RESEARCH ON ELECTRICITY CONSUMPTION PREDICTION BASED ON DEEP INTEGRATION MODELS
| dc.contributor.advisor | Chen, Ying | |
| dc.contributor.author | Alkhattabi, Moayad | |
| dc.date.accessioned | 2025-05-21T12:46:53Z | |
| dc.date.issued | 2024 | |
| dc.description | This paper mainly discusses the related technologies of power consumption prediction, proposes an adaptive ensemble learning classification algorithm based on improved particle swarm optimization (PSO) algorithm, and constructs a deeply integrated power consumption prediction model through stacked ensemble learning method. Although LSTM performs well in processing sequence data, its performance is still limited in the face of complex and heterogeneous data sets. Therefore, in order to further improve the performance of the model, this paper introduces an improved version of PSO algorithm to optimize the hyperparameters in the ensemble learning process, especially adding dynamic weighting factors and compression factors. In this paper, a variety of machine learning methods, including LSTM networks, are combined to determine the best combination of different base learners through adaptive ensemble learning strategies. With this approach, multiple learners are able to complement each other's strengths and weaknesses, resulting in a powerful integrated model that effectively improves the accuracy of power consumption predictions. The experimental results show that compared with traditional methods, the improved model exhibits higher prediction accuracy and stronger robustness, especially when dealing with complex and large-scale data sets. Future research will continue to explore how more advanced machine learning and deep learning techniques, such as Markov models, can be used to further improve the accuracy of power consumption predictions. In addition, with the rapid development of the energy Internet, power consumption forecasting will need to integrate more data sources, such as grid data, meteorological data, market data, etc., to support the efficient operation of the energy Internet. This puts higher demands on data processing and analysis capabilities, so how to develop more powerful data processing tools, especially when dealing with large, heterogeneous data sets, remains a key issue. | |
| dc.description.abstract | With the development of power system and the improvement of intelligence level, power consumption forecast plays a vital role in power system operation management, energy dispatching and market trading. Effective power demand forecasting is the key to power system planning and operation, and is of great significance to achieve safe, efficient and sustainable energy supply. However, the traditional deep learning model has the problem of falling into local optimal in the optimization process, which leads to the unstable performance of the model. To overcome this problem, the particle swarm optimization (PSO) algorithm is improved in this study to improve the performance of deep learning models in power consumption prediction tasks. This study collates and summarizes the challenges encountered when dealing with nonlinear, non-stationary, and high-dimensional data. To overcome these challenges, an improved particle swarm optimization (PSO) algorithm is proposed to optimize the parameters of deep learning models, thereby enhancing the model's fitting ability and generalization performance. The improved PSO algorithm in this study adopts dynamic weight adjustment and multi-stage optimization strategy, which effectively realizes the balance between global search and local search, and greatly improves the performance of the model in complex power systems. In the process of model construction, the stack ensemble learning method is adopted, and five machine learning methods including long short-term memory network (LSTM) are used to build a deeply integrated power consumption model prediction model. To verify the validity and applicability of the model, extensive experimental tests are carried out on real world power system data sets. The experimental results show that the PSO-Stacking model in this study has a root-mean-square error (RMSE) of 0.095, a mean absolute error (MAE) of 0.074, and an R square (R²) of 0.862, which are robust performance indicators. These results demonstrate the effectiveness of improved particle swarm optimization algorithm and stacked ensemble learning model in power consumption prediction tasks. Compared with the traditional deep learning model, the optimized deep learning model using the improved PSO algorithm shows considerable improvement in accuracy, stability and response speed. | |
| dc.format.extent | 54 | |
| dc.identifier.citation | Alkhattabi, Moayad. (2024). Research on Electricity Consumption Prediction Based on Deep Integration Models (Master’s thesis, Harbin Institute of Technology). | |
| dc.identifier.uri | https://lib.hit.edu.cn/main.htm | |
| dc.identifier.uri | https://hdl.handle.net/20.500.14154/75434 | |
| dc.language.iso | en | |
| dc.publisher | Harbin Institute of Technology | |
| dc.subject | Deep learning | |
| dc.subject | electricity consumption forecasting | |
| dc.subject | Particle Swarm Optimization algorithm | |
| dc.subject | Optimization of parameter searching for Stacking | |
| dc.title | RESEARCH ON ELECTRICITY CONSUMPTION PREDICTION BASED ON DEEP INTEGRATION MODELS | |
| dc.type | Thesis | |
| sdl.degree.department | School of Economics and Management | |
| sdl.degree.discipline | Management Science and Engineering | |
| sdl.degree.grantor | Harbin Institute of Technology | |
| sdl.degree.name | Master of Management |