ADMM Empowered Distributed Computational Intelligence for Internet of Energy

Abstract

Internet of Energy (IoE), the paradigm of applying Internet of Things (IoT) to energy management systems, aims to improve energy systems' efficiency and reliability by enhancing connectivity and interoperability among geographically distributed energy devices. This requires distributed computational intelligence responsible for data processing and decision making of the energy devices. To achieve distributed, scalable, and privacy-protected energy management in IoE, this article proposes using Alternating Direction Method of Multipliers (ADMM) as the theoretical framework to design the distributed computational intelligence in IoE. In the first place, a brief introduction of ADMM for solving energy management problems is given. Based on the ADMM framework, a distributed intelligence system is designed for each decision maker in energy systems. With the distributed intelligence, decision makers can interact with each other to achieve system-wide goals of energy management without disclosing their private data. Moreover, we provide some examples of ADMM applications in practical distributed energy management in IoE and discuss the challenges of ADMM implementation in IoE. Lastly, a joint computing and networking resources management architecture is proposed to meet the challenges. The result of a case study shows that this architecture can reduce communications and computing costs of ADMM implementation.