performance is validated under real-world conditions. By detecting unusual data movements and providing early warnings, the proposed system contributes significantly to visual analytics and decision science. Early detection of anomalies enables timely troubleshooting, preventing financial losses and potential disasters such as fire incidents.

A Real-time Anomaly Detection Using Convolutional Autoencoder with Dynamic Threshold

The majority of modern consumer-level energy is generated by real-time smart metering systems. These frequently contain anomalies, which prevent reliable estimates of the series' evolution. This work introduces a hybrid modeling approach combining statistics and a Convolutional Autoencoder with a dynamic threshold. The threshold is determined based on Mahalanobis distance and moving averages. It has been tested using real-life energy consumption data collected from smart metering systems. The solution includes a real-time, meter-level anomaly detection system that connects to an advanced monitoring system. This makes a substantial contribution by detecting unusual data movements and delivering an early warning. Early detection and subsequent troubleshooting can financially benefit organizations and consumers and prevent disasters from occurring.

Adaptive Differential Evolution with Diversification: Addressing Optimization Challenges

The existing variants of the Differential Evolution (DE) algorithm come with certain limitations, such as poor local search and susceptibility to premature convergence. This study introduces Adaptive Differential Evolution with Diversification (ADED), a method that dynamically modifies the neighborhood structure by evaluating the trial solutions' fitness. Developed to work with both convex and nonconvex objective functions, ADED is validated with 22 benchmark functions, including Rosenbrock, Rastrigin, Ackley, and DeVilliers-Glasser02. The development is carried out in Google Cloud using Jupyter Notebook and Python v3.10.12, with additional testing conducted on the multi-objective benchmark ZDT test suite. ADED distinguishes itself with its adaptive and diverse approach, which includes adaptive mutation and crossover-rates, diverse mutation tactics, diversification measurements, local search mechanisms, and convergence monitoring. The unique combination of these features collectively enhances ADED's effectiveness in navigating complex and diverse landscapes, positioning it as a promising tool for addressing challenges in both single- and multi-objective optimization scenarios.

Advancements in Optimization: Adaptive Differential Evolution with Diversification Strategy

This study presents a population-based evolutionary optimization algorithm (Adaptive Differential Evolution with Diversification Strategies or ADEDS). The algorithm developed using the sinusoidal objective function and subsequently evaluated with a wide-ranging set of 22 benchmark functions, including Rosenbrock, Rastrigin, Ackley, and DeVilliersGlasser02, among others. The study employs single-objective optimization in a two-dimensional space and runs ADEDS on each of the benchmark functions with multiple iterations. In terms of convergence speed and solution quality, ADEDS consistently outperforms standard DE for a variety of optimization challenges, including functions with numerous local optima, plate-shaped, valley-shaped, stretched-shaped, and noisy functions. This effectiveness holds great promise for optimizing supply chain operations, driving cost reductions, and ultimately enhancing overall performance. The findings imply the importance of effective optimization strategy for improving supply chain efficiency, reducing costs, and enhancing overall performance.

Backorder Prediction in Inventory Management: Classification Techniques and Cost Considerations

This article introduces an advanced analytical approach for predicting backorders in inventory management. Backorder refers to an order that cannot be immediately fulfilled due to stock depletion. Multiple classification techniques, including Balanced Bagging Classifiers, Fuzzy Logic, Variational Autoencoder - Generative Adversarial Networks, and Multi-layer Perceptron classifiers, are assessed in this work using performance evaluation metrics such as ROC-AUC and PR-AUC. Moreover, this work incorporates a profit function and misclassification costs, considering the financial implications and costs associated with inventory management and backorder handling. The results demonstrate the effectiveness of the predictive model in enhancing inventory system service levels, which leads to customer satisfaction and overall organizational performance. Considering interpretability is a significant aspect of using AI in commercial applications, permutation importance is applied to the selected model to determine the importance of features. This research contributes to the advancement of predictive analytics and offers valuable insights for future investigations in backorder forecasting and inventory control optimization for decision-making.

Sampling - Variational Auto Encoder - Ensemble: In the Quest of Explainable Artificial Intelligence

Explainable Artificial Intelligence (XAI) models have recently attracted a great deal of interest from a variety of application sectors. Despite significant developments in this area, there are still no standardized methods or approaches for understanding AI model outputs. A systematic and cohesive framework is also increasingly necessary to incorporate new techniques like discriminative and generative models to close the gap. This paper contributes to the discourse on XAI by presenting an empirical evaluation based on a novel framework: Sampling - Variational Auto Encoder (VAE) - Ensemble Anomaly Detection (SVEAD). It is a hybrid architecture where VAE combined with ensemble stacking and SHapley Additive exPlanations are used for imbalanced classification. The finding reveals that combining ensemble stacking, VAE, and SHAP can. not only lead to better model performance but also provide an easily explainable framework. This work has used SHAP combined with Permutation Importance and Individual Conditional Expectations to create a powerful interpretability of the model. The finding has an important implication in the real world, where the need for XAI is paramount to boost confidence in AI applications.

Time-Series Forecasting: Unleashing Long-Term Dependencies with Fractionally Differenced Data

This study introduces a novel forecasting strategy that leverages the power of fractional differencing (FD) to capture both short- and long-term dependencies in time series data. Unlike traditional integer differencing methods, FD preserves memory in series while stabilizing it for modeling purposes. By applying FD to financial data from the SPY index and incorporating sentiment analysis from news reports, this empirical analysis explores the effectiveness of FD in conjunction with binary classification of target variables. Supervised classification algorithms were employed to validate the performance of FD series. The results demonstrate the superiority of FD over integer differencing, as confirmed by Receiver Operating Characteristic/Area Under the Curve (ROCAUC) and Mathews Correlation Coefficient (MCC) evaluations.

Ensemble Differential Evolution with Simulation-Based Hybridization and Self-Adaptation for Inventory Management Under Uncertainty

This study proposes an Ensemble Differential Evolution with Simula-tion-Based Hybridization and Self-Adaptation (EDESH-SA) approach for inven-tory management (IM) under uncertainty. In this study, DE with multiple runs is combined with a simulation-based hybridization method that includes a self-adaptive mechanism that dynamically alters mutation and crossover rates based on the success or failure of each iteration. Due to its adaptability, the algorithm is able to handle the complexity and uncertainty present in IM. Utilizing Monte Carlo Simulation (MCS), the continuous review (CR) inventory strategy is ex-amined while accounting for stochasticity and various demand scenarios. This simulation-based approach enables a realistic assessment of the proposed algo-rithm's applicability in resolving the challenges faced by IM in practical settings. The empirical findings demonstrate the potential of the proposed method to im-prove the financial performance of IM and optimize large search spaces. The study makes use of performance testing with the Ackley function and Sensitivity Analysis with Perturbations to investigate how changes in variables affect the objective value. This analysis provides valuable insights into the behavior and robustness of the algorithm.

Multiple Independent DE Optimizations to Tackle Uncertainty and Variability in Demand in Inventory Management

To determine the effectiveness of metaheuristic Differential Evolution optimization strategy for inventory management (IM) in the context of stochastic demand, this empirical study undertakes a thorough investigation. The primary objective is to discern the most effective strategy for minimizing inventory costs within the context of uncertain demand patterns. Inventory costs refer to the expenses associated with holding and managing inventory within a business. The approach combines a continuous review of IM policies with a Monte Carlo Simulation (MCS). To find the optimal solution, the study focuses on meta-heuristic approaches and compares multiple algorithms. The outcomes reveal that the Differential Evolution (DE) algorithm outperforms its counterparts in optimizing IM. To fine-tune the parameters, the study employs the Latin Hypercube Sampling (LHS) statistical method. To determine the final solution, a method is employed in this study which combines the outcomes of multiple independent DE optimizations, each initiated with different random initial conditions. This approach introduces a novel and promising dimension to the field of inventory management, offering potential enhancements in performance and cost efficiency, especially in the presence of stochastic demand patterns.