The efficient planning of electric power systems is essential to meet both the current and future energy demands. In this context, reinforcement learning (RL) has emerged as a promising tool for control problems modeled as Markov decision processes (MDPs). Recently, its application has been extended to the planning and operation of power systems. This study provides a systematic review of advances in the application of RL and deep reinforcement learning (DRL) in this field. The problems are classified into two main categories: Operation planning including optimal power flow (OPF), economic dispatch (ED), and unit commitment (UC) and expansion planning, focusing on transmission network expansion planning (TNEP) and distribution network expansion planning (DNEP). The theoretical foundations of RL and DRL are explored, followed by a detailed analysis of their implementation in each planning area. This includes the identification of learning algorithms, function approximators, action policies, agent types, performance metrics, reward functions, and pertinent case studies. Our review reveals that RL and DRL algorithms outperform conventional methods, especially in terms of efficiency in computational time. These results highlight the transformative potential of RL and DRL in addressing complex challenges within power systems.
This paper shows the technical–economic, operational and environmental feasibility of four off-grid hybrid power systems to supply energy to the Cerrito de los Morreños community in Ecuador. These configurations consist of combinations of diesel generators, solar photovoltaic systems, and battery energy storage systems. Each configuration was simulated and the results were analyzed for two different load conditions: (1) the existing load profile and (2) a reduced load profile by incorporating an energy efficiency initiative. Homer Pro software was used to perform the simulations. The planning horizon for the simulations was selected to be 15 years. The results showed the diesel/photovoltaic/battery configuration with energy efficiency showed the best performance, which was achieved with a photovoltaic system of 160 kWp, the existing generator of 165 kW and a storage system of 283 kWh. The stand-alone diesel generator and photovoltaic/diesel configurations showed higher Net Present Costs, instability problems and higher CO2 emissions. Additionally, the configurations without energy efficiency had increases of between 15% and 40% higher costs compared to their respective energy-efficient scenarios. The information in this work could be useful for some organizations in Ecuador who are interested in investing in rural electrification projects with renewable energy to reduce and/or compensate their CO2 emissions.
This paper presents a technical, economic, and environmental analysis and optimization of the impact of the reduction of diesel fuel subsidy in the design of an off-grid hybrid power system (OHPS). The OHPS includes a diesel generator, battery energy storage system (BESS), and a solar power system (SPS). This impact will focus on the electricity production levels of each of the OHPS components according to the increase of the fuel price and the SPS size. The Bellavista community in Ecuador was selected as the case study for this work. In this South American country, the government has begun a gradual increase in the diesel fuel price until it reaches international prices. Fifteen scenarios of OHPSs were simulated, in Homer Pro software, considering three SPS sizes and varying the diesel fuel price in five values. The annual load profile for the simulations was built based on the information of a previous study in this community. The results showed that for lower fuel prices (USD$0.26/L and USD$0.35/L), the OHPSs worked mostly with their diesel generators with reduced use of their BESSs. However, there was a higher penetration of the power delivered from the SPSs and BESSs, with higher fuel prices (USD$0.44/L, USD$0.53/L, and USD$0.62/L). These OHPSs considerably reduced their CO2 emissions compared with the standalone diesel generator scenario.
This paper shows the design considerations of an off- grid solar power system working independently with an existing diesel generator to supply energy for lighting circuits and some low-power appliances installed in the Bellavista community. The main purpose of this design is to take advantage of the available infrastructure in the community to reduce initial investment costs while ensuring reliable energy access for the community. In addition, this system may be used as a starting point to build upon for future sustainable energy projects. The community is currently being powered through a diesel generator operating for 5 hours every day during the evening when the period of higher demand occurs. However, the community requires access to reliable energy access throughout the day to improve their quality of life. For the generator's analysis, we adapted its load profile from available data of previous studies carried out in the community. We used the HOMER Pro renewable energy software for the simulation and the Meteonorm 7.3 database to obtain the site's weather data file. The results show the sizing of the solar power system, its annual electricity production, and other indicators obtained from its operation. We also show the system's initial capital costs and the Net Present Cost, taking into account the existing equipment in the community. Besides, we estimate the annual electricity production of the generator, its amount of fuel used, its operating costs, and a baseline for greenhouse gas emissions produced in a year according to the actual operating conditions.
This study assessed the techno-economic and environmental feasibility of a grid-connected PV system on a university building, with a focus on potential revenue from carbon credit sales. The analysis assumes a regulated CO2 emissions market in Ecuador and references carbon credit prices from the European Union, New Zealand, China, and the Republic of Korea. Seven PV system configurations, varying in size and capacity, were modeled using Homer Pro and assessed for their techno-economic feasibility and environmental performance. The results indicated that the 166 kWp system was the most promising, supplying approximately 74% of the building’s electricity demand. Thus, this system was selected as the baseline for evaluating potential revenues from carbon credit sales in international markets, based on average carbon prices in 2022. The selected markets generated annual revenues of USD 4410.68, USD 2587.55, USD 446.34, and USD 958.37, respectively. While these additional revenues improved the Net Present Value (NPV) of the 166 kWp system, the overall NPV remained negative due to the high initial investment costs.
This paper proposes a new efficient method to mitigate transmission line overloads by switching lines, based on sensitivity analysis and heuristic techniques. The proposed method, which constitutes an improvement of a method that has been published in the literature recently, results in better processing times due to the use of a dedicated search space reduction procedure while searching for line switching alternatives. The proposed method is evaluated and discussed through simulations using different sized power transmission networks, and shows great potential for use in real time operations.