Data Management in Dynamic AAL Environments

Abstract

With the increasing elderly population, especially in developed countries, there is an urgent need for advanced systems capableof adapting to dynamic and complex data environments in healthcareand assisted living scenarios. This research introduces a framework devised to optimize data flow in dynamic network environments, focusingon enhancing Ambient Assisted Living (AAL) through the integration ofAmbient Intelligence (AmI) and ubiquitous computing technologies.The architecture involves a network of nodes that dynamically manageand prioritize data flow. Central to the framework is its ability to preprocess data at the network edge, which is critical for reducing latencyand ensuring that high-priority data reaches its destination swiftly andreliably. This is particularly important in AAL settings, where delays indata delivery can impact the level of care and monitoring provided to residents. By processing data closer to its source, the framework minimizesbandwidth consumption. It alleviates the burden on the core network,essential for scalability in environments with a high density of networkeddevices and sensors. The effectiveness of this system is validated throughsimulations using the ns-3 network simulator and BonnMotion, focusing on scenarios typical of nursing homes. These simulations help tounderstand how the framework adapts to changes in network densityand mobility patterns, which is crucial for its application in real-worldscenarios.Simulation results show that the framework significantly improves thesuccess rates of data gathering across various network configurations,with data prioritization playing a crucial role in enhancing the overallefficiency of the data management system in AAL applications. Futurework will explore the integration of more advanced AI algorithms forbetter decision-making in data prioritization and network management.