Building energy consumption prediction using multilayer perceptron neural network-assisted models; comparison of different optimization algorithms

Energy, Год журнала: 2023, Номер 282, С. 128446 - 128446

Опубликована: Июль 15, 2023

Язык: Английский

---

Peak Electrical Energy Consumption Prediction by ARIMA, LSTM, GRU, ARIMA-LSTM and ARIMA-GRU Approaches

Energies, Год журнала: 2023, Номер 16(12), С. 4739 - 4739

Опубликована: Июнь 15, 2023

Forecasting peak electrical energy consumption is important because it allows utilities to properly plan for the production and distribution of energy. This reduces operating costs avoids power outages. In addition, can help reduce environmental impact by allowing more efficient generation reducing need additional fossil fuels during periods high demand. current work, electric data from “Compagnie Electrique du Benin (CEB)” was used deduce at hours. The predicted using hybrid approaches based on traditional time series prediction methods (autoregressive integrated moving average (ARIMA)) deep learning (long short-term memory (LSTM), gated recurrent unit (GRU)). ARIMA approach model trend term, while were employed interpret fluctuation outputs these models combined provide final result. approach, ARIMA-LSTM, provided best performance with root mean square error (RMSE) 7.35, ARIMA-GRU RMSE 9.60. Overall, outperformed single approaches, such as GRU, LSTM, ARIMA, which exhibited values 18.11, 18.74, 49.90, respectively.

Язык: Английский

---

Energy management programming to reduce distribution network operating costs in the presence of electric vehicles and renewable energy sources

Energy, Год журнала: 2022, Номер 263, С. 125695 - 125695

Опубликована: Окт. 12, 2022

Язык: Английский

---

Energy efficient behavior modeling for demand side recommender system in solar microgrid applications using multi-agent reinforcement learning model

Sustainable Cities and Society, Год журнала: 2023, Номер 90, С. 104392 - 104392

Опубликована: Янв. 13, 2023

Язык: Английский

---

Flexibility quantification and enhancement of flexible electric energy systems in buildings

Journal of Building Engineering, Год журнала: 2023, Номер 68, С. 106114 - 106114

Опубликована: Фев. 22, 2023

Язык: Английский

---

Efficient energy management of domestic loads with electric vehicles by optimal scheduling of solar-powered battery energy storage system

Electric Power Systems Research, Год журнала: 2024, Номер 234, С. 110570 - 110570

Опубликована: Июнь 11, 2024

Язык: Английский

---

Complex artificial intelligence models for energy sustainability in educational buildings

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Июль 1, 2024

Energy consumption of constructed educational facilities significantly impacts economic, social and environment sustainable development. It contributes to approximately 37% the carbon dioxide emissions associated with energy use procedures. This paper aims introduce a study that investigates several artificial intelligence-based models predict most important buildings; schools. These include decision trees, K-nearest neighbors, gradient boosting, long-term memory networks. The research also relationship between input parameters yearly usage buildings. has been discovered school sizes AC capacities are impact variable higher consumption. While 'Type School' is less direct or weaker correlation 'Annual Consumption'. four developed were evaluated compared in training testing stages. Decision Tree model demonstrates strong performance on data an average prediction error about 3.58%. K-Nearest Neighbors errors, RMSE as high 38,429.4, which may be indicative overfitting. In contrast, Gradient Boosting can almost perfectly variations within dataset. metrics suggest some manage this variability better than others, LSTM standing out terms their ability handle diverse ranges, from minimum 99,274.95 maximum 683,191.8. underscores importance buildings not only physical learning spaces but dynamic environments contribute informal processes. Sustainable serve real-world examples environmental stewardship, teaching students efficiency sustainability through design operation. By incorporating advanced AI-driven tools optimize consumption, become interactive hubs encourage engage concepts everyday surroundings.

Язык: Английский

---

Demand-Side Flexibility in Power Systems: A Survey of Residential, Industrial, Commercial, and Agricultural Sectors

Sustainability, Год журнала: 2022, Номер 14(13), С. 7916 - 7916

Опубликована: Июнь 29, 2022

In recent years, environmental concerns about climate change and global warming have encouraged countries to increase investment in renewable energies. As the penetration of power goes up, intermittency system increases. To counterbalance fluctuations, demand-side flexibility is a workable solution. This paper reviews potentials demand sectors, including residential, industrial, commercial, agricultural, facilitate integration renewables into systems. residential sector, home energy management systems heat pumps exhibit great potential. The former can unlock household devices, e.g., wet appliances lighting latter integrates joint heat–power heating grids. industrial heavy industries, cement manufacturing plants, metal smelting, oil refinery are surveyed. It discussed how energy-intensive plants provide for commercial supermarket refrigerators, hotels/restaurants, parking lots electric vehicles pointed out. Large-scale be considered as electrical storage not only upstream network but also supply local shopping stores. agricultural irrigation pumps, on-farm solar sites, variable-frequency-drive water shown flexible demands. livestock farms

Язык: Английский

---

Optimization of operational strategy for ice thermal energy storage in a district cooling system based on model predictive control

Journal of Energy Storage, Год журнала: 2023, Номер 62, С. 106872 - 106872

Опубликована: Фев. 16, 2023

Язык: Английский

---

A Review on the Applications of PSO-Based Algorithm in Demand Side Management: Challenges and Opportunities

IEEE Access, Год журнала: 2023, Номер 11, С. 53373 - 53400

Опубликована: Янв. 1, 2023

The increase in energy consumption, environmental pollution issues, and low-carbon agenda has grown the research area of demand side management (DSM). DSM programs provide feasible solutions significantly enhance efficiency sustainability electrical distribution systems. This paper classifies discusses broad definition based on comprehensive literature study considering response efficiency. implementation Artificial Intelligence algorithms applications been employed many studies to help researchers make optimal decisions achieve predictions by analyzing massive amount historical data. Owing its simplicity consistent performance fast convergence time, Particle Swarm Optimization (PSO) is widely used as a part swarm AI algorithm become prominent technique optimization process exploit full benefit demand-side program. variants PSO have developed overcome limitations original solve high complexity uncertainty process. proposed PSO-based can optimize consumers' consumption curves, reducing peak hence minimizing electricity cost when integrated with DR or EE measures. works seen an increasing trend past decade. Therefore, this reviewed application fields some constraints discussed challenges from previous work. potential for new opportunities identified so that methods be future research.

Язык: Английский

---