This article reviews recent works applying machine learning (ML) techniques in the context of energy systems’ reliability assessment and control. We showcase both the progress achieved to date as well as the important future directions for further research, while providing an adequate background in the fields of reliability management and of ML. The objective is to foster the synergy between these two fields and speed up the practical adoption of ML techniques for energy systems reliability management. We focus on bulk electric power systems and use them as an example, but we argue that the methods, tools, etc. can be extended to other similar systems, such as distribution systems, microgrids, and multienergy systems.

/pdf/recent-developments-in-machine-learning-for-energy-systems-2v0d619oz0.pdf

Recent Developments in Machine Learning for Energy Systems Reliability Management

Current state of neural networks applications in power system monitoring and control

https://onlinelibrary.wiley.com/doi/pdf/10.1002/est2.46

Optimal placement and sizing of photovoltaics and battery storage in distribution networks

This article presents the Reliability Assessment (RA) of renewable energy interfaced Electrical Distribution System (EDS) considering the electrical loss minimization (ELM). ELM aims at minimizing the detrimental effect of real power and reactive power losses in the EDS. Some techniques, including integration of Renewable Energy Source (RES), network reconfiguration, and expansion planning, have been suggested in the literature for achieving ELM. The optimal RES integration (also referred to as Distributed Generation (DG)) is one of the globally accepted techniques to achieve minimization of electrical losses. Therefore, first, the locations to accommodate these DGs are obtained by implementing two indexes, namely Index-1 for single DG and Index-2 for multiple DGs. Second, a Constriction Factor-based Particle Swarm Optimization (CF-PSO) technique is applied to obtain an optimal sizing(s) of the DGs for achieving the ELM. Third, the RA of the EDS is performed using the optimal location(s) and sizing(s) of the RESs (i.e., Solar photovoltaic (SPV) and Wind Turbine Generator (WTG)). Moreover, a Battery Storage System (BSS) is also incorporated optimally with the RESs to further achieve the ELM and to improve the system’s reliability. The result analysis is performed by considering the power output rating of WTG-GE’s V162-5.6MW (IECS), SPV-Sunpower’s SPR-P5-545-UPP, and BSS-Freqcon’s BESS-3000 (i.e., Battery Energy Storage System 3000), which are provided by the corresponding manufacturers. According to the outcomes of the study, the results are found to be coherent with those obtained using other techniques that are available in the literature. These results are considered for the RA of the EDS. RA is further analyzed considering the uncertainties in reliability data of WTG and SPV, including the failure rate and the repair time. The RA of optimally placed DGs is performed by considering the electrical loss minimization. It is inferred that the reliability of the EDS improves by contemplating suitable reliability data of optimally integrated DGs.

https://www.mdpi.com/1996-1073/13/21/5631/pdf

Reliability Assessment of Wind-Solar PV Integrated Distribution System Using Electrical Loss Minimization Technique

—The optimal power flow problem seeks to find an optimal profile of active and reactive power generations along with voltage magnitudes in such a manner as to minimize the total operating costs of a power system while satisfying network security constraints. This article presents a firefly algorithm to solve the optimal power flow problem incorporating a thyristor-controlled series capacitor. A thyristor-controlled series capacitor is considered to find the optimal location in transmission lines to enhance the power transfer capability of the transmission line. To assess the effectiveness of the proposed algorithm, it was tested on a 5-bus test system, an IEEE 14-bus system, and a modified IEEE 30-bus system, and it was compared with the genetic algorithm and differential evolution with and without a thyristor-controlled series capacitor. It has also been observed that the proposed algorithm can be applied to larger systems and does not suffer with computational difficulties. The results show that...

Optimal Location of Thyristor-controlled Series Capacitor to Enhance Power Transfer Capability Using Firefly Algorithm

Voltage stability assessment in power network using self organizing feature map and radial basis function

Spider monkey optimization technique–based allocation of distributed generation for demand side management

SUMMARY
This paper presents an artificial neural network–based approach, in which Kohonen's self-organising feature map technique in association with learning vector quantisation has been applied to classify the power system operating states on the basis of their degree of static voltage stability. The proposed scheme can seamlessly integrate itself within the energy management systems in the smart grid scenario. A self-organising feature map has been considered to be an ideal choice because the state classification problem is a typical multiclass pattern classification problem, which can be efficiently handled by a self-organising feature map with much shorter training time compared with other neural networks. The self-organising feature map provided information about the operating states of the power system and classified them into three categories, namely, normal state, intermediate state and emergency (or alert) state. To augment the classification accuracy of self-organising feature map, a learning vector quantisation–based supervised classification was also adopted. The proposed method was tested on a real 203-bus system of an Indian power utility, and the results obtained has been compared with standard voltage stability indicator–based classical voltage stability assessment results. Copyright © 2011 John Wiley & Sons, Ltd.

Classification of power system voltage stability conditions using Kohonen's self-organising feature map and learning vector quantisation

Due to increase in load demand the use of distributed generation has been increased in the distribution system. Voltage profile as well as voltage security state of the distribution system can be i...

Modified Spider Monkey Optimization-Based Optimal Placement of Distributed Generators in Radial Distribution System for Voltage Security Improvement

Load demands on distribution system is growing rapidly. So, the distribution system is operating nearer to the stability boundary. A stability index named line stability indicator (LSI) is developed in this paper for voltage stability analysis of radial distribution system. The applicability of the indicator is tested on a standard (IEEE) 33-bus Radial Distribution System. To find the value of proposed indicator for different lines of the system under consideration MATLAB code is used. This indicator is able to find the weak lines of the system. By using FACTS device at the receiving end side of the weak line the voltage level of buses of the system can be improved. Results indicate that installation of FACTS device at the appropriate bus will make the whole system more stable in respect of voltage.

Kabir Chakraborty

Papers

Voltage stability assessment in power network using self organizing feature map and radial basis function

Spider monkey optimization technique–based allocation of distributed generation for demand side management

Classification of power system voltage stability conditions using Kohonen's self-organising feature map and learning vector quantisation

Modified Spider Monkey Optimization-Based Optimal Placement of Distributed Generators in Radial Distribution System for Voltage Security Improvement

Voltage stability assessment in radial distribution system by line stability indicator (LSI) and its improvement using SVC