• Energy Research
• 2025-2025close
• 7. Clean energy close
• CN close
• SA close
• RO close

Energy forecasting is an essential task in power system operations. Operators usually issue forecasts and leverage them to schedule energy dispatch ahead of time. However, forecast models are typically developed in a way that overlooks the operational value of the forecasts. To bridge the gap, we design a value-oriented point forecasting approach for sequential energy dispatch problems with renewable energy sources. At the training phase, we align the loss function with the overall operation cost function, thereby achieving reduced operation costs. The forecast model parameter estimation is formulated as a bilevel program. Under mild assumptions, we convert the upper-level objective into an equivalent form using the dual solutions obtained from the lower-level operation problems. Additionally, a novel iterative solution strategy is proposed for the newly formulated bilevel program. Under such an iterative scheme, we show that the upper-level objective is locally linear regarding the forecast model output, and can act as the loss function. Numerical experiments demonstrate that, compared to commonly used statistical quality-oriented point forecasting methods, forecasts obtained by the proposed approach result in lower operation costs. Meanwhile, the proposed approach is more computationally efficient than traditional two-stage stochastic programs. Accepted in IEEE Transactions on Smart Grid

Recent years have witnessed exponential growth in developing deep learning models for time series electricity forecasting in power systems. However, most of the proposed models are designed based on the designers’ inherent knowledge and experience without elaborating on the suitability of the proposed neural architectures. Moreover, these models cannot be self-adjusted to dynamically changed data patterns due to the inflexible design of their structures. Although several recent studies have considered the application of the neural architecture search (NAS) technique for obtaining a network with an optimized structure in the electricity forecasting sector, their training process is computationally expensive and their search strategies are not flexible, indicating that the NAS application in this area is still at an infancy stage. In this study, we propose an intelligent automated architecture search (IAAS) framework for the development of time series electricity forecasting models. The proposed framework contains three primary components, that is, network function–preserving transformation operation, reinforcement learning–based network transformation control, and heuristic network screening, which aim to improve the search quality of a network structure. After conducting comprehensive experiments on two publicly available electricity load data sets and two wind power data sets, we demonstrate that the proposed IAAS framework significantly outperforms the 10 existing models or methods in terms of forecasting accuracy and stability. Finally, we perform an ablation experiment to showcase the importance of critical components in the proposed IAAS framework in improving forecasting accuracy. History: Accepted by Ram Ramesh, Area Editor for Data Science and Machine Learning. Funding: J. Yang, G. Jiang, and Y. Chen were supported by the National Natural Science Foundation of China [Grants 72293562, 72121001, 72101066, 72131005, 71801148, and 72171060]. Y. Chen was supported by the Heilongjiang Natural Science Excellent Youth Fund [YQ2022G004]. Supplemental Material: The software ( Yang et al. 2023 ) that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2023.0034 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2023.0034 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .

Gas turbine (GT) power plants operating in arid climates suffer a decrease in output power during the hot summer months because of insufficient cooling. Cooling the air intake to the compressor has been widely used to mitigate this shortcoming. An energy analysis of a GT Brayton cycle coupled to a refrigeration cycle shows a promise for increasing the output power with a little decrease in thermal efficiency. A thermo-economics algorithm is developed and applied to an open cycle, Hitachi MS700 GT plant at the industrial city of Yanbu by the Red Sea in the Kingdom of Saudi Arabia. Result shows that the enhancement in output power depends on the degree of chilling the air intake to the compressor (a 12 - 22 K decrease is achieved). For this case study, maximum power gain ratio (PGR) is 15.46%, at a decrease in thermal efficiency of 12.25%. The cost of adding the air cooling system is also investigated and a cost function is derived that incorporates time-dependent meteorological data, operation characteristics of the GT and the air intake cooling system and other relevant parameters such as interest rate, lifetime, and operation and maintenance costs. The profit of adding the air cooling system is calculated for different electricity tariff.

Global climate challenge is demanding urgent actions for decarbonization, while electric power systems take the major roles in clean energy transition. Due to the existence of spatially and temporally dispersed renewable energy resources and the uneven distribution of carbon emission intensity throughout the grid, it is worth investigating future load planning and demand management to offset those generations with higher carbon emission rates. Such techniques include inter-region utilization of geographically shiftable resources and stochastic renewable energy. For instance, data center is considered to be a major carbon emission producer in the future due to increasing information load, while it holds the capability of geographical load balancing. In this paper, we propose a novel planning and operation model minimizing the system-level carbon emissions via sitting and operating geographically shiftable resources. This model decides the optimal locations for shiftable resources expansion along with power dispatch schedule. To accommodate future system operation patterns and a wide range of operating conditions, we incorporate 20-year fine-grained load and renewables scenarios for grid simulations of realistic sizes (e.g., up to 1888 buses). To tackle the computational challenges coming from the combinatorial nature of such large-scale planning problem, we develop a customized Monte Carlo Tree Search (MCTS) method, which can find reasonable solutions satisfying solution time limits. Besides, MCTS enables flexible time window settings and offline solution adjustments. Extensive simulations validate that our planning model can reduce more than 10\% carbon emission across all setups. Compared to off-the-shelf optimization solvers such as Gurobi, our method achieves up to 8.1X acceleration while the solution gaps are less than 1.5\% in large-scale cases. Accepted at IEEE Transactions on Power Systems

In order to solve the problem of excessive burden of electricity and energy consumption in urban landscape buildings clusters, the study combined data mining algorithms to establish a prediction model for energy-saving renovation of urban landscape building clusters. Firstly, the energy demand and energy consumption of theurban landscape buildings complex were analysed, a mathematical model was established to predict the energy consumption of the building complex. Then, the prediction model of energy-saving retrofitting of building clusters was constructed by combining data mining techniques. The experimental results show that the change trend of total energy consumption is different under different single influencing factors of energy consumption. Among them, the lighting power density factor has the greatest influence on energy consumption, and its annual energy consumption change rate can reach about 0.35. Applying the prediction model to the energy consumption prediction of 15 urban single buildings, it was found that the total energy consumption of the buildings before the retrofit was much higher than that after the retrofit, and the energy-saving rate of the whole observed sample building group was as high as 18.5%, meanwhile, the highest energy-saving rate of the single buildings reached 30.1%.

Electrical load forecasting plays a crucial role in decision-making for power systems, including unit commitment and economic dispatch. The integration of renewable energy sources and the occurrence of external events, such as the COVID-19 pandemic, have rapidly increased uncertainties in load forecasting. The uncertainties in load forecasting can be divided into two types: epistemic uncertainty and aleatoric uncertainty. Separating these types of uncertainties can help decision-makers better understand where and to what extent the uncertainty is, thereby enhancing their confidence in the following decision-making. This paper proposes a diffusion-based Seq2Seq structure to estimate epistemic uncertainty and employs the robust additive Cauchy distribution to estimate aleatoric uncertainty. Our method not only ensures the accuracy of load forecasting but also demonstrates the ability to separate the two types of uncertainties and be applicable to different levels of loads. The relevant code can be found at \url{https://anonymous.4open.science/r/DiffLoad-4714/}. Accepted by IEEE Transactions on Power Systems, 2024

With the advent of employing bio-fuels along with the diesel in compression ignition engines the study of performance and emission characteristics have occupied the prominence, owing to diversified multi responses. As the limited information is available about the application of Taguchi based GTMA process to maximize the overall performance and emission characteristics of diesel engine, in the present work the investigation was carried out to maximize the overall utility by employing the Taguchi based GTMA process. By following the user preference rating, weights for the response characteristics namely brake thermal efficiency, brake specific fuel consumption, carbon monoxide and oxides of nitrogen were calculated using graph theory and matrix approach (GTMA). The parameter hydrogen induction played a major role to an extent of 78.62% while Injection opening pressure playing a minor role with a contribution of 7.06%. The optimal parameters condition was at mid-level of the governing parameters namely IOP, CR and volume of hydrogen inducted. The predicted results were within 95% of confidence interval of the optimal values. Therefore, the hydrogen inductance into the cylinder not only improving the performance but also minimizing the emission characteristics.

Machine learning's application in solar-thermal desalination is limited by data shortage and inconsistent analysis. This study develops an optimized dataset collection and analysis process for the representative solar still. By ultra-hydrophilic treatment on the condensation cover, the dataset collection process reduces the collection time by 83.3%. Over 1,000 datasets are collected, which is nearly one order of magnitude larger than up-to-date works. Then, a new interdisciplinary process flow is proposed. Some meaningful results are obtained that were not addressed by previous studies. It is found that Radom Forest might be a better choice for datasets larger than 1,000 due to both high accuracy and fast speed. Besides, the dataset range affects the quantified importance (weighted value) of factors significantly, with up to a 115% increment. Moreover, the results show that machine learning has a high accuracy on the extrapolation prediction of productivity, where the minimum mean relative prediction error is just around 4%. The results of this work not only show the necessity of the dataset characteristics' effect but also provide a standard process for studying solar-thermal desalination by machine learning, which would pave the way for interdisciplinary study.