Emergency Load Shedding Strategy for Microgrids Based on Dueling Deep Q-Learning

Abstract

The rapid drop of frequency under the disturbance is a major threat to the safe and stable operation of a microgrid (MG) system. Emergency load shedding is the main measure to prevent continuous frequency drop and power outage. The existing load shedding strategies have poor adaptability to deal with the problem of MG load shedding under different disturbance situations, and it is difficult to ensure the safe and stable operation of an MG in different operating environments. To address this problem, this paper proposes a data-driven load shedding strategy. First, considering the importance of the load and the frequency recovery time of the system, a load shedding contribution indicator is designed that takes into account the load frequency adjustment effect and the load shedding priority. This contribution indicator is introduced as a load shedding criterion into the reward value function of dueling deep Q learning. Second, considering the suddenness and uncertainty of emergency load shedding, a MG emergency load shedding strategy (ELSS) based on dueling deep Q-learning is proposed. On this basis, the dueling deep Q learning algorithm is used to obtain the load shedding decision with the maximum cumulative reward. Finally, taking the MG load shedding cases in two different scenarios as examples, a simulation study is carried out on a modified IEEE-25 bus MG. The simulation results show that, compared with the model-driven implicit enumeration strategy (IES), the proposed ELSS has superiority in maintaining stable power supply for important loads and reducing load shedding decision-making time and frequency fluctuations.

Load Shedding in Microgrids with Dual Neural Networks and AHP Algorithm

“…This test system consists of 8 synchronous machines with excitation types AC5A and AC8B [20], 25 buses, 25 transmission lines, 9 transformers, and 11 constant impedance loads. The total load demand is 393kW [21]. The diagram of the MG system is shown in Figure 2.…”

A New Load Shedding Scheme With Consideration of Distributed Energy Resources’ Active Power Ramping Capability

“…In [23], [24], genetic algorithms are used to find the optimal amount of load that needs to be shed. [25] presents an emergency load shedding scheme based on deep Q learning, where the load priority and the anticipated effect of shedding actions considering loads' frequency dependent characteristics are formulated in the reward function, thus to achieve fast frequency recovery, while maintaining the power supply to critical loads. The Q-learning algorithm is also applied in [26], where the load shedding amount is determined by considering the frequency droop characteristics of DERs, and the load priority is formulated as the reward for the Q-learning algorithm to minimize the interruption to critical loads.…”

Design of a Partially Grid-Connected Photovoltaic Microgrid Using IoT Technology

“…Microgrids are quite different from classical power systems due to the intermittent nature of generation resources. The operation of microgrids in both grid-connected and islanded modes has been investigated in the literature [37][38][39]. Microgrid operation emphasizes the supply of critical loads during power outages.…”

“…Figure 2a shows a simple two-node system with a source or a distributed generation (DG) unit, which feeds a reactive power load through a line segment of resistance and Microgrids are quite different from classical power systems due to the intermittent nature of generation resources. The operation of microgrids in both grid-connected and islanded modes has been investigated in the literature [37][38][39]. Microgrid operation emphasizes the supply of critical loads during power outages.…”