Coordination for Multienergy Microgrids Using Multiagent Reinforcement Learning

Abstract

Multienergy microgrids (MEMGs) have significant potential to offer high energy utilization efficiency and system flexibility. The coordination of these MEMGs poses challenges due to the various system dynamics and uncertainties and the need to preserve privacy. This article proposes a double auction (DA)-market-based coordination framework. As such, MEMGs can not only schedule their own energy components but also trade energy with others in the DA market. After that, we formulate this problem as Markov games and propose a multiagent reinforcement learning method by making use of the DA market public information to enhance the stability with privacy perseverance. Case studies involving a real-world scenario validate the superior performance of the proposed method in reducing both the energy costs and the carbon emissions.

Decentralized power grid control scheme utilizing photonic sensing and computing

“…There are many neural network architectures and training algorithms available, but extensive literature shows the effectiveness of stabilizing the power grid in this fashion 19 . 20 For each of these sub-systems to be replaced, the following sections describe technologies or existing research that could pave the path for this fully photonic device: optical sensors, optical wavelet transforms, and optical inference of RNNs and CNNs.…”

Distributed optimization for joint peer‐to‐peer electricity and carbon trading among multi‐energy microgrids considering renewable generation uncertainty

“…Recently, reinforcement learning (RL) has gained significant attention in power systems for its autonomous learning capability and utilization of environmental and historical data. For instance, in [25], a multiagent RL method was utilized to enhance the stability of P2P electricity trading through the use of public information from the double auction market. A multi-agent RL paradigm-based joint P2P electricity and carbon allowance trading mechanism for a building community was formulated in [26], effectively addressing the complex operations of coupling multi-energy sectors in decentralized markets.…”

“…While these studies contribute to carbon reduction, neglecting the uncertainty from RESs may disrupt the supply and demand balance of MEMGs, potentially leading to economic losses. Moreover, RL models are challenged by a potential dimensional catastrophe as the number of interactions increases quadratically with the number of participants, necessitating further discussion on the scalability of the proposed RL model and algorithm in [25,26].…”

The coordinated operation strategy of multi-type power generations in different modes in prosumer with high renewables

“…For example, in the literatures (Hou et al, 2015;Mortezaei et al, 2015), the prosumer with multiple photovoltaic inverters is established to realize coordinated operation of high renewables and provide voltage and frequency support for the grid while the types of power supply in the prosumer are still not satisfactory. In the literatures (Qiu et al, 2022) and (Capuder et al, 2020), they establish the prosumer with multi-type power generations and the DGs can operate in parallel stably only in normal grid-connected mode. Therefore, the research on the coordinated operation strategy of the prosumer's multiple generations in different modes still needs further study.…”