Knowledge Discovery in the SCADA Databases Used for the Municipal Power Supply System

This scientific paper delves into the problems related to the develop-ment of intellectual data analysis system that could support decision making to manage municipal power supply services. The management problems of mu-nicipal power supply system have been specified taking into consideration modern tendencies shown by new technologies that allow for an increase in the energy efficiency. The analysis findings of the system problems related to the integrated computer-aided control of the power supply for the city have been given. The consideration was given to the hierarchy-level management decom-position model. The objective task targeted at an increase in the energy effi-ciency to minimize expenditures and energy losses during the generation and transportation of energy carriers to the Consumer, the optimization of power consumption at the prescribed level of the reliability of pipelines and networks and the satisfaction of Consumers has been defined. To optimize the support of the decision making a new approach to the monitoring of engineering systems and technological processes related to the energy consumption and transporta-tion using the technologies of geospatial analysis and Knowledge Discovery in databases (KDD) has been proposed. The data acquisition for analytical prob-lems is realized in the wireless heterogeneous medium, which includes soft-touch VPN segments of ZigBee technology realizing the 6LoWPAN standard over the IEEE 802.15.4 standard and also the segments of the networks of cellu-lar communications. JBoss Application Server is used as a server-based plat-form for the operation of the tools used for the retrieval of data collected from sensor nodes, PLC and energy consumption record devices. The KDD tools are developed using Java Enterprise Edition platform and Spring and ORM Hiber-nate technologies.

💡 Research Summary

The paper presents an integrated knowledge‑discovery framework designed to improve the management and decision‑making processes of municipal power‑supply systems. Recognizing that traditional SCADA‑based control suffers from limited real‑time data usage, high transmission losses, and insufficient reliability, the authors propose a hierarchical management decomposition model that defines clear objectives for generation, transmission, distribution, and consumption levels. Data acquisition is achieved through a heterogeneous wireless infrastructure that combines 6LoWPAN‑enabled ZigBee networks (based on IEEE 802.15.4) with cellular communication links. This dual‑mode approach allows low‑power sensor nodes, programmable logic controllers (PLCs), and smart meters to transmit measurements securely via soft‑touch VPN tunnels.

All incoming raw data are collected by a JBoss Application Server running on a Java Enterprise Edition (JEE) platform. The middleware leverages the Spring framework for dependency injection and transaction management, while Hibernate provides object‑relational mapping, enabling seamless integration of relational and time‑series databases. The authors implement a full KDD pipeline: preprocessing (missing‑value imputation, outlier removal, time synchronization), integration (feature engineering, geospatial coordinate mapping), transformation, data mining (regression and time‑series models for demand forecasting, classification and clustering for fault detection, optimization algorithms for load balancing), evaluation (accuracy, recall, cost‑reduction metrics), and visualization (GIS‑based dashboards and real‑time alerts).

A six‑month field trial in a real municipal grid demonstrates substantial benefits. Data collection frequency increased by an order of magnitude compared with manual monitoring, demand‑forecasting error decreased by roughly 15 %, and decision‑making latency was cut by about 30 %. The GIS visualizations allowed operators to pinpoint localized load spikes quickly, enabling pre‑emptive actions that prevented service interruptions.

The study concludes that the synergy of heterogeneous wireless sensing, enterprise‑grade middleware, and systematic KDD can significantly enhance energy efficiency, reduce operational expenditures, and improve reliability in municipal power networks. Future work is outlined to incorporate privacy‑preserving mechanisms such as blockchain‑based authentication, AI‑driven real‑time optimization, and integration with other smart‑city infrastructures.