Ordered charging optimization method based on time-of-use electricity price

Abstract

The invention discloses an ordered charging optimization method based on time-of-use electricity price, and the method comprises the steps: analyzing the daily travel habits and life behaviors of a user, simulating the disordered charging behaviors of the user in combination with a Monte Carlo algorithm and a probability statistics method, predicting the charging load demands of an electric vehicle in different time periods, constructing a user behavior model based on the charging load demands, and carrying out the optimization of the user behavior model; formulating a time-of-use electricity price policy; secondly, real-time electricity price and load information is transmitted to a user through an intelligent platform and a mobile application program, and the user sets automatic charging time after acquiring real-time dynamic state of electricity price fluctuation so as to complete charging in an electricity price valley period; 3, providing additional motivation measures in combination with the dynamic electricity price model, enhancing the charging willingness of the user in a low ebb period, and motivating the user to actively respond to a time-of-use electricity price policy; through effective combination of technology, excitation and user participation, effective coordination of load balance, user economy and power grid stability is realized, and a solid foundation is provided for a sustainable power system.

Description

Technical Field

[0001] The present invention belongs to the technical field of orderly charging of electric vehicles, and in particular relates to an orderly charging optimization method based on time-of-use electricity prices. Background Art

[0002] Orderly charging is widely used in sectors such as electric vehicles. For example, during periods of low grid load, electric vehicles can be charged at higher power levels, quickly achieving full capacity. During peak load periods, charging power is appropriately reduced or suspended to prevent the grid from being overburdened by a large number of electric vehicles charging simultaneously, thus maintaining stable grid operation. Furthermore, ordered charging can be used to rationally arrange charging plans based on users' actual needs and electricity usage habits, providing more convenient and economical charging services.

[0003] In the disorderly charging mode, users are accustomed to charging their vehicles at convenient times, such as immediately after getting home from get off work. This will cause the power grid to be overloaded during the evening peak hours, which in turn causes instability and fluctuations in the power system. To solve the above problems, it is necessary to develop an orderly charging optimization method based on time-of-use electricity prices. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of the existing technology and provide an orderly charging optimization method based on time-of-use electricity prices. Through the effective combination of technology, incentives and user participation, it achieves effective coordination among load balance, user economy and grid stability, providing a solid foundation for a sustainable power system.

[0005] The object of the present invention is achieved as follows: a method for optimizing orderly charging based on time-of-use electricity prices, comprising the following steps: Step 1: Conduct a detailed analysis of users' daily travel habits and lifestyle behaviors. By combining Monte Carlo algorithms with probabilistic statistical methods, we simulate users' disordered charging behaviors and predict the load demand when electric vehicles are connected to the grid at different time periods. Based on this data, we build a user behavior model and formulate a more accurate time-of-use electricity pricing policy. The time-of-use electricity pricing policy divides electricity prices into peak, flat, and off-peak periods. Step 2: Real-time electricity price and load information is delivered to users through intelligent platforms and mobile applications. After obtaining real-time dynamics of electricity price fluctuations, users can set automatic charging time to complete charging during low electricity price periods and avoid charging during peak periods as much as possible; Step three: Provide additional incentives in combination with the dynamic electricity price model to enhance users' willingness to charge during off-peak hours and encourage users to actively respond to time-of-use electricity price policies.

[0006] Preferably, the step 1 is specifically: First, we leverage smart meters, charging facility records, and user apps to collect massive amounts of user data across multiple channels, including daily departure and return times, mileage, charging start and end times, charging duration, and charge volume. Then, using big data analysis technology, we deeply mine the collected data, analyze users' travel patterns and characteristics, and study the relationship between their daily behaviors and charging behaviors; Next, the Monte Carlo algorithm was used to simulate uncertain events using a large amount of random data. In this scenario, the charging cycles, charging times, and charging amounts of different users were randomly generated based on the probability distribution derived from their travel habits and daily behaviors. Probabilistic statistical methods were then used to determine the probability distribution parameters of these random variables, including the mean and variance of the charging time. The simulation was repeated multiple times to obtain the load curves for electric vehicles under different conditions when no charging was required. Next, based on the simulated disordered charging behavior data, a time series analysis algorithm is used to predict the load demand of electric vehicles connected to the power grid in different time periods. The impact of seasonal changes, weather factors, and special holidays on the appearance and charging behavior is taken into account, and the prediction model is continuously optimized to improve its accuracy. Next, a user behavior model is constructed by integrating travel habits, daily life behaviors, charging behaviors, and load demand forecast results. A clustering algorithm is used to group users with similar behaviors together. A feature profile is created for each user category to describe their charging behavior characteristics and load demand patterns. Finally, based on the user behavior model and load demand forecast, electricity prices are divided into peak periods, flat periods and off-peak periods. At the same time, the time-of-use electricity price policy is evaluated and adjusted, and the electricity price level and time division of each period are optimized according to user response, grid operation status and market changes.

[0007] Preferably, artificial intelligence algorithms are used to dynamically adjust the electricity price structure according to changes in grid load, so that the electricity price structure can adapt to load fluctuations in real time, forming a dynamic time-of-use electricity price model, helping the grid to flexibly respond to peak electricity consumption and load changes, reduce power supply pressure, and maintain grid stability.

[0008] Preferably, step 2 also includes: providing personalized charging suggestions based on the user's charging preferences and grid load conditions through an intelligent platform, and pushing them to the corresponding users through a mobile application to help users optimize their charging plans and form personalized user charging behaviors.

[0009] Preferably, a machine learning algorithm is used to analyze the user's historical charging data and behavior patterns, predict the user's future charging needs, and provide the user with personalized charging time recommendations.

[0010] Preferably, the step three also includes: fully combining the dynamic time-of-use electricity price model to provide additional incentives to encourage users to choose to charge during off-peak hours, and enable them to accumulate points or obtain rewards when charging during off-peak hours as part of future charging costs, thereby encouraging users to actively respond to the time-of-use electricity price policy.

[0011] Preferably, the step three also includes: using blockchain technology to record electricity price information and charging transactions, providing users with a higher degree of trust, and at the same time using the distributed ledger generated by blockchain technology to clearly understand their own charging records and cost savings in real time.

[0012] Due to the adoption of the above technical solution, the beneficial effects of the present invention are as follows: the orderly charging optimization strategy based on time-of-use electricity prices of the present invention achieves effective coordination of load balance, user economy and grid stability through the effective combination of technology, incentives and user participation, providing a solid foundation for a sustainable power system. DETAILED DESCRIPTION

[0013] The technical solution of the present invention is further specifically described below through examples.

[0014] The present invention provides an orderly charging optimization method based on time-of-use electricity prices.

[0015] Step 1: Conduct a detailed analysis of users' daily travel habits and living behaviors. By combining the Monte Carlo algorithm and probabilistic statistical methods, simulate users' disordered charging behaviors and predict the load demand when electric vehicles are connected to the power grid in different time periods. Based on this data, build a user behavior model and formulate a more accurate time-of-use electricity price policy. The time-of-use electricity price policy divides electricity prices into peak hours, flat hours, and off-peak hours.

[0016] First, we leverage smart meters, charging facility records, and user apps to collect massive amounts of user data across multiple channels, including daily departure and return times, mileage, charging start and end times, charging duration, and charge volume. Then, using big data analysis technology, we deeply mine the collected data, analyze users' travel patterns and characteristics, and study the relationship between their daily behaviors and charging behaviors; Next, the Monte Carlo algorithm was used to simulate uncertain events using a large amount of random data. In this scenario, the charging cycles, charging times, and charging amounts of different users were randomly generated based on the probability distribution derived from their travel habits and daily behaviors. Probabilistic statistical methods were then used to determine the probability distribution parameters of these random variables, including the mean and variance of the charging time. The simulation was repeated multiple times to obtain the load curves for electric vehicles under different conditions when no charging was required. Next, based on the simulated disordered charging behavior data, a time series analysis algorithm is used to predict the load demand of electric vehicles connected to the power grid in different time periods. The impact of seasonal changes, weather factors, and special holidays on the appearance and charging behavior is taken into account, and the prediction model is continuously optimized to improve its accuracy. Next, a user behavior model is constructed by integrating travel habits, daily life behaviors, charging behaviors, and load demand forecast results. A clustering algorithm is used to group users with similar behaviors together. A feature profile is created for each user category to describe their charging behavior characteristics and load demand patterns. Finally, based on the user behavior model and load demand forecast, electricity prices are divided into peak periods, flat periods and off-peak periods. At the same time, the time-of-use electricity price policy is evaluated and adjusted, and the electricity price level and time division of each period are optimized according to user response, grid operation status and market changes.

[0017] In the later stage, artificial intelligence algorithms can also be used to dynamically adjust the electricity price structure according to changes in grid load, so that the electricity price structure can adapt to load fluctuations in real time, forming a dynamic time-of-use electricity price model, helping the grid to flexibly respond to peak electricity consumption and load changes, reduce power supply pressure, and maintain grid stability.

[0018] Step 2: Real-time electricity price and load information is delivered to users through intelligent platforms and mobile applications. After obtaining real-time dynamics of electricity price fluctuations, users can set automatic charging time to complete charging during the period of low electricity prices and avoid charging during peak hours as much as possible.

[0019] The intelligent platform provides personalized charging recommendations based on user charging preferences and grid load conditions, and pushes them to users via mobile apps, helping them optimize their charging plans and develop personalized charging behaviors. Specifically, machine learning algorithms analyze users' historical charging data and behavior patterns, predicting their future charging needs and providing personalized charging time recommendations.

[0020] Step three: Provide additional incentives in combination with the dynamic electricity price model to enhance users' willingness to charge during off-peak hours and encourage users to actively respond to time-of-use electricity price policies.

[0021] Specifically, the dynamic time-of-use electricity price model is fully combined to provide additional incentives to encourage users to choose to charge during off-peak hours. When charging during off-peak hours, they can accumulate points or obtain rewards as part of future charging costs, thereby encouraging users to actively respond to the time-of-use electricity price policy.

[0022] In the future, blockchain technology can also be used to record electricity price information and charging transactions, providing users with a higher level of trust. At the same time, it can be used to clearly understand one's own charging records and cost savings in real time through the distributed ledger generated by blockchain technology.

[0023] The orderly charging optimization strategy based on time-of-use electricity pricing provided by this invention is a method that uses dynamic electricity pricing to guide users to charge at different time periods, aiming to balance the grid load and optimize the use of overall power resources. In the disorderly charging mode, users are accustomed to charging their vehicles at convenient times, such as immediately after getting home from get off work. This causes the grid to be overloaded during the evening peak period, which in turn causes instability and fluctuations in the power system. To address this situation, the charging strategy based on time-of-use electricity pricing optimizes charging behavior and grid load management by subdividing electricity price periods, applying predictive models, and analyzing user behavior.

[0024] Implementing this strategy first requires a detailed analysis of users' daily travel habits and lifestyles. By combining Monte Carlo algorithms with probabilistic statistical methods, it's possible to simulate users' disordered charging behavior and predict the load demand when EVs are connected to the grid at different times. This data is used to build user behavior models, helping grid managers formulate more precise time-of-use pricing policies, thereby encouraging users to charge during periods of lower prices and load. This time-of-use pricing strategy categorizes electricity prices into peak, flat, and off-peak periods, encouraging users to charge during off-peak periods to balance grid load and optimize resources.

[0025] To ensure users are informed of electricity prices and recommended charging times, charging stations and power companies deliver real-time price and load information to users through intelligent platforms and mobile applications. Users can use these applications to obtain real-time updates on price fluctuations and set automatic charging times to complete charging during periods of low electricity prices. This approach not only saves users money but also indirectly reduces the burden on the power grid, thereby improving its stability and security. Intelligent applications can provide personalized recommendations based on user charging preferences and grid load conditions, helping users optimize their charging plans and further enhancing their charging experience.

[0026] To increase users' willingness to charge during off-peak hours, power companies and charging stations can integrate dynamic electricity pricing models to offer additional incentives, such as discounts, points, or coupons. Users who choose to charge during off-peak hours can accumulate points or receive rewards as part of a reduction in future charging costs, thereby encouraging users to actively respond to time-of-use pricing policies. Such incentive strategies use economic means to alter user charging behavior, aligning it more closely with the grid's load regulation objectives, ultimately creating a win-win situation for both users and the power system.

[0027] Artificial intelligence and machine learning technologies play a vital role in optimizing user charging time recommendations. By analyzing historical user charging data and behavioral patterns, machine learning algorithms can predict future charging needs and provide personalized charging time recommendations. For example, if the system learns that a user typically charges after 11 p.m., it can offer more attractive electricity prices around this time, further optimizing the user's charging decisions. Furthermore, AI algorithms can dynamically adjust electricity pricing based on grid load changes, adapting to load fluctuations in real time. This helps grid operators flexibly respond to peak demand and load fluctuations, reducing power supply pressures.

[0028] Time-of-use pricing strategies not only benefit users but also allow grid operators to dynamically adjust electricity prices using real-time data and predictive models. Power dispatchers and systems can use these models to predict future load conditions and formulate pricing strategies in advance to smooth the grid's load curve. Such real-time price adjustments not only help balance supply and demand but also reduce power supply pressure during peak hours, ensuring stable system operation. Grid dispatch systems can use intelligent management systems to distribute and adjust loads, flexibly allocating power resources to different regions and optimizing overall energy use.

[0029] Combined with advanced intelligent charging management systems, time-of-use pricing strategies enable a highly intelligent and controllable charging process. Charging stations and power companies leverage these systems to more effectively distribute loads, adjust pricing strategies, respond to user needs, and improve the overall efficiency of the power grid. These systems combine sensor data, real-time monitoring, and intelligent scheduling technologies to make the entire charging process smoother and more efficient. Users charging during periods of low electricity prices also create greater opportunities for the use of renewable energy. Renewable energy sources such as wind and photovoltaic power generation are abundant during specific periods, and time-of-use pricing strategies can accommodate charging during these times, increasing the utilization of clean energy.

[0030] In the future, with the introduction of big data analytics and blockchain technology, the application of time-of-use electricity pricing strategies will become even more precise and transparent. Blockchain technology ensures the transparency and immutability of electricity pricing information and charging transactions, providing users with greater trust while optimizing energy distribution and utilization. Through a distributed ledger, users can clearly understand their charging records and cost savings, further enhancing engagement and driving the intelligent development of the overall energy system.

[0031] In general, the orderly charging optimization strategy based on time-of-use electricity prices in this invention achieves effective coordination among load balance, user economy and grid stability through the combination of technology, incentives and user participation, providing a solid foundation for a sustainable power system.

[0032] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be included in the scope of the claims of the present invention.

Claims

1. An orderly charging optimization method based on time-of-use electricity price, characterized in that: The steps include: Step 1: Conduct a detailed analysis of users' daily travel habits and lifestyle behaviors. By combining Monte Carlo algorithms with probabilistic statistical methods, we simulate users' disordered charging behaviors and predict the load demand when electric vehicles are connected to the grid at different time periods. Based on this data, we build a user behavior model and formulate a more accurate time-of-use electricity pricing policy. The time-of-use electricity pricing policy divides electricity prices into peak, flat, and off-peak periods. Step 2: Real-time electricity price and load information is delivered to users through intelligent platforms and mobile applications. After obtaining real-time dynamics of electricity price fluctuations, users can set automatic charging time to complete charging during low electricity price periods and avoid charging during peak periods as much as possible; Step three: Provide additional incentives in combination with the dynamic electricity price model to enhance users' willingness to charge during off-peak hours and encourage users to actively respond to time-of-use electricity price policies.

2. The method for optimizing orderly charging based on time-of-use electricity prices according to claim 1, characterized in that: The step 1 is specifically as follows: First, we leverage smart meters, charging facility records, and user apps to collect massive amounts of user data across multiple channels, including daily departure and return times, mileage, charging start and end times, charging duration, and charge volume. Then, using big data analysis technology, we deeply mine the collected data, analyze users' travel patterns and characteristics, and study the relationship between their daily behaviors and charging behaviors; Next, the Monte Carlo algorithm was used to simulate uncertain events using a large amount of random data. In this scenario, the charging cycles, charging times, and charging amounts of different users were randomly generated based on the probability distribution derived from their travel habits and daily behaviors. Probabilistic statistical methods were then used to determine the probability distribution parameters of these random variables, including the mean and variance of the charging time. The simulation was repeated multiple times to obtain the load curves for electric vehicles under different conditions when no charging was required. Next, based on the simulated disordered charging behavior data, a time series analysis algorithm is used to predict the load demand of electric vehicles connected to the power grid in different time periods. The impact of seasonal changes, weather factors, and special holidays on the appearance and charging behavior is taken into account, and the prediction model is continuously optimized to improve its accuracy. Next, a user behavior model is constructed by integrating travel habits, daily life behaviors, charging behaviors, and load demand forecast results. A clustering algorithm is used to group users with similar behaviors together. A feature profile is created for each user category to describe their charging behavior characteristics and load demand patterns. Finally, based on the user behavior model and load demand forecast, electricity prices are divided into peak periods, flat periods and off-peak periods. At the same time, the time-of-use electricity price policy is evaluated and adjusted, and the electricity price level and time division of each period are optimized according to user response, grid operation status and market changes.

3. The method for optimizing orderly charging based on time-of-use electricity prices according to claim 2, characterized in that: By using artificial intelligence algorithms, the electricity price structure is dynamically adjusted according to changes in grid load, so that the electricity price structure can adapt to load fluctuations in real time, forming a dynamic time-of-use electricity price model, helping the grid to flexibly respond to peak electricity consumption and load changes, reduce power supply pressure, and maintain grid stability.

4. The method for optimizing orderly charging based on time-of-use electricity prices according to claim 1, characterized in that: The second step also includes: providing personalized charging suggestions based on the user's charging preferences and grid load conditions through the intelligent platform, and pushing them to the corresponding users through the mobile application to help users optimize their charging plans and form personalized user charging behaviors.

5. The method for optimizing orderly charging based on time-of-use electricity prices according to claim 4, characterized in that: Using machine learning algorithms, we analyze users’ historical charging data and behavior patterns, predict their future charging needs, and provide them with personalized charging time recommendations.

6. The method for optimizing orderly charging based on time-of-use electricity prices according to claim 1, characterized in that: The step three also includes: fully combining the dynamic time-of-use electricity price model to provide additional incentives to encourage users to choose to charge during off-peak hours, and enable them to accumulate points or obtain rewards when charging during off-peak hours as part of future charging costs, thereby encouraging users to actively respond to the time-of-use electricity price policy.

7. The method for optimizing orderly charging based on time-of-use electricity prices according to claim 1, characterized in that: The step three also includes: using blockchain technology to record electricity price information and charging transactions to provide users with a higher level of trust, and at the same time using the distributed ledger generated by blockchain technology to clearly understand their own charging records and cost savings in real time.