Cloud-edge collaboration-based bi-level optimal scheduling for intelligent healthcare systems

The development of intelligent healthcare systems (IHS) has raised the added value of digital medical data. With an efficient exploitation of digital medical data for diagnosis assistance, federated learning (FL) is promising in future digital health care. However, in multiple task performances, federated nodes deployed at the edge of IHS are constrained by computing and storage resources, as well as increased privacy breach risks. On account of these challenges, this paper proposes a more elaborated cloud-edge collaboration (CEC) framework of IHS combining FL and blockchain. Thus, a bi-level optimization scheduling IHS model is proposed, considering the large-scale access requirement of distributed generation (DG), energy storage (ES) and controllable load (CL) access to the IHS. Simulation results confirm an effective reduction of execution delay and power consumption, and a better interest coordination among multi-stakeholders.(c) 2022 Elsevier B.V. All rights reserved.

Automated summary

The development of intelligent healthcare systems has increased the value of digital medical data. Federated learning shows promise in future digital healthcare by harnessing digital medical data for diagnosis assistance. However, the computing and storage constraints, as well as privacy risks, faced by federated nodes deployed at the edge of intelligent healthcare systems pose challenges. To address these challenges, this paper proposes a cloud-edge collaboration framework that combines federated learning and blockchain. It introduces a bi-level optimization scheduling model for intelligent healthcare systems, considering the large-scale access requirement of distributed generation, energy storage, and controllable load. Simulation results demonstrate reduced execution delay and power consumption, as well as improved interest coordination among stakeholders.