Intelligent scheduling method and system for local energy management system based on day-ahead electricity price

Abstract

The invention relates to the technical field of energy intelligent scheduling, in particular to a local energy management system intelligent scheduling method and system based on day-ahead electricity price. The method comprises the following steps: obtaining a day-ahead electricity price, and obtaining corresponding power grid load data in the date; predicting the photovoltaic generating capacity; searching past load and predicted load of the station; identifying the charging and discharging interval, and dividing charging and discharging time slices; determining a charging period, a discharging period and electric energy; adjusting a charging and discharging strategy according to the result, and outputting the strategy; the system comprises a data acquisition module, a photovoltaic generating capacity prediction module, a load prediction module, an analysis module, a determination module and an adjustment module, realizes dynamic identification of low-price charging and high-price discharging intervals based on market real-time electricity price data, avoids the rigid defect of a traditional fixed threshold or fixed time period strategy, and improves the efficiency of the system. And the energy storage charging and discharging scheduling is more flexible, and the economic benefit is higher.

Description

Technical Field

[0001] This invention relates to the field of intelligent energy dispatching technology, and in particular to an intelligent dispatching method and system for a local energy management system based on day-ahead electricity prices. Background Technology

[0002] With the development of new energy technologies, distributed photovoltaic (PV) and energy storage systems are rapidly becoming widespread on the user side. Local Energy Management Systems (EMS), as the core dispatching platform coordinating power sources, the grid, loads, and energy storage, play a crucial role in optimizing energy use and improving system efficiency and economy. Traditional EMS systems often focus on predicting load and energy output when formulating dispatching strategies, but they do not fully utilize electricity market price signals (especially day-ahead prices), preventing energy storage systems from achieving effective price arbitrage and hindering further reductions in user electricity costs. Simultaneously, some systems ignore the physical limitations and grid constraints of energy storage system operation, potentially leading to strategy failures or increased system operational risks. Therefore, how to fully utilize electricity price fluctuation information and combine the dispatching capabilities of energy storage and PV to formulate flexible, economical, and efficient EMS dispatching strategies while ensuring system safety has become an important research direction in distributed energy management.

[0003] Currently, fixed electricity price thresholds or time periods are typically used to control the charging and discharging behavior of energy storage devices, such as charging at low prices at night and discharging at high prices during the day.

[0004] However, existing charging and discharging strategies based on fixed thresholds cannot dynamically adapt to real-time fluctuations in market electricity prices. The strategies are rigid, lack flexibility, have limited economic benefits, and are difficult to maximize the use of electricity price differences. Summary of the Invention

[0005] The purpose of this invention is to provide an intelligent scheduling method and system for a local energy management system based on current electricity prices. This aims to solve the technical problems of existing charging and discharging strategies based on fixed thresholds, which cannot dynamically adapt to real-time fluctuations in market electricity prices, have strong rigidity, lack flexibility, have limited economic benefits, and are difficult to maximize the use of electricity price differences.

[0006] To achieve the above objectives, the present invention employs an intelligent dispatching method for a local energy management system based on day-ahead electricity prices, comprising the following steps:

[0007] Obtain the day-ahead electricity price and the corresponding grid load data for that date;

[0008] Predicting photovoltaic power generation;

[0009] Collect data on past load at the site and predict the load.

[0010] Identify the charging and discharging range and divide the charging and discharging time segments;

[0011] Determine the charging period, discharging period, and electrical energy;

[0012] Adjust the charging and discharging strategy based on the results, and output the strategy.

[0013] In the steps of obtaining the day-ahead electricity price and acquiring the corresponding grid load data for that date:

[0014] Call the electricity market data interface to obtain hourly electricity price information {P0, P1, ..., P} for the target date. 23};

[0015] By using the load database, the corresponding power grid load data for that date is obtained, ensuring the time-series integrity of the load data.

[0016] In the step of predicting photovoltaic power generation:

[0017] Deep learning time series models are trained using historical power generation data from each power station and the station's own hardware data.

[0018] Forecast the 24-hour power generation data for the day before the price is predicted {PV0, PV1, ... PV} 23}

[0019] Among the steps involved in collecting past load data from the power station and predicting the load:

[0020] Collect the load data of each site over a period of time and use it to train the model;

[0021] Forecast the day's price and the 24-hour load {L0, L1, ..., L} 23}

[0022] Among them, the steps of identifying the charge / discharge range and dividing the charge / discharge time segment are as follows:

[0023] By using a set threshold for electricity price differences, the electricity price curve is dynamically analyzed to identify continuous low-price charging intervals and high-price discharging intervals.

[0024] By iterating through price data points throughout the 24 hours of a day, we can detect the upward and downward trends of electricity prices, determine the low and high points of electricity prices, and divide the charging and discharging time segments.

[0025] The charging and discharging cycle is dynamically determined by using a sliding window. This charging and discharging cycle includes a peak and a trough in the electricity price.

[0026] Among the steps for determining the charging period, discharging period, and electrical energy:

[0027] Within each interval, sort by time sequence, select the low electricity price area for charging, and the high electricity price area for discharging. The charging time period should be before the discharging time period.

[0028] The safe available capacity is calculated based on the battery's current state of charge and a preset safe state of charge threshold, avoiding overcharging and over-discharging.

[0029] In the step of adjusting the charging and discharging strategy based on the results and outputting the strategy:

[0030] Based on the segmented calculation results, some charging and discharging strategies are adjusted to generate a complete 24-hour charging and discharging strategy recommendation, including the hourly charging and discharging power and corresponding status.

[0031] During the invocation phase, the interface is re-invoked every hour to obtain updates on the strategy and charging / discharging power.

[0032] This invention also provides an intelligent dispatching system for a local energy management system based on day-ahead electricity prices, comprising a data acquisition module, a photovoltaic power generation prediction module, a load prediction module, an analysis module, a determination module, and an adjustment module; wherein:

[0033] The data acquisition module is used to obtain the day-ahead electricity price and the corresponding grid load data for that date;

[0034] The photovoltaic power generation prediction module is used to predict photovoltaic power generation.

[0035] The load prediction module is used to predict the load.

[0036] The analysis module is used to identify the charge / discharge interval and divide the charge / discharge time segments.

[0037] The determining module is used to determine the charging period, the discharging period, and the electrical energy.

[0038] The adjustment module is used to adjust the results and output the strategy.

[0039] This invention discloses an intelligent dispatching method and system for a local energy management system based on day-ahead electricity prices. The system employs a data acquisition module, a photovoltaic power generation prediction module, a load prediction module, an analysis module, a determination module, and an adjustment module to perform the following steps: acquiring the day-ahead electricity price and obtaining the corresponding grid load data for that date; predicting photovoltaic power generation; collecting past load data from power plants and predicting the load; identifying charging and discharging intervals and dividing charging and discharging time segments; determining charging periods, discharging periods, and electrical energy; adjusting the charging and discharging strategy based on the results, and outputting the strategy. In this approach, by analyzing the day-ahead electricity price sequence, periods of significant price fluctuations are automatically identified. Combined with local load prediction, photovoltaic prediction, and energy storage status, a strategy is implemented where energy storage charges during low electricity prices and discharges during high electricity prices, thereby achieving economic arbitrage and reducing load costs. The system also dynamically optimizes the strategy based on factors such as grid power purchase and sale costs, energy storage capacity, and safe state of charge (SOC), supporting retrospective adjustments between different time periods to improve overall dispatching benefits and operational safety. The variables are:

[0040] t∈{0,1,…,23}: represents the t-th hour of the day;

[0041] Pt: Market electricity price in hour t Lt: Load power (kW) at hour t; ut: Energy storage operating power at hour t, in kW, positive value is charging, negative value is discharging; SOCt: State of the energy storage system at time t (%).

[0042] CBESS: Total capacity of energy storage system (kWh), PBESSmax: Maximum charging / discharging power of energy storage system (kW), PGRIDmax: Maximum grid-connected power (kW);

[0043] ηc∈(0,1]: charging efficiency, ηd∈(0,1]: discharging efficiency

[0044] Objective function:

[0045]

[0046] Explanation: ut>0: indicates charging during low electricity prices, leading to an increase in instantaneous electricity purchase; ut<0: indicates discharging during high electricity prices, reducing electricity purchase. By using real-time market electricity price data, this invention dynamically identifies low-price charging and high-price discharging intervals, avoiding the rigidity of traditional fixed threshold or fixed time period strategies. This makes energy storage charging and discharging scheduling more flexible and economically efficient. Specifically, it not only adjusts strategies based on electricity price fluctuations but also combines load forecasting, battery current state of charge (SOC), and safety thresholds to achieve scientific allocation of charging and discharging power and time periods, effectively preventing overcharging or over-discharging and extending the lifespan of energy storage devices. Furthermore, by dividing the electricity price curve into multiple intervals and calculating charging and discharging strategies segment by segment, combined with historical charging and discharging records for supplementary charging, more precise energy management is achieved, improving the overall performance of the energy storage system. Additionally, by fully utilizing electricity price differences for intelligent charging and discharging, this invention significantly reduces electricity costs, improves the economic efficiency of the energy storage system, and releases energy during high-price periods, alleviating grid pressure and promoting stable grid operation. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 This is a flowchart of the steps of the intelligent dispatching method for a local energy management system based on day-ahead electricity prices according to the present invention.

[0049] Figure 2 This is a flowchart illustrating the intelligent dispatching method for a local energy management system based on day-ahead electricity prices according to the present invention.

[0050] Figure 3 This is a flowchart of steps S100 of the present invention.

[0051] Figure 4 This is a flowchart of steps S200 of the present invention.

[0052] Figure 5 This is a flowchart of steps S300 of the present invention.

[0053] Figure 6 This is a flowchart of steps S400 of the present invention.

[0054] Figure 7 This is a flowchart of steps S500 of the present invention.

[0055] Figure 8 This is a flowchart of steps S600 of the present invention.

[0056] Figure 9 This is a schematic diagram of the present invention for obtaining power grid load data.

[0057] Figure 10 This is a schematic diagram of the intelligent dispatching system of the local energy management system based on day-ahead electricity prices of the present invention.

[0058] 801 - Data Acquisition Module, 802 - Photovoltaic Power Generation Prediction Module, 803 - Load Prediction Module, 804 - Analysis Module, 805 - Determination Module, 806 - Adjustment Module. Detailed Implementation

[0059] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application.

[0060] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0061] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0062] Please see Figures 1-9 This invention provides an intelligent dispatching method for a local energy management system based on day-ahead electricity prices, comprising the following steps:

[0063] S100: Obtain the day-ahead electricity price and the corresponding grid load data for that date.

[0064] In this embodiment, the day-ahead electricity price is obtained, and the corresponding grid load data for that date is acquired. The specific process is as follows:

[0065] S101: Call the electricity market data interface to obtain hourly electricity price information {P0, P1, ..., P} for the target date.23};

[0066] S102: Obtain the corresponding power grid load data for the given date from the load database to ensure the time-series integrity of the load data.

[0067] During the above process, the system automatically calls the electricity market data interface to obtain hourly electricity price information {P0, P1, ..., P} for the target date. 23}, obtain the corresponding power grid load data for that date through a load database or real-time acquisition system to ensure the time-series integrity of the load data (24 hours), see Figure 9 .

[0068] S200: Predicted photovoltaic power generation.

[0069] In this embodiment, the process of predicting photovoltaic power generation is as follows:

[0070] S201: Train a deep learning time series model using historical power generation data from each power station and the station's own hardware data;

[0071] S202: 24-hour power generation data for the day-ahead price forecast {PV0, PV1, ... PV} 23}

[0072] In the above process, photovoltaic power generation is related to the capacity and hardware of the power station itself, as well as the weather factors of the region. A deep learning time-series model is trained using historical power generation data from each power station and its own hardware data to predict the 24-hour power generation data {PV0, PV1, ... PV} for the day before the price. 23}

[0073] S300: Collects past load data for the site and predicts the load.

[0074] In this embodiment, the past load of the power station is collected and the load is predicted. The specific process is as follows:

[0075] S301: Collect the load of each site over a period of time and use it to train the model;

[0076] S302: Forecast the 24-hour load of the day before the price is predicted {L0, L1, ..., L...} 23}

[0077] In the above process, the load data of each station is related to the daily electricity consumption of customers. Daily electricity consumption is closely related to the station's historical load data, weather data, calendar characteristics, and time characteristics. It is also positively correlated with the usual electricity consumption habits of household appliances, charging stations, and special instruments. Load data from each station over a period of time is collected and used to train a model to predict the 24-hour load {L0, L1, ..., L...} of the current day's price. 23}

[0078] S400: Identifies the charge / discharge range and divides the charge / discharge time segments.

[0079] In this embodiment, the identification of the charge / discharge range and the division of charge / discharge time segments are carried out as follows:

[0080] S401: Using a set electricity price difference threshold, dynamically analyze the electricity price curve to identify continuous low-price charging intervals and high-price discharging intervals.

[0081] S402: By traversing the price data points of a 24-hour day, detect the upward and downward trends of electricity prices, determine the low and high points of electricity prices, and divide the charging and discharging time segments.

[0082] S403: The charging and discharging cycle is dynamically determined by a sliding window. This charging and discharging cycle includes a peak and a trough in the electricity price.

[0083] S404: Controls the end point of the charge / discharge cycle by the price difference between the price that drops after the peak and the price at the lowest point.

[0084] In the above process, the electricity price curve is dynamically analyzed using a set electricity price difference threshold to identify continuous low-price charging and high-price discharging intervals. By traversing price data points throughout the 24 hours of the day, the upward and downward trends of electricity prices are detected to determine the electricity price troughs and peaks, thus dividing the charging and discharging time segments. A sliding window method is used to dynamically determine the charging and discharging cycle. This period must include a peak and a trough in the electricity price; the trough is not mandatory.

[0085] Define the minimum price value within a certain price range as:

[0086]

[0087] If there exists a certain t h ∈[tb, te], satisfying:

[0088]

[0089] Then the interval [t] b , t hThis can be considered a candidate range for charging. We add it to the set:

[0090] W charge =W charge ∪{[t b , t h ]}

[0091] The corresponding discharge window can be defined as:

[0092] W discharge =W discharge ∪{[t h +1, t e ]}

[0093] Among them, t e Therefore, the end point is defined as the price difference between the price at the end of the window and the lowest point being less than ΔP, or the end point of the entire day.

[0094] The end point of the charge-discharge cycle is controlled by the price difference between the price drop after the peak and the price at the lowest point. This price difference is usually the criterion for judging whether it is worthwhile after considering various factors such as the cost of charging and discharging the battery and consumption. That is, when the price difference is greater than this value, charging at the low point and discharging at the high point can yield positive benefits, and vice versa.

[0095] S500: Determines the charging period, discharging period, and electrical energy.

[0096] In this embodiment, the charging period, discharging period, and electrical energy are determined as follows:

[0097] S501: Within each interval, sort by time, select the low electricity price area for charging, and the high electricity price area for discharging. The charging time period should be before the discharging time period.

[0098] S502: Calculates the safe available capacity based on the battery's current state of charge and the preset safe state of charge threshold, avoiding overcharging and over-discharging.

[0099] In the above process, within each interval, the process is ordered chronologically, with charging occurring in the low-electricity-price zone and discharging in the high-electricity-price zone. The charging period must precede the discharging period.

[0100] In interval T c In the middle, sorted from low to high electricity prices:

[0101]

[0102] Based on the battery's current state of charge (SOC) and a preset safe SOC threshold (e.g., 50%), the safe usable capacity is calculated to avoid overcharging or over-discharging. Of course, the charging and discharging efficiency η must be taken into account during the charging and discharging process.c and η d Considering the maximum capacity and charging / discharging power limitations of energy storage devices, charging power should be allocated rationally, based on several criteria:

[0103] For each defined electricity price range, combined with load data, a recommended charging and discharging load is calculated;

[0104] A segmented sorting method is adopted, prioritizing charging during the period with the lowest price and discharging during the period with the highest price; for the intervals that are not fully charged, supplementary adjustments are made using charging records from historical intervals to ensure that the energy storage capacity is fully utilized.

[0105] S600: Adjusts the charging and discharging strategy based on the results and outputs the strategy.

[0106] In this embodiment, the charging and discharging strategy is adjusted based on the results, and the strategy is output. The specific process is as follows:

[0107] S601: Based on the segmented calculation results, adjust some of the charging and discharging strategies to generate a complete 24-hour charging and discharging strategy recommendation, including the hourly charging and discharging power and corresponding status.

[0108] S602: During the call phase, the interface is called again every hour to obtain updates on the strategy and charging / discharging power.

[0109] In the above process, based on the segmented calculation results, some charging and discharging strategies are adjusted to generate a complete 24-hour charging and discharging strategy suggestion, including hourly charging and discharging power and corresponding status. During the invocation phase, the interface is re-invoked every hour to obtain updates to the strategy and charging and discharging power, ensuring the real-time performance of this method and bridging the gap between planning and actual execution.

[0110] Furthermore, the variables in a smart dispatching method for a local energy management system based on day-ahead electricity prices are:

[0111] t∈{0,1,…,23}: represents the t-th hour of the day;

[0112] Pt: Market electricity price in hour t Lt: Load power (kW) at hour t; ut: Energy storage operating power at hour t, in kW, positive value is charging, negative value is discharging; SOCt: State of the energy storage system at time t (%).

[0113] CBESS: Total capacity of energy storage system (kWh), PBESSmax: Maximum charging / discharging power of energy storage system (kW), PGRIDmax: Maximum grid-connected power (kW);

[0114] ηc∈(0,1]: charging efficiency, ηd∈(0,1]: discharging efficiency

[0115] Objective function:

[0116]

[0117] Explanation: ut>0: indicates charging during low electricity prices, resulting in an increase in instantaneous electricity purchases; ut<0: indicates discharging during high electricity prices, resulting in a decrease in electricity purchases.

[0118] Please see Figure 10 The present invention also provides an intelligent dispatching system for a local energy management system based on day-ahead electricity prices, comprising a data acquisition module, a photovoltaic power generation prediction module, a load prediction module, an analysis module, a determination module, and an adjustment module; wherein:

[0119] The data acquisition module is used to obtain the day-ahead electricity price and the corresponding grid load data for that date;

[0120] The photovoltaic power generation prediction module is used to predict photovoltaic power generation.

[0121] The load prediction module is used to predict the load.

[0122] The analysis module is used to identify the charge / discharge interval and divide the charge / discharge time segments.

[0123] The determining module is used to determine the charging period, the discharging period, and the electrical energy.

[0124] The adjustment module is used to adjust the results and output the strategy.

[0125] In this embodiment, the photovoltaic power generation prediction module predicts the photovoltaic power generation; the load prediction module predicts the load; the analysis module identifies the charging and discharging intervals and divides the charging and discharging time segments; the determination module determines the charging period, discharging period, and electrical energy; and the adjustment module adjusts the results and outputs the strategy.

[0126] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0127] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A smart dispatching method for a local energy management system based on day-ahead electricity prices, characterized in that, Includes the following steps: Obtain the day-ahead electricity price and the corresponding grid load data for that date; Predicting photovoltaic power generation; Collect data on past load at the site and predict the load. Identify the charging and discharging range and divide the charging and discharging time segments; Determine the charging period, discharging period, and electrical energy; Adjust the charging and discharging strategy based on the results, and output the strategy.

2. The intelligent dispatching method for a local energy management system based on day-ahead electricity prices as described in claim 1, characterized in that, In the steps of obtaining the day-ahead electricity price and acquiring the corresponding grid load data for that date: Call the electricity market data interface to obtain hourly electricity price information {P0, P1, ..., P} for the target date. 23 }; By using the load database, the corresponding power grid load data for that date is obtained, ensuring the time-series integrity of the load data.

3. The intelligent dispatching method for a local energy management system based on day-ahead electricity prices as described in claim 1, characterized in that, In the steps of predicting photovoltaic power generation: Deep learning time series models are trained using historical power generation data from each power station and the station's own hardware data. Forecast the 24-hour power generation data for the day before the price is predicted {PV0, PV1, ... PV} 23 } 4. The intelligent dispatching method for a local energy management system based on day-ahead electricity prices as described in claim 1, characterized in that, In the process of collecting past load data from the site and predicting the load: Collect the load data of each site over a period of time and use it to train the model; Forecast the day's price and the 24-hour load {L0, L1, ..., L} 23 } 5. The intelligent dispatching method for a local energy management system based on day-ahead electricity prices as described in claim 1, characterized in that, In the steps of identifying the charge / discharge range and dividing the charge / discharge time segments: By using a set threshold for electricity price differences, the electricity price curve is dynamically analyzed to identify continuous low-price charging intervals and high-price discharging intervals. By iterating through price data points throughout the 24 hours of a day, we can detect the upward and downward trends of electricity prices, determine the low and high points of electricity prices, and divide the charging and discharging time segments. The charging and discharging cycle is dynamically determined by using a sliding window. This charging and discharging cycle includes a peak and a trough in the electricity price. The end point of the charge / discharge cycle is controlled by the price difference between the price that drops after the peak and the price at the lowest point.

6. The intelligent dispatching method for a local energy management system based on day-ahead electricity prices as described in claim 5, characterized in that, In the steps of determining the charging period, discharging period, and electrical energy: Within each interval, sort by time sequence, select the low electricity price area for charging, and the high electricity price area for discharging. The charging time period should be before the discharging time period. The safe available capacity is calculated based on the battery's current state of charge and a preset safe state of charge threshold, avoiding overcharging and over-discharging.

7. The intelligent dispatching method for a local energy management system based on day-ahead electricity prices as described in claim 6, characterized in that, In the steps of adjusting the charging and discharging strategy based on the results and outputting the strategy: Based on the segmented calculation results, some charging and discharging strategies are adjusted to generate a complete 24-hour charging and discharging strategy recommendation, including the hourly charging and discharging power and corresponding status. During the invocation phase, the interface is re-invoked every hour to obtain updates on the strategy and charging / discharging power.

8. A smart dispatching system for a local energy management system based on day-ahead electricity prices, applied to the smart dispatching method for a local energy management system based on day-ahead electricity prices as described in claim 1, characterized in that, It includes a data acquisition module, a photovoltaic power generation prediction module, a load prediction module, an analysis module, a determination module, and an adjustment module; among which: The data acquisition module is used to obtain the day-ahead electricity price and the corresponding grid load data for that date; The photovoltaic power generation prediction module is used to predict photovoltaic power generation. The load prediction module is used to predict the load. The analysis module is used to identify the charge / discharge interval and divide the charge / discharge time segments. The determining module is used to determine the charging period, the discharging period, and the electrical energy. The adjustment module is used to adjust the results and output the strategy.

Images