Electric power energy management system and method based on intelligent internet of things

Abstract

The invention relates to the technical field of energy management, and discloses an electric power energy management system and method based on intelligent Internet of Things, and the system comprises a data collection unit, a data processing unit, an electric power analysis unit, an electric power prediction unit, an optimization allocation unit, and a result display unit. According to the invention, the data processing unit cleans data accurately, removes abnormities and replaces the abnormities, and guarantees the reliability of the data; the power analysis unit deeply analyzes load characteristics to obtain a peak-valley difference and a load rate, load fluctuation and operation states are clarified, and optimization scheduling and maintenance planning of the system are assisted; the power prediction unit analyzes and predicts power load and power generation power by using a time sequence, and insight into supply and demand trends in advance; and the optimal allocation unit balances supply and demand according to prediction, reasonably stores and allocates in excess, and preferentially guarantees key loads in insufficient conditions, so that the energy utilization efficiency is improved, the stable operation of the system is ensured, and the intelligent management and resource optimal utilization level of the power system is effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of energy management technology, and in particular to an electric energy management system and method based on smart Internet of Things. Background Art

[0002] Against the backdrop of the continued expansion of the power system scale, increasingly complex structure and sharp growth in electricity demand, the traditional power energy management model faces many severe challenges and can no longer meet today's needs for efficient, accurate and intelligent power energy management.

[0003] The analysis, prediction and dispatching capabilities of the power system need to be improved urgently. In terms of power analysis, traditional methods are difficult to accurately analyze the load characteristics of power equipment, cannot accurately determine the peak-to-valley difference and load rate of key nodes for power equipment, and are difficult to fully understand the fluctuation state and operation state of power equipment corresponding to the power load. This makes it impossible for the power system to make effective adjustments according to load changes in time during operation, which is easy to cause waste of power resources or tight power supply. In the field of power forecasting, traditional forecasting models are mostly based on simple historical data statistical analysis, lack of in-depth mining and accurate grasp of the inherent laws of time series data, low prediction accuracy and short prediction cycle. This makes it impossible for the power system to make scientific and reasonable plans and response measures in advance when facing the dynamic changes of power load and power generation, and it is difficult to achieve the optimal configuration and efficient utilization of power energy. In the optimization and dispatching link, the traditional model lacks systematic and intelligent dispatching strategies, and can often only make passive adjustments after the imbalance of power supply and demand occurs, and the adjustment means are single and inflexible. This not only makes it difficult to effectively maintain the balance of power supply and demand, but also may cause stability problems of the power system due to improper dispatching, affecting the quality and reliability of power supply.

[0004] In order to effectively solve the problems existing in the above-mentioned traditional power energy management mode, the present invention proposes a power energy management system based on smart Internet of Things. Summary of the invention

[0005] The purpose of the present invention is to provide an electric energy management system and method based on smart Internet of Things, which solves the technical problems raised in the background technology.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] The power energy management system based on smart IoT includes:

[0008] A data acquisition unit is used to collect power data in real time by deploying corresponding sensors at various key nodes in the power system;

[0009] The data processing unit is used to perform data cleaning processing on the power data, and according to the processing result, remove the abnormal data collected in the specified analysis period, and replace the abnormal data in the specified analysis period;

[0010] The power analysis unit is used to analyze the load characteristics based on the power data. According to the analysis results, the peak-to-valley difference and load rate of the key nodes for the applied power equipment are determined to understand the fluctuation state and operation state of the power equipment corresponding to the power load:

[0011] A power forecasting unit, used to make short-term forecasts of power load and power generation in the power system using a time series analysis method;

[0012] The optimization and dispatching unit is used to analyze the supply and demand balance of electric energy according to the short-term forecast results of electric load and power generation, and then optimize the supply and demand according to the supply and demand balance;

[0013] The result display unit is also used to display the results obtained by the power analysis unit, the power prediction unit and the optimization and allocation unit on the relevant display interface.

[0014] As a further solution of the present invention: wherein the key nodes include power generation equipment, power transmission lines, and power consumption equipment;

[0015] Power data includes but is not limited to voltage value, current value, power value and their corresponding timestamps;

[0016] The voltage value is collected by a voltage sensor;

[0017] The current value is collected by the current sensor;

[0018] The power value is calculated from the voltage and current values;

[0019] The power value is calculated according to the formula: P = V × L;

[0020] In the formula, V represents the voltage value, L represents the current value, and P represents the power value.

[0021] As a further solution of the present invention: the data cleaning processing method is as follows:

[0022] StepA1, select the voltage value, extract n voltage values ​​collected within the specified analysis period T;

[0023] StepA2: Calculate the mean and standard deviation of n voltage values ​​and mark them as V p 、V b ;

[0024] StepA3, set each voltage value V i Combine the corresponding mean and standard deviation to make abnormal judgment;

[0025] When |V i -V p |>3×V b When V i Abnormal value;

[0026] When |V i -V p |≤3×V b When V i The value is normal;

[0027] Wherein, i=1, 2, ... n, and they are marked according to the time trend;

[0028] StepA4, when the corresponding V i If the value is abnormal, calculate the value with V i The average value of two adjacent voltage values ​​is used to calculate the V i Replace the value;

[0029] The formula is: TV i =(V i-1 +V i+1 ) / 2

[0030] In the formula, TV i Refers to the corresponding V i The value to be replaced, V i-1 and V i+1 Refers to V i The values ​​are two adjacent voltage values.

[0031] As a further solution of the present invention: wherein, the data cleaning processing method of the current value is consistent with the data cleaning processing method of the voltage value.

[0032] As a further solution of the present invention: the data cleaning processing method of the power value is implemented based on the data cleaning processing method corresponding to the current value and the voltage value;

[0033] After the current and voltage values ​​are cleaned, they are then i =V i ×L i , perform data cleaning on the power values ​​on each acquisition node;

[0034] Where P i is the power value after data cleaning on the corresponding acquisition node, V i is the voltage value after data cleaning on the corresponding acquisition node, L i is the current value after data cleaning on the corresponding acquisition node.

[0035] As a further solution of the present invention: the load characteristic analysis method is as follows:

[0036] Select a power device corresponding to a key node, extract the maximum power value and the minimum power value within the analysis period, and mark them as Pmax and Pmin respectively;

[0037] Then, the peak-to-valley difference PFC of the load of the key node to the applied electrical equipment during the analysis period is calculated through PFC=Pmax-Pmin;

[0038] At the same time, the rated power value of the key node for the electrical equipment is extracted and marked as PE;

[0039] Then pass:

[0040] Calculate the average PP of the power values ​​corresponding to each acquisition node within the analysis period;

[0041] Then pass:

[0042] Calculate the load rate FL of the key node to the electrical equipment during the analysis period.

[0043] As a further solution of the present invention: the short-term prediction method of power load is as follows:

[0044] In the current analysis cycle and the previous analysis cycles, the power values ​​of all key nodes in the power system corresponding to the power equipment are extracted, and then the corresponding power values ​​of each key node corresponding to the power equipment in each analysis cycle are marked as P i，d-j，k , where d represents the current, j = 0, 1, 2, ... m, and they are marked according to the time trend, m represents the number of multiple historical analysis cycles, k = 1, 2, ... r, r represents the number of power-applying devices corresponding to all key nodes in the power system;

[0045] Then through:

[0046] Calculate the power load value FH of the power system in each historical analysis period d-j ;

[0047] Then the moving average method is used to predict the power load value of the next analysis period;

[0048] The prediction formula is as follows:

[0049] Where FH d+1 It is the total power load value predicted for the next analysis period.

[0050] As a further solution of the present invention: the short-term prediction method of power generation is as follows:

[0051] In the current analysis cycle and the previous analysis cycles, extract the power values ​​of the power generation equipment corresponding to all key nodes in the power system, and then analyze the total power value predicted for the next analysis cycle according to the short-term power load forecast method, and mark it as GZ d+1 .

[0052] As a further solution of the present invention: the supply and demand balance situation is analyzed as follows:

[0053] By GFC d+1 =FH d+1 -GZ d+1 ;

[0054] Calculate the forecast supply and demand gap GFC for the next analysis period d+1 ;

[0055] Then according to GFC d+1 Determine whether the forecasted supply and demand relationship of electric energy in the next analysis period is balanced;

[0056] If GFC d+1 >0, it means that there is an excess supply of electricity in the predicted supply and demand relationship of electric energy in the next analysis period;

[0057] If GFC d+1 <0, it means that the power supply is insufficient in the predicted supply and demand relationship of electric energy in the next analysis period;

[0058] If GFC d+1 =0, the predicted supply and demand relationship of electric energy in the next analysis period is in a state of supply and demand balance.

[0059] As a further solution of the present invention: the supply and demand optimization allocation method is as follows:

[0060] When there is an excess of electricity, the remaining electricity is stored in the energy storage device, and the excess electricity is distributed to surrounding areas where the load can be adjusted;

[0061] When the power supply is insufficient, the power of the energy storage device is called upon to supplement the power. At the same time, when the energy storage device cannot meet the power demand, the power consumption of the power consumption of the low-priority power consumption equipment is reduced according to the pre-set power supply priority order.

[0062] The electric energy management method based on smart Internet of Things is implemented by an electric energy management system based on smart Internet of Things. The method comprises the following steps:

[0063] Step 1: Data collection:

[0064] Collect power data in power systems;

[0065] Step 2: Data processing:

[0066] Remove and replace abnormal data in power data;

[0067] Step 3: Power Analysis:

[0068] Analyze the load peak-to-valley difference and load characteristics of power equipment corresponding to the load rate in the power data;

[0069] Step 4: Power forecast:

[0070] Make short-term forecasts of power load and generation in power systems;

[0071] Step 5: Optimize deployment:

[0072] Analyze the supply and demand balance of electric energy based on the short-term forecast results of power load and power generation, and then optimize the supply and demand allocation according to the supply and demand balance;

[0073] Step 6: Results display:

[0074] Display the results of power analysis, power forecasting and optimized deployment to relevant personnel.

[0075] Beneficial effects of the present invention:

[0076] Comprehensive data collection: By deploying sensors at key nodes such as power generation equipment, transmission lines, and power-consuming equipment, power data including voltage, current, power, and timestamps can be collected in real time and comprehensively, providing a rich and accurate data foundation for the entire power energy management, and helping to gain a deeper understanding of the operating conditions of each link in the power system.

[0077] Accurate data processing: The data processing unit adopts a specific data cleaning processing method to clean the collected voltage, current and power values, effectively identify and process abnormal data, improve the reliability and accuracy of the data, avoid abnormal data from interfering with subsequent analysis and decision-making, and make the analysis results based on these data more credible.

[0078] In-depth power analysis: The power analysis unit can analyze load characteristics based on power data and calculate key indicators such as load peak-to-valley difference and load rate. It can clearly understand the fluctuation of power load corresponding to power equipment and the overall operation level, which is helpful for optimizing the scheduling and equipment maintenance planning of the power system, such as preventing equipment failures that may be caused by excessive load fluctuations in advance.

[0079] Effective power forecasting: The power forecasting unit uses time series analysis methods to make short-term forecasts of power load and power generation. It can know the future supply and demand trends of the power system in advance, provide a basis for the rational allocation of electric energy, reduce energy waste or power shortage risks caused by supply and demand imbalance, and improve the stability and economy of power system operation.

[0080] Reasonable optimization and deployment: The optimization and deployment unit analyzes the supply and demand balance according to the short-term forecast results of power load and power generation, and optimizes the supply and demand accordingly. When there is an oversupply of electricity, it can reasonably store or deploy excess electricity, and when there is an insufficient supply of electricity, it can give priority to the operation of key loads. Through orderly resource management, the utilization efficiency of electric energy is improved, the stable power supply of the power system is guaranteed, and the adverse effects of imbalance between supply and demand on production and life are reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] The present invention will be further described below in conjunction with the accompanying drawings.

[0082] Figure 1 It is a system block diagram of the power energy management system based on smart Internet of Things of the present invention.

[0083] Figure 2 It is a flow chart of the electric energy management method based on smart Internet of Things of the present invention. DETAILED DESCRIPTION

[0084] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0085] Embodiment 1

[0086] See also Figure 1 and Figure 2 As shown, the present invention is an electric energy management system based on smart Internet of Things, comprising:

[0087] A data acquisition unit is used to collect power data in real time by deploying corresponding sensors at various key nodes in the power system;

[0088] Among them, key nodes include power generation equipment, transmission lines, and power-consuming equipment;

[0089] Power data includes but is not limited to voltage value, current value, power value and their corresponding timestamps;

[0090] The voltage value is collected by a voltage sensor;

[0091] The current value is collected by the current sensor;

[0092] The power value is calculated from the voltage and current values;

[0093] The power value is calculated according to the formula: P = V × L;

[0094] In the formula, V represents the voltage value, L represents the current value, and P represents the power value;

[0095] In this embodiment, the power data collected by the data collection unit is the basic data source for the operation of the entire system, providing raw materials for subsequent data processing, analysis, prediction and deployment. Without this data, the entire system will not be able to work;

[0096] A data processing unit, used for performing data cleaning processing on power data;

[0097] Taking the selected voltage value as an example, the data cleaning process is as follows:

[0098] StepA1, extracting n voltage values ​​collected within a specified analysis period T;

[0099] In this embodiment, the data acquisition frequency of the voltage sensor and the current sensor is set to be consistent, and the data acquisition frequency is f; for example, for an industrial power consumption area, a current transformer and a voltage transformer are installed at the incoming line end of each large motor to obtain the current and voltage data during its operation, and the acquisition frequency is set to once per second;

[0100] Where n = T × f;

[0101] StepA2: Calculate the mean and standard deviation of n voltage values ​​and mark them as V p 、V b ;

[0102] StepA3, set each voltage value V i Combine the corresponding mean and standard deviation to make abnormal judgment;

[0103] When |V i -V p |>3×V b When V i Abnormal value;

[0104] When |V i -V p |≤3×V b When V i The value is normal;

[0105] Wherein, i=1, 2, ... n, and they are marked according to the time trend;

[0106] StepA4, when the corresponding V i If the value is abnormal, calculate the value with V i The average value of two adjacent voltage values ​​is used to calculate the V i Replace the value;

[0107] The formula is: TV i =(V i-1 +V i+1 ) / 2

[0108] In the formula, TV i Refers to the corresponding V i The value to be replaced, V i-1 and V i+1 Refers to V i Two adjacent voltage values;

[0109] The data cleaning processing method for current values ​​is the same as that for voltage values;

[0110] The data cleaning processing method of the power value is implemented based on the corresponding data cleaning processing method of the current value and the voltage value;

[0111] After the current and voltage values ​​are cleaned, they are then i =V i ×L i , perform data cleaning on the power values ​​on each acquisition node;

[0112] Where P i is the power value after data cleaning on the corresponding acquisition node, V i is the voltage value after data cleaning on the corresponding acquisition node, L i is the current value after data cleaning processing on the corresponding acquisition node;

[0113] In this embodiment, the data processed by the data processing unit has higher accuracy and reliability. These cleaned data provide reliable data support for the power analysis unit, so that the load characteristic analysis results can better reflect the actual power load situation. At the same time, they also provide a high-quality data basis for the power prediction unit, which helps to improve the accuracy of the prediction.

[0114] The power analysis unit is used to analyze load characteristics based on power data:

[0115] Taking the power equipment corresponding to a key node as an example, the load characteristic analysis method is as follows:

[0116] In the analysis period, the maximum power value and the minimum power value are extracted and marked as Pmax and Pmin respectively;

[0117] Then, the peak-to-valley difference PFC of the load of the key node to the applied electrical equipment during the analysis period is calculated through PFC=Pmax-Pmin;

[0118] At the same time, the rated power value of the key node for the electrical equipment is extracted and marked as PE;

[0119] Then pass:

[0120] Calculate the average PP of the power values ​​corresponding to each acquisition node within the analysis period;

[0121] Then pass:

[0122] Calculate the load factor FL of the key node to the electrical equipment during the analysis period;

[0123] In this embodiment, the load peak-to-valley difference PFC and load rate FL of the applied electrical equipment by the key node can be used to understand the fluctuation of the power load corresponding to the power equipment and the overall operation level;

[0124] In this embodiment, the load peak-to-valley difference and load rate obtained by the power analysis unit can intuitively reflect the operating status and load characteristics of the power equipment, and provide key reference indicators for the operation and management of the power system. For example, these indicators can be used to evaluate the operating efficiency of the power equipment and formulate equipment maintenance plans. At the same time, these indicators can also assist the optimization and allocation unit to determine the focus and priority of power supply and demand allocation;

[0125] The result display unit is used to display the results obtained by the power analysis unit on the relevant display interface.

[0126] This embodiment constructs an infrastructure of electric energy management system based on smart Internet of Things. By deploying sensors at key nodes such as power generation equipment, transmission lines, and power equipment, electric power data including voltage values, current values, power values ​​and their timestamps are collected. The data processing unit uses a specific algorithm to clean the data to improve accuracy. The power analysis unit performs load characteristic analysis based on the processed data to obtain key indicators such as load peak-to-valley difference and load rate that reflect the operating status and load characteristics of the power equipment. The result display unit presents the analysis results intuitively, providing a complete set of preliminary guarantee systems for power system operation management with data foundation, precise analysis and intuitive presentation.

[0127] Embodiment 2

[0128] As the second embodiment of the present invention, when the present application is implemented, compared with the first embodiment, the technical solution of the present embodiment is different from that of the first embodiment only in that the present embodiment further includes:

[0129] A power forecasting unit, used to make short-term forecasts of power load and power generation in the power system using a time series analysis method;

[0130] Step D1: The short-term forecasting method of power load is as follows:

[0131] In the current analysis cycle and the previous analysis cycles, the power values ​​of all key nodes in the power system corresponding to the power equipment are extracted, and then the corresponding power values ​​of each key node corresponding to the power equipment in each analysis cycle are marked as P i，d-j，k , where d represents the current, j = 0, 1, 2, ... m, and they are marked according to the time trend, m represents the number of multiple historical analysis cycles, k = 1, 2, ... r, r represents the number of power-applying devices corresponding to all key nodes in the power system;

[0132] Then through:

[0133] Calculate the power load value FH of the power system in each historical analysis period d-j ;

[0134] Then the moving average method is used to predict the power load value of the next analysis period;

[0135] The prediction formula is as follows:

[0136] Where FH d+1 is the total power load value predicted for the next analysis period;

[0137] Step D2: The short-term prediction method of power generation is as follows:

[0138] In the current analysis cycle and the previous analysis cycles, extract the power values ​​of the power generation equipment corresponding to all key nodes in the power system, and then analyze the total power value predicted for the next analysis cycle according to the short-term power load forecast method, and mark it as GZ d+1 ;

[0139] In this embodiment, the power load and power generation results predicted by the power prediction unit are important bases for the optimization and dispatching unit to perform supply and demand balance analysis and optimize dispatching decisions, so that dispatching decisions can be arranged in advance, more forward-looking and reasonable, and ensure that the power system can operate stably and efficiently under different supply and demand conditions;

[0140] The optimization and dispatching unit is used to analyze the supply and demand balance of electric energy according to the short-term forecast results of electric load and power generation, and then optimize the supply and demand according to the supply and demand balance;

[0141] Step P1: The supply and demand balance analysis method is as follows:

[0142] By GFC d+1 =FH d+1 -GZ d+1 ;

[0143] Calculate the forecast supply and demand gap GFC for the next analysis period d+1 ;

[0144] Then according to GFC d+1 Determine whether the forecasted supply and demand relationship of electric energy in the next analysis period is balanced;

[0145] If GFC d+1 >0, it means that there is an excess supply of electricity in the predicted supply and demand relationship of electric energy in the next analysis period;

[0146] If GFC d+1 <0, it means that the power supply is insufficient in the predicted supply and demand relationship of electric energy in the next analysis period;

[0147] If GFC d+1 =0, the predicted supply and demand relationship of electric energy in the next analysis period is in a state of supply and demand balance;

[0148] Step P2: The supply and demand optimization allocation method is as follows:

[0149] When there is an oversupply of electricity, priority is given to storing the excess electricity in energy storage devices, while also considering other reasonable uses of the excess electricity, such as allocating electricity to surrounding areas where loads can be adjusted;

[0150] When the power supply is insufficient, the energy storage device will be used to supplement the power. If the energy storage device cannot meet the demand, some non-critical loads will be reduced in order according to the priority of power supply to ensure the stable operation of critical loads. For example, the lighting in industrial production is set as a non-critical load, and the core power part of the production equipment is set as a critical load. When there is a power shortage, the lighting power will be appropriately reduced to give priority to the operation of production equipment.

[0151] In this embodiment, the supply and demand balance analysis result of the optimization allocation unit directly determines the allocation strategy of electric energy, and the implementation of optimization allocation can ensure the stable operation of the power system, improve energy utilization efficiency and reduce various problems caused by supply and demand imbalance, which is the key link for the entire electric energy management system to achieve its management goals;

[0152] The result display unit is also used to display the results obtained by the power prediction unit and the optimization and allocation unit on the relevant display interface.

[0153] This embodiment is further expanded on the basis of the first embodiment, and an additional power prediction unit is provided to use a time series analysis method to perform short-term predictions on the power load and power generation in the power system. The results become an important basis for the optimization and dispatching unit to perform supply and demand balance analysis and optimize dispatching decisions. The optimization and dispatching unit accurately determines the supply and demand relationship based on the prediction results and formulates dispatching strategies such as energy storage utilization and load reduction. The result display unit displays the power prediction and optimization dispatching results together, thereby enabling the entire power energy management system to have the ability to predict future supply and demand, plan and dispatch in advance to ensure stable and efficient operation of the power system and reduce supply and demand imbalance problems.

[0154] Embodiment 3

[0155] As the third embodiment of the present invention, when the present application is specifically implemented, compared with the first and second embodiments, the technical solution of this embodiment is to combine the solutions of the first and second embodiments mentioned above for implementation.

[0156] Embodiment 3 integrates the solutions of embodiment 1 and embodiment 2, and combines the data collection, analysis and display process with the power forecasting and optimization allocation function. It can not only comprehensively and accurately collect, process and analyze power data to obtain power equipment operation and load characteristic information, but also predict power load and power generation based on time series analysis, carry out supply and demand balance analysis and optimization allocation according to the prediction results, and present all relevant results through the display unit, forming a more complete and comprehensive power energy management system solution, which effectively ensures that the power system achieves efficient energy utilization on the basis of stable operation and provides all-round support for multi-faceted management.

[0157] See also Figure 1 and Figure 2 As shown, the present invention also provides an electric energy management method based on smart Internet of Things, which is implemented by an electric energy management system based on smart Internet of Things. The method includes the following steps:

[0158] Step 1: Data collection:

[0159] Collect power data in power systems;

[0160] Step 2: Data processing:

[0161] Remove and replace abnormal data in power data;

[0162] Step 3: Power Analysis:

[0163] Analyze the load peak-to-valley difference and load characteristics of power equipment corresponding to the load rate in the power data;

[0164] Step 4: Power forecast:

[0165] Make short-term forecasts of power load and generation in power systems;

[0166] Step 5: Optimize deployment:

[0167] Analyze the supply and demand balance of electric energy based on the short-term forecast results of power load and power generation, and then optimize the supply and demand allocation according to the supply and demand balance;

[0168] Step 6: Results display:

[0169] Display the results of power analysis, power forecasting and optimized deployment to relevant personnel.

[0170] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0171] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. The power energy management system based on smart IoT is characterized by: include: A data acquisition unit is used to collect power data in real time by deploying corresponding sensors at various key nodes in the power system; The data processing unit is used to perform data cleaning processing on the power data, and according to the processing result, remove the abnormal data collected in the specified analysis period, and replace the abnormal data in the specified analysis period; The power analysis unit is used to analyze the load characteristics based on the power data, and determine the load peak-to-valley difference and load rate of the power equipment corresponding to the key nodes according to the analysis results; A power forecasting unit, used to make short-term forecasts of power load and power generation in the power system using a time series analysis method; The optimization and dispatching unit is used to analyze the supply and demand balance of electric energy according to the short-term forecast results of electric load and power generation, and then optimize the supply and demand according to the supply and demand balance; The result display unit is used to display the results obtained by the power analysis unit, the power prediction unit and the optimization and allocation unit on the relevant display interface.

2. The power energy management system based on smart Internet of Things according to claim 1 is characterized in that: The data cleaning process is as follows: StepA1, select the voltage value, extract n voltage values ​​collected within the specified analysis period T; StepA2: Calculate the mean and standard deviation of n voltage values ​​and mark them as V p 、V b ; StepA3, set each voltage value V i Combine the corresponding mean and standard deviation to make abnormal judgment; When |V i -V p |>3×V b When V i Abnormal value; When |V i -V p |≤3×V b When V i The value is normal; Wherein, i=1, 2, ... n, and they are marked according to the time trend; StepA4, when the corresponding V i If the value is abnormal, calculate the value with V i The average value of two adjacent voltage values ​​is used to calculate the V i Replace the value; The formula is: TV i =(V i-1 +V i+1 ) / 2 In the formula, TV i Refers to the corresponding V i The value to be replaced, V i-1 and V i+1 Refers to V i The values ​​are two adjacent voltage values.

3. The power energy management system based on smart Internet of Things according to claim 2 is characterized in that: in, The data cleaning processing method for current values ​​is the same as that for voltage values; The data cleaning processing method of the power value is implemented based on the corresponding data cleaning processing method of the current value and the voltage value; After the current and voltage values ​​are cleaned, they are then i =V i ×L i , perform data cleaning on the power values ​​on each acquisition node; Where P i is the power value after data cleaning on the corresponding acquisition node, V i is the voltage value after data cleaning on the corresponding acquisition node, L i is the current value after data cleaning on the corresponding acquisition node.

4. The power energy management system based on smart Internet of Things according to claim 3 is characterized in that: The load characteristics analysis method is as follows: Select a power device corresponding to a key node, extract the maximum power value and the minimum power value within the analysis period, and mark them as Pmax and Pmin respectively; Then, the peak-to-valley difference PFC of the load of the key node to the applied electrical equipment during the analysis period is calculated through PFC=Pmax-Pmin; At the same time, the rated power value of the key node for the electrical equipment is extracted and marked as PE; Then pass: Calculate the average PP of the power values ​​corresponding to each acquisition node within the analysis period; Then pass: Calculate the load rate FL of the key node to the electrical equipment during the analysis period.

5. The power energy management system based on intelligent Internet of Things according to claim 3 is characterized in that: The short-term forecasting method of power load is as follows: In the current analysis cycle and the previous analysis cycles, the power values ​​of all key nodes in the power system corresponding to the power equipment are extracted, and then the corresponding power values ​​of each key node corresponding to the power equipment in each analysis cycle are marked as P i，d-j，k , where d represents the current, j = 0, 1, 2, ... m, and they are marked according to the time trend, m represents the number of multiple historical analysis cycles, k = 1, 2, ... r, r represents the number of power-applying devices corresponding to all key nodes in the power system; Then through: Calculate the power load value FH of the power system in each historical analysis period d-j ; Then the moving average method is used to predict the power load value of the next analysis period; The prediction formula is as follows: Where FH d+1 It is the total power load value predicted for the next analysis period.

6. The power energy management system based on intelligent Internet of Things according to claim 5 is characterized in that: The short-term prediction method of power generation is as follows: In the current analysis cycle and the previous analysis cycles, extract the power values ​​of the power generation equipment corresponding to all key nodes in the power system, and then analyze the total power value predicted for the next analysis cycle according to the short-term power load forecast method, and mark it as GZ d+1 .

7. The power energy management system based on intelligent Internet of Things according to claim 6 is characterized in that: The supply and demand balance situation is analyzed as follows: By GFC d+1 =FH d+1 -GZ d+1 ; Calculate the forecast supply and demand gap GFC for the next analysis period d+1 ; Then according to GFC d+1 Determine whether the forecasted supply and demand relationship of electric energy in the next analysis period is balanced; If GFC d+1 >0, it means that there is an excess supply of electricity in the predicted supply and demand relationship of electric energy in the next analysis period; If GFC d+1 <0, it means that the power supply is insufficient in the predicted supply and demand relationship of electric energy in the next analysis period; If GFC d+1 =0, the predicted supply and demand relationship of electric energy in the next analysis period is in a state of supply and demand balance.

8. The power energy management system based on smart Internet of Things according to claim 7 is characterized in that: The supply and demand optimization allocation method is as follows: When there is an excess supply of electricity, the remaining electricity is stored in energy storage devices; When the electricity supply is insufficient, the power of the energy storage device is called upon to supplement the electricity.

9. The power energy management system based on smart Internet of Things according to claim 1 is characterized in that: in, Key nodes include power generation equipment, transmission lines, and power-consuming equipment; Power data includes but is not limited to voltage value, current value, power value and their corresponding timestamps; The voltage value is collected by a voltage sensor; The current value is collected by the current sensor; The power value is calculated from the voltage and current values; The power value is calculated according to the formula: P = V × L; In the formula, V represents the voltage value, L represents the current value, and P represents the power value.

10. The power energy management method based on smart Internet of Things is characterized by: The method is implemented through the electric energy management system based on smart Internet of Things as described in any one of claims 1-9.

Images