Federated Reinforcement Learning for Energy Management of Multiple Smart Homes with Distributed Energy Resources

Abstract Demand response (DR), an integral part of the smart grid, has great potential in handling the challenges of the existing power grid. The potential of different DR programs in the energy management of residential consumers (RCs) and the integration of distributed energy resources (DERs) is an important research topic. A novel distributed approach for energy management of RCs considering the competitive interactions among them is presented in this paper. The impact of participation of RC’s in price-based (PB) and incentive-based (IB) DR programs is investigated using game theory. For this, an energy management optimization problem (EMOP) is formulated to minimize electricity cost. The utility company employs electricity price as a linear function of aggregated load in the PB DR program and an incentive rate in the IBDR program. RCs are categorized into active and passive users. Active users are further distinguished based on the ownership of energy storage devices (SD) and dispatchable generation units (DGU). EMOP is modeled using a non-cooperative game, and the distributed proximal decomposition method is used to obtain the Nash equilibrium of the game. The results of the proposed approach are analyzed using different case studies. The performance of the proposed approach is evaluated in terms of aggregated cost and system load profile. It has been observed that participation in PB and IBDR program benefits both the utility and the consumers.

Download Full-text

An Aggregated Model for Energy Management Considering Crowdsourcing Behaviors of Distributed Energy Resources

IEEE Access ◽

10.1109/access.2019.2945288 ◽

2019 ◽

Vol 7 ◽

pp. 145757-145766 ◽

Cited By ~ 2

Author(s):

Bomiao Liang ◽

Weijia Liu ◽

Lei Sun ◽

Zhiyuan He ◽

Beiping Hou

Keyword(s):

Energy Management ◽

Energy Resources ◽

Distributed Energy Resources ◽

Distributed Energy ◽

Aggregated Model

Download Full-text

Blockchain-Based Decentralized Energy Management Platform for Residential Distributed Energy Resources in A Virtual Power Plant

WSEAS TRANSACTIONS ON CIRCUITS AND SYSTEMS ◽

10.37394/23201.2021.20.10 ◽

2021 ◽

Vol 20 ◽

pp. 75-91

Author(s):

Qing Yang ◽

Hao Wang ◽

Taotao Wang ◽

Shengli Zhang ◽

Xiaoxiao Wu ◽

...

Keyword(s):

Power Plant ◽

Power System ◽

Energy Management ◽

Energy Resources ◽

Network Services ◽

Distributed Energy Resources ◽

Virtual Power ◽

Distributed Energy ◽

Virtual Power Plant ◽

Management Platform

The advent of distributed energy resources (DERs), such as distributed renewables, energy storage, electric vehicles, and controllable loads, brings a significantly disruptive and transformational impact on the centralized power system. It is widely accepted that a paradigm shift to a decentralized power system with bidirectional power flow is necessary to the integration of DERs. The virtual power plant (VPP) emerges as a promising paradigm for managing DERs to participate in the power system. In this paper, we develop a blockchain-based VPP energy management platform to facilitate a rich set of transactive energy activities among residential users with renewables, energy storage, and flexible loads in a VPP. Specifically, users can interact with each other to trade energy for mutual benefits and provide network services, such as feed-in energy, reserve, and demand response, through the VPP. To respect the users’ independence and preserve their privacy, we design a decentralized optimization algorithm to optimize the users’ energy scheduling, energy trading, and network services. Then we develop a prototype blockchain network for VPP energy management and implement the proposed algorithm on the blockchain network. By experiments using real-world data trace, we validated the feasibility and e_ectiveness of our algorithm and the blockchain system. The simulation results demonstrate that our blockchain-based VPP energy management platform reduces the users’ cost by up to 38.6% and reduces the overall system cost by 11.2%.

Download Full-text