Enterprise System Integration For Distributed And Interoperable Architectures

Abstract

Modern enterprise environments require seamless integration of heterogeneous systems and real-time decision-making across distributed and interoperable architectures. However, traditional Enterprise Resource Planning (ERP) systems remain constrained by monolithic designs, limited interoperability, and inefficient processing of distributed CSV-based enterprise data, thereby restricting scalability and adaptive decision support. Research proposes a distributed enterprise system integration method explicitly designed for interoperable architectures, incorporating a novel Capuchin Search Graph Neural Network (CS-GNN). The proposed method adopts a cloud-based distributed architecture supported by service-oriented and Application Programming Interface (API)-driven interoperability to enable seamless communication among heterogeneous enterprise modules. Evaluation is conducted using a structured CSV dataset comprising 13000 data points, which includes enterprise transactional and operational records distributed across multiple subsystems. Data preprocessing includes Z-score normalization and missing value imputation to ensure consistency across distributed nodes. Feature extraction is performed using Independent Component Analysis (ICA) to derive statistically independent components from high-dimensional data. These features are transformed into graph-structured representations to capture interdependencies among enterprise entities. The CS-GNN model integrates graph neural learning with CSO to enhance decision-making across distributed components. Experimental results demonstrate a precision of 98.5% and a response time of 0.30s, which is implemented in Python and demonstrates improved interoperability, efficient cross-system integration, and enhanced decision support performance in distributed environments. The findings establish that integrating CS-GNN with ICA within distributed, interoperable architectures enables scalable, adaptive, and intelligent enterprise decision-making.