Energy Consumption Prediction and Optimization of Electric Vehicles Based on RLS and Improved SOA
The new energy vehicle industry is facing new challenges. To predict and optimize the energy consumption of electric vehicles, this study predicts energy consumption based on the energy consumption characteristics of the electric vehicle power system and air conditioning system, and combines path op...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10464291/ |
| _version_ | 1797243292437446656 |
|---|---|
| author | Chunling Liu |
| author_facet | Chunling Liu |
| author_sort | Chunling Liu |
| collection | DOAJ |
| description | The new energy vehicle industry is facing new challenges. To predict and optimize the energy consumption of electric vehicles, this study predicts energy consumption based on the energy consumption characteristics of the electric vehicle power system and air conditioning system, and combines path optimization algorithms for energy-saving path planning. The study first improves the recursive least squares algorithm by combining the forgetting factor, and constructs a vehicle energy consumption identification model based on the improved recursive least squares algorithm and neural network. Then, a path optimization model based on improved seagull optimization is established using chaotic mapping strategy and t-distribution to improve the seagull optimization algorithm. The results showed that the predicted final energy consumption of the model constructed in the study was 2.81kW.h, with an error rate of 5.1%. The improved seagull optimization algorithm obtained an optimal solution of 30.88m for burma14 and 423.74m for oliver30, which were consistent with the published optimal solutions. When the air conditioning was turned on, the energy consumption of the path selected by the algorithm was reduced by about 5.6%. Under the condition of not turning on the air conditioning, the energy consumption of the path selected by the algorithm was reduced by about 4.98%. In summary, the model constructed through research has good application effects in predicting and optimizing vehicle energy consumption. The contribution of the research lies in it helps to reveal the laws of energy utilization in electric vehicles, improve the economy, safety, and environmental friendliness of electric vehicles during operation, and promote the overall management of new energy vehicles. |
| first_indexed | 2024-04-24T18:52:48Z |
| format | Article |
| id | doaj.art-5f4ef6d2d28b495eafb49f26da232fef |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-24T18:52:48Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-5f4ef6d2d28b495eafb49f26da232fef2024-03-26T17:49:13ZengIEEEIEEE Access2169-35362024-01-0112381803819110.1109/ACCESS.2024.337535510464291Energy Consumption Prediction and Optimization of Electric Vehicles Based on RLS and Improved SOAChunling Liu0https://orcid.org/0009-0004-6165-7572Institute of Automotive Engineering, College of Humanities & Information, Changchun University of Technology, Changchun, ChinaThe new energy vehicle industry is facing new challenges. To predict and optimize the energy consumption of electric vehicles, this study predicts energy consumption based on the energy consumption characteristics of the electric vehicle power system and air conditioning system, and combines path optimization algorithms for energy-saving path planning. The study first improves the recursive least squares algorithm by combining the forgetting factor, and constructs a vehicle energy consumption identification model based on the improved recursive least squares algorithm and neural network. Then, a path optimization model based on improved seagull optimization is established using chaotic mapping strategy and t-distribution to improve the seagull optimization algorithm. The results showed that the predicted final energy consumption of the model constructed in the study was 2.81kW.h, with an error rate of 5.1%. The improved seagull optimization algorithm obtained an optimal solution of 30.88m for burma14 and 423.74m for oliver30, which were consistent with the published optimal solutions. When the air conditioning was turned on, the energy consumption of the path selected by the algorithm was reduced by about 5.6%. Under the condition of not turning on the air conditioning, the energy consumption of the path selected by the algorithm was reduced by about 4.98%. In summary, the model constructed through research has good application effects in predicting and optimizing vehicle energy consumption. The contribution of the research lies in it helps to reveal the laws of energy utilization in electric vehicles, improve the economy, safety, and environmental friendliness of electric vehicles during operation, and promote the overall management of new energy vehicles.https://ieeexplore.ieee.org/document/10464291/Recursive least squares algorithmseagull optimization algorithmvehicle energy consumptionneural networkpath planning |
| spellingShingle | Chunling Liu Energy Consumption Prediction and Optimization of Electric Vehicles Based on RLS and Improved SOA IEEE Access Recursive least squares algorithm seagull optimization algorithm vehicle energy consumption neural network path planning |
| title | Energy Consumption Prediction and Optimization of Electric Vehicles Based on RLS and Improved SOA |
| title_full | Energy Consumption Prediction and Optimization of Electric Vehicles Based on RLS and Improved SOA |
| title_fullStr | Energy Consumption Prediction and Optimization of Electric Vehicles Based on RLS and Improved SOA |
| title_full_unstemmed | Energy Consumption Prediction and Optimization of Electric Vehicles Based on RLS and Improved SOA |
| title_short | Energy Consumption Prediction and Optimization of Electric Vehicles Based on RLS and Improved SOA |
| title_sort | energy consumption prediction and optimization of electric vehicles based on rls and improved soa |
| topic | Recursive least squares algorithm seagull optimization algorithm vehicle energy consumption neural network path planning |
| url | https://ieeexplore.ieee.org/document/10464291/ |
| work_keys_str_mv | AT chunlingliu energyconsumptionpredictionandoptimizationofelectricvehiclesbasedonrlsandimprovedsoa |