Communication-assisted adaptive protection can improve the speed and selectivity of the protection system. However, in the event, that communication is disrupted to the relays from the centralized adaptive protection system, predicting the local relay protection settings is a viable alternative. This work evaluates the potential for machine learning to overcome these challenges by using the Prophet algorithm programmed into each relay to individually predict the time-dial (TDS) and pickup current (IPICKUP) settings. A modified IEEE 123 feeder was used to generate the data needed to train and test the Prophet algorithm to individually predict the TDS and IPICKUP settings. The models were evaluated using the mean average percentage error (MAPE) and the root mean squared error (RMSE) as metrics. The results show that the algorithms could accurately predict IPICKUP setting with an average MAPE accuracy of 99.961%, and the TDS setting with a average MAPE accuracy of 94.32% which is sufficient for protection parameter prediction.
In this paper, the effects and mitigation strategies of pulsed loads on medium voltage DC (MVDC) electric ships are explored. Particularly, the effect of high-powered pulsed loads on generator frequency stability are examined. As a method to stabilize a generator which has been made unstable by high-powered pulsed loads, it is proposed to temporarily extract energy from the propulsion system using regenerative propeller braking. The damping effects on generator speed oscillation of this method of control are examined. The impacts on propeller and ship speed are also presented.
This paper proposes an optimal relay placement approach for microgrids. The proposed approach considers both grid-connected and islanded microgrid modes. The algorithm separately calculates the System Average Interruption Frequency Index (SAIFI) of a microgrid in each operating mode. Then, two weighting factors corresponding to different operating modes are used to calculate the overall SAIFI of the microgrid. The objective is to find the optimal relay locations such that the microgrid overall SAIFI is minimized. The power electronics interfaces associated with distributed energy resources may be classified as grid following or grid forming. As opposed to grid-following distributed energy resources (DERs) such as typical solar inverters, grid-forming inverters are able to control the microgrid voltage and frequency at the point of their interconnection. Therefore, these DERs can facilitate the formation of sub-islands in the microgrid when the protective relays isolate a portion of the microgrid. If there is at least one grid-forming DER available in a sub-island, that sub-island can continue supplying its local load. The exchange market algorithm (EMA) is used for optimizing functions. The effectiveness of the proposed optimal relay placement approach is verified using an 18-bus microgrid and IEEE 123-bus test system.