A method and system for monitoring and forecasting energy consumption

Abstract

The present application relates to the field of data processing, in particular to a kind of energy consumption monitoring and prediction method and system, by introducing and device real-time energy consumption related energy consumption efficiency factor, and it is integrated into the global information pheromone update mechanism of ant colony algorithm, make scheduling scheme dynamic deviation energy consumption more optimal equipment. Meanwhile, to deal with emergency insert order and other emergencies, the present application constructs disturbance degree model, for evaluating the priority and urgency of event. When disturbance degree exceeds threshold value, the system will trigger re-scheduling and adjust heuristic information, preferentially process emergency, finally form a closed-loop optimization system that can perceive and adapt, improve the energy efficiency and robustness of scheduling. The present application updates ant colony algorithm information pheromone by introducing energy consumption efficiency factor, and dynamically adjusts heuristic information according to event disturbance degree, realizes closed-loop adaptive scheduling to energy consumption and emergency.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of data processing, in particular to an energy consumption monitoring and prediction method. BACKGROUND

[0002] In modern production workshops, production scheduling is the core link to ensure efficient and low-consumption operation of production processes, and its goal is to reasonably allocate a series of production tasks to available devices to optimize key indicators such as total production time, device utilization, or energy consumption.

[0003] However, the scheduling methods in the prior art are mostly static scheduling, facing two major challenges. First, the performance of the device is not constant and will change dynamically due to factors such as aging and wear and tear, resulting in a deviation between the preset energy consumption model and the actual operation, so that the scheduling scheme generated based on old data performs poorly in energy consumption control. Second, dynamic events such as emergency orders and sudden device failures often occur in the production process, and the traditional scheduling system lacks real-time sensing and rapid response mechanisms, making it difficult to effectively respond, resulting in disruption of production plans and poor robustness.

[0004] To solve the above problems, intelligent optimization algorithms such as ant colony algorithm are often used for production scheduling. This algorithm simulates the foraging behavior of ants to find the optimal scheduling path in the solution space. However, in the above dynamic scenarios, the standard ant colony algorithm has obvious defects: First, its pheromone update mechanism usually only relies on a fixed cost model (such as total working hours or estimated energy consumption), and cannot sense the real-time health status of the device. When a device deteriorates and causes actual energy consumption to rise, the algorithm cannot detect it in time and may continue to allocate tasks due to its lower historical cost, resulting in a deviation between the scheduling result and the actual energy consumption. Second, the heuristic information in the algorithm (i.e., the expected degree of task transfer) is usually static and does not change once it is set, which makes the algorithm slow to respond when facing unexpected events and unable to intelligently adjust task priorities to prioritize high-importance or high-urgency tasks. SUMMARY

[0005] To solve the problems of deviation between the scheduling result and actual energy consumption and slow response to emergencies, in a first aspect, the application provides an energy consumption monitoring and prediction method, which comprises: obtaining a production task set and an available device set; scheduling the production tasks based on an ant colony algorithm to generate a scheduling scheme; collecting actual power of each task on the corresponding device during execution of the scheduling scheme, and obtaining expected power calculated based on device reference data; calculating a device energy consumption efficiency factor, which is negatively correlated with the actual power and positively correlated with the expected power; introducing the device energy consumption efficiency factor into a global pheromone update mechanism of the ant colony algorithm, so that the pheromone increment is positively correlated with the average value of the energy consumption efficiency factors of all tasks corresponding to the devices in the path; in response to an emergency in the production process, calculating a disturbance degree which is positively correlated with the priority of the emergency and the urgency of the deadline; when the disturbance degree is greater than a set threshold, triggering rescheduling and adjusting heuristic information to prioritize processing of the emergency.

[0006] Compared with the prior art which adopts a static energy consumption model and lacks the ability to respond to emergencies, the application introduces a device energy consumption efficiency factor based on real-time power monitoring and integrates it into the global pheromone update mechanism of the ant colony algorithm, realizes dynamic perception of the real energy consumption state of the device, makes the scheduling decision continuously favor the device with the highest energy efficiency, and thus reduces the total energy consumption of actual production. At the same time, the application constructs a disturbance degree model to quantify the urgency of the emergency, automatically triggers rescheduling and adjusts heuristic information when the disturbance degree exceeds the threshold, gives the scheduling system the ability to respond to dynamic changes such as emergency orders or device failures, and significantly improves the robustness and adaptability of production scheduling.

[0007] Further, the calculation method of the device energy consumption efficiency factor comprises:

[0008] ;

[0009] Wherein represents the energy consumption efficiency factor of the device when executing the task ; represents the real-time collected power of the device when executing the task ; represents the expected power of the device when executing the task ; represents a hyperbolic tangent function; represents a tuning factor.

[0010] The present application normalizes and nonlinearly maps the relative deviation of actual power and expected power by using hyperbolic tangent function, so that the energy efficiency factor can respond to power fluctuation smoothly and boundedly. Compared with simple linear proportional calculation, this way can effectively suppress the excessive influence of extreme power deviation value, make the factor change more stable, and thus ensure the robustness of subsequent pheromone update.

[0011] Further, the global pheromone update mechanism is specifically:

[0012] ;

[0013] Wherein represents the ant After selecting the path of the task , the pheromone increment left on the path; represents the pheromone intensity constant; represents the total evaluation cost of the scheduling scheme constructed by the ant ; represents the average value of energy efficiency factors of all tasks assigned to the device in the path of the ant .

[0014] The global pheromone update mechanism of the present application directly links the average value of the energy efficiency factor of the path to the pheromone increment, realizing positive incentive for energy consumption optimization. Unlike the traditional ant colony algorithm which only considers path length or fixed cost, the present application enables the paths containing devices with higher energy efficiency in recent performance to accumulate more pheromone during the iterative optimization process of the scheduling scheme, thereby guiding the algorithm to converge to a global optimal or suboptimal scheduling solution with lower energy consumption more quickly.

[0015] Further, the calculation method of the disturbance degree is specifically:

[0016] ;

[0017] Wherein represents the new event caused to the task currently being executed or about to be executed; represents the priority of the new event; represents the average priority of all tasks in the current task pool; represents the deadline point of the new event required relative to the current time; represents the estimated completion time point of the current task ; and are weight coefficients with a value range of , and the sum is 1.​

[0018] The calculation method of the disturbance degree in the application comprehensively considers two key dimensions of the priority and the urgency of the deadline of the emergency, and balances through the weight coefficient, so that the impact degree of the new event on the existing plan can be more comprehensively and objectively evaluated. Compared with the prior art which only judges whether to reschedule according to a single rule (such as first come first served), the application provides a quantifiable and more detailed decision basis, avoids unnecessary frequent rescheduling, and also ensures that events with high importance and high urgency can be responded in time.

[0019] Further, the adjustment heuristic information specifically includes:

[0020] ;

[0021] Wherein represents the adjusted heuristic information; represents the original heuristic information; represents the disturbance influence factor with a value greater than 0; represents the task as the disturbance degree of the emergency event to the preceding task .

[0022] The heuristic information adjustment method of the application directly uses the calculated disturbance degree to enhance the transfer expectation of the emergency event task, that is, the probability of the ant selecting the emergency event as the next task is significantly improved when rescheduling. Compared with the traditional ant colony algorithm in which the heuristic information is fixed, this dynamic adjustment mechanism can directly convert the urgency information of the emergency event into the search preference of the algorithm, so that the event can be processed preferentially in the rescheduling process, ensuring that it can be arranged as soon as possible, and effectively shortening the response time to the emergency event.

[0023] Further, the production task set is modeled as a graph model , wherein a node set represents all production tasks, and an edge set represents the allowed process transfer relationship between tasks.

[0024] Further, obtaining the production task set and the available equipment set includes, further comprising: obtaining the production task set and the available equipment set from a manufacturing execution system (MES), a device monitoring system (SCADA), and an enterprise resource planning system (ERP).

[0025] Further, when the actual power is equal to the expected power, the energy consumption efficiency factor is equal to 1; when the actual power is greater than the expected power, the energy consumption efficiency factor is less than 1; and when the actual power is less than the expected power, the energy consumption efficiency factor is greater than 1.

[0026] Further, the calculation method of the disturbance degree comprises a time urgency term; the time urgency term takes a positive value only when the predicted completion time of the current task is later than the deadline of the new event, and takes a value of 0 in other cases.

[0027] In a second aspect, the present application provides an energy consumption monitoring and prediction system comprising a processor and a memory, the memory storing computer program instructions which, when executed by the processor, implement the energy consumption monitoring and prediction method of the present application.

[0028] The technical effects of the present application are:

[0029] The present application proposes a dynamic intelligent scheduling method. The core innovation lies in the double improvement of the traditional ant colony algorithm: first, the energy consumption efficiency factor related to the real-time power of the equipment is introduced to dynamically update the pheromone, so that the scheduling continuously tends to the optimal solution of energy consumption; second, a disturbance degree model quantifying the emergency degree of events is constructed, which can automatically trigger rescheduling and give priority to processing in the case of emergency orders and other situations, thereby forming a closed-loop adaptive scheduling system with energy efficiency optimization and dynamic event response capability, significantly improving the efficiency and robustness of production scheduling. BRIEF DESCRIPTION OF DRAWINGS

[0030] Figure 1 is a flow chart of the energy consumption monitoring and prediction method of the embodiment in the present application;

[0031] Figure 2 is a thermal map of the device energy consumption efficiency factor in the 9th iteration of the embodiment in the present application;

[0032] Figure 3 is a thermal map of the pheromone matrix after the 9th iteration of the embodiment in the present application;

[0033] Figure 4 is a thermal map of the device energy consumption efficiency factor in the 10th iteration of the embodiment in the present application;

[0034] Figure 5 is a thermal map of the pheromone matrix after the 10th iteration of the embodiment in the present application;

[0035] Figure 6 is a block diagram of the structure of the energy consumption monitoring and prediction system of the embodiment in the present application. DETAILED DESCRIPTION

[0036] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0037] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0038] Example of an energy consumption monitoring and prediction method:

[0039] like Figure 1 As shown, the energy consumption monitoring and prediction method of the present invention includes:

[0040] S1. Initialization and modeling of production task and equipment status data.

[0041] First, the system obtains the set of production tasks to be scheduled from the Manufacturing Execution System (MES), the Supervisory Control and Data Acquisition System (SCADA), and the Enterprise Resource Planning System (ERP). and available device set For each production task This involves obtaining static information such as process ID, planned output, working hours, and delivery date for each piece of equipment. To obtain benchmark data such as its rated power and energy consumption models under different operating conditions.

[0042] In this embodiment, the complex production scheduling problem can be abstracted into a graph model. , where the set of nodes Represents all production tasks to be executed, edge set This represents the permissible and feasible transfer relationships between tasks in terms of the technological process. This modeling process lays the foundation for subsequent path optimization using ant colony optimization based on graph search.

[0043] S2. Construct a dynamic pheromone update mechanism based on real-time energy consumption deviation.

[0044] Traditional ant colony optimization algorithms only consider the total path length (i.e., total energy consumption or total working time) built by ants when updating pheromones. This invention introduces consideration of the deviation between the actual and expected energy consumption of the device.

[0045] First, during production execution, the system collects data from each device in real time via the SCADA interface. In performing the task Actual power at time Meanwhile, based on the equipment baseline energy consumption model obtained in step S1, the energy consumption of this task is calculated. In this device Theoretical expected power .

[0046] To quantify the energy consumption performance of a device when performing a specific task, this embodiment constructs a device energy efficiency factor. This factor aims to reflect the degree to which the actual energy consumption of equipment deviates from the theoretical model. The factor is constructed based on comparing the relative deviations between actual and expected power, and then using a nonlinear function for smoothing and normalization to obtain a stable indicator of efficiency. The specific calculation formula is as follows:

[0047] ;

[0048] in Indicates equipment In performing the task Energy efficiency factor at that time; Indicates equipment In performing the task Real-time power acquisition at any time; This indicates the equipment calculated based on the equipment reference model. In performing the task Expected power at that time; This represents the hyperbolic tangent function, with a range of (-1, 1), which can smooth and normalize the power deviation. This represents the parameter tuning factor, which can be taken as an empirical value of 1e-6 in this embodiment to avoid the case where the denominator is 0.

[0049] From the above formula, it can be seen that when the actual power equal to expected power At this time, the deviation is 0. , This indicates that the equipment's energy consumption performance meets theoretical expectations, and its efficiency is at the standard level. When the actual power... Greater than expected power For example, increased energy consumption due to equipment aging or malfunction will result in a positive power deviation. A positive value makes The value will be less than 1, and the larger the deviation, the better. The closer it is to 0, the lower the energy efficiency of the equipment.

[0050] Conversely, when the actual power Less than expected power For example, energy consumption was reduced through technological upgrades or operational optimization, resulting in a negative deviation. The value is negative. A value greater than 1 indicates that the equipment's energy efficiency is better than expected.

[0051] Further, a device energy efficiency factor is incorporated into the global pheromone update rule of the ant colony algorithm. The incorporation is based on the fact that when evaluating the quality of a dispatch path, not only its total cost should be considered, but also the paths that use devices in a better state (i.e. with higher energy efficiency) should be rewarded. When an ant completes a path construction, i.e. generates a complete dispatch sequence, it leaves an increment of pheromone on the edges of the path it has taken. The increment of pheromone is modified by

[0052] ;

[0053] wherein denotes the increment of pheromone left by the ant after the task and before the task ; denotes a pheromone intensity constant; denotes the total evaluation cost of the dispatch scheme constructed by the ant , which in one embodiment can be the total energy consumption; denotes the average of the energy efficiency factors of all tasks assigned to the device in the path of the ant .

[0054] This pheromone update rule ensures that even if two dispatch schemes have the same total cost , but one of them uses more devices with high recent energy efficiency (i.e. with a large value), the path corresponding to this scheme will be rewarded with more pheromone. This will positively guide the subsequent ant population to preferentially select devices in a better state, thus enabling the dispatch scheme to dynamically and adaptively favor the use of efficient devices.

[0055] As shown in FIG. 9, this heat map intuitively shows the real-time energy efficiency factors of each device (M00-M03) when performing different tasks (T00-T14) in the 9th iteration. According to the legend, the red area represents , indicating that the actual power consumption of the device on this task is lower than expected, and the energy efficiency is better. The blue area represents , indicating that the device energy consumption is higher than expected, and there may be aging or inefficient operation.

[0056] As shown in FIG. 10, this heat map intuitively shows the real-time energy efficiency factors of each device (M00-M03) when performing different tasks (T00-T14) in the 10th iteration. According to the legend, the red area represents Figure 3 , indicating that the actual power consumption of the device on this task is lower than expected, and the energy efficiency is better. The blue area represents , indicating that the device energy consumption is higher than expected, and there may be aging or inefficient operation.As shown, this pheromone matrix heatmap illustrates the pheromone concentration distribution along the transfer paths between tasks after the 9th iteration. The bright spots in the graph, namely the yellow and white areas, represent the paths the ants tend to choose. This is based on the aforementioned pheromone update rules. Those in Figure 2 The red devices exhibit high efficiency, meaning that the task paths they execute receive more pheromone rewards. Therefore, this pheromone map can guide subsequent searches to favor the most efficient devices currently available.

[0057] S3. Design a dynamic heuristic information adjustment strategy based on production event disturbances.

[0058] Traditional ant colony optimization algorithms typically rely on heuristics, such as the expected degree of task transfer, based on static data like the reciprocal of task processing time or energy consumption. This approach fails to provide a rapid response to unexpected events during production. This embodiment introduces the ability to detect unexpected events during production and dynamically adjusts heuristics to achieve a rapid and intelligent response to scheduling plans.

[0059] When unexpected events occur during production, such as emergency orders, equipment failures, or material delays, the system needs to quantify the degree of disruption this event causes to the current scheduling plan. Therefore:

[0060] ;

[0061] in Indicates a new event For tasks currently being performed or about to be performed The degree of disturbance caused; It indicates a newly occurring event, such as an urgently inserted task; The task currently being processed or the next task to be processed in the current scheduling plan; This indicates the priority of new events, which is assigned by the system according to business rules. For example, urgent orders from VIP customers have higher priority. This indicates the average priority of all tasks in the current task pool; Indicates the deadline required by the new event relative to the current time; Indicates the current task The expected completion time; and These represent the weighting coefficients for priority and urgency, respectively. .

[0062] The above formula assesses disturbances from two dimensions: importance and time urgency. The first term... This reflects the relative importance of new events; the higher the priority of the event, the greater the disturbance. (Second item) This reflects the time urgency of the new event. If the current task's completion time... It is already past the deadline for the new event. If the time conflict is severe, the term will be positive, indicating a high degree of disturbance; conversely, if there is ample time, the term will be 0, indicating no urgent disturbance. The larger the value, the greater the impact of the new event on the existing plan, and the more drastic the algorithm needs to be adjusted.

[0063] When a perturbation degree When the preset threshold is exceeded, the system triggers a rescheduling. Heuristic information is used during the new ant colony search process. (representing the task) Transfer to task The expected level will be dynamically adjusted, specifically:

[0064] ;

[0065] in This represents the adjusted heuristic information; Represents the original heuristic information, typically for the task. The reciprocal of processing energy consumption ; This represents the disturbance impact factor, a positive coefficient used to control the intensity of the disturbance's influence. Indicates task Relative to the task The event disturbance degree. This specifically refers to the event disturbance degree if the task... It is an urgent task to be inserted, then The calculation will be based on Attributes.

[0066] Based on the state transition probability formula of the ant colony algorithm The above adjustments mean that when a highly disruptive emergency mission... When it appears, all pointing to the task Heuristic information about the path All of these will be significantly amplified. This makes the task more prominent when the ant chooses its next task. The probability of being selected increases significantly. In this way, the algorithm can respond quickly, prioritizing urgent tasks and inserting them into the scheduling sequence, thus achieving adaptive adjustment to external events.

[0067] like Figure 4 As shown, after the scheduling system ran for the 9th iteration, a sudden event occurred, and a new emergency task 'T15_URGENT' appeared in the task list. The appearance of this emergency task will trigger the event perturbation degree in S3. Calculation. Since this is a high-priority, urgent task, its disturbance level is likely to exceed the threshold, triggering a rescheduling. During the rescheduling process, the system will calculate according to the above formula. Dynamically increase the heuristic information for all paths pointing to task 'T15_URGENT'.

[0068] like Figure 5 As shown, comparing the pheromone heatmaps from the 9th and 10th iterations reveals a significant change in pheromone distribution. The 10th heatmap shows new bright spots and paths, which is the result of the ant colony finding the optimal insertion position for the urgent task 'T15_URGENT' under the guidance of the adjusted heuristic information.

[0069] S4. Closed-loop dynamic scheduling of execution and feedback.

[0070] Integrating the above steps S1 to S3 forms a dynamic optimization closed-loop system of "planning-execution-perception-adjustment".

[0071] First, before production begins, the system runs an optimization based on the standard ant colony algorithm to generate an initial low-energy scheduling plan, and production starts according to this plan. Next, the system enters a continuous closed-loop monitoring and adjustment phase. On one hand, the system continuously executes the logic of step S2, monitoring the energy efficiency factor of each device in real time. Based on the results, the global pheromone is continuously fine-tuned in each iteration. This allows the pheromone environment to continuously and accurately reflect the actual energy consumption of the equipment; furthermore, the system executes the logic of step S3 in parallel, monitoring external production events in real time. Once a disturbance is detected... Events exceeding the threshold immediately suspend the current scheduling and trigger a rescheduling. During the rescheduling process, the ant colony algorithm will use the... Real-time corrected pheromones and quilt Dynamically adjusted heuristic information A new round of path search is conducted; finally, after generating a new scheduling scheme that is more adapted to the current situation, the system returns to the stage of continuous execution, monitoring and response, forming a complete dynamic optimization closed loop.

[0072] In summary, this invention, through the aforementioned scheme, transforms the traditional static ant colony algorithm into a dynamic intelligent scheduling system capable of sensing and adapting to changes in the real-world production environment. This system not only dynamically optimizes scheduling paths based on the real-time energy consumption of equipment but also provides rapid and appropriate responses to unexpected events during the production process, thereby achieving continuous and effective energy consumption optimization and robust production execution in complex and ever-changing industrial scenarios.

[0073] Energy consumption monitoring and forecasting system embodiments:

[0074] In another aspect, the present application also provides an energy consumption monitoring and forecasting system. As shown in Figure 6 the energy consumption monitoring and forecasting system comprises a processor and a memory storing computer program instructions which, when executed by the processor, implement the energy consumption monitoring and forecasting method according to the first aspect of the present application.

[0075] The energy consumption monitoring and forecasting system further comprises other components such as communication interface, which are well known to those skilled in the art, and thus will not be described in detail herein.

[0076] In the present application, the aforementioned memory can be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, the computer readable storage medium can be any suitable magnetic storage medium or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random-Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc., or any other medium that can be used to store the desired information and that can be accessed by an application, module, or both. Any such computer storage media can be part of the device or accessible or connectable thereto. Any applications or modules described in the present application can be implemented using computer readable / executable instructions stored or otherwise held by such computer readable media.

[0077] In the description of the present application, the meaning of "a plurality of", "several" is at least two, for example two, three or more, etc., unless otherwise explicitly specified.

[0078] Although the present application has been shown and described with respect to several embodiments thereof, it will be apparent that equivalents, modifications, and variations of such embodiments will occur to those skilled in the art in light of the foregoing description. It is therefore contemplated to cover in the appended claims any and all such modifications, variations, and equivalents that fall within the true spirit and scope of the present application. It should be understood that in the process of practicing the present application, various alternatives, modifications, and equivalents can be employed.

Claims

1. A method for monitoring and predicting energy consumption, characterized in that the method... The method comprises: acquiring a production task set and an available device set, and scheduling the production tasks based on an ant colony algorithm to generate a scheduling scheme; acquiring actual power of each task on a corresponding device during execution of the scheduling scheme, and acquiring expected power calculated based on device reference data; calculating a device energy consumption efficiency factor, specifically: ； in Indicates equipment In performing the task Energy efficiency factor at that time; Indicates equipment In performing the task Real-time power acquisition at any time; Indicates equipment In performing the task Expected power at that time; Represents the hyperbolic tangent function; Indicates the parameter tuning factor; introducing the device energy consumption efficiency factor into a global pheromone update mechanism of the ant colony algorithm, so that the pheromone increment is positively correlated with an average value of the energy consumption efficiency factors of the devices corresponding to all tasks in the path; the global pheromone update mechanism specifically comprises: ； wherein denotes an ant on a task after selecting a task leaves pheromone increments on the path; denotes a pheromone intensity constant; denotes an ant the total evaluation cost of the constructed scheduling scheme; denotes the average of the energy efficiency factors assigned to the devices in the path of the ant ; in response to a sudden event in the production process, calculating a disturbance degree that is positively correlated with an event priority and positively correlated with a time urgency of a deadline, specifically: ； wherein represents a new event a task currently being performed or about to be performed the degree of disturbance caused by the task; represents the priority of the new event; represents the average priority of all tasks in the current task pool; represents the deadline point of the new event required relative to the current time; represents the predicted completion time point of the current task ; and is a weight coefficient with a value range of , and and are 1. when the disturbance degree is greater than a set threshold, triggering rescheduling and adjusting heuristic information to prioritize processing of the sudden event.

2. The method of claim 1, wherein, The adjustment of the heuristic information specifically comprises: ； wherein denotes the adjusted heuristic information; denotes the original heuristic information; denotes a perturbation impact factor with a value greater than 0; denotes a task as a perturbation degree of the emergency event on the prequel task .

3. The method of claim 1, wherein, Also included is modeling the set of production tasks as a graph model where a set of nodes represent all production tasks, and a set of edges represent allowed process transfer relationships between tasks.

4. The method of claim 1, wherein, acquiring the production task set and the available device set comprises: acquiring the production task set and the available device set from a manufacturing execution system (MES), a supervisory control and data acquisition system (SCADA), and an enterprise resource planning system (ERP).

5. The method of claim 1, wherein, When the actual power is equal to the expected power, the energy consumption efficiency factor is equal to 1; when the actual power is greater than the expected power, the energy consumption efficiency factor is less than 1; and when the actual power is less than the expected power, the energy consumption efficiency factor is greater than 1.

6. The method of claim 1, wherein, The calculation method of the disturbance degree contains a time urgency term; the time urgency term takes a positive value only when the estimated completion time of the current task is later than the deadline of the new event, and takes a value of 0 in other cases.

7. An energy consumption monitoring and forecasting system, characterized by, The device comprises a processor and a memory, and the memory stores computer program instructions that, when executed by the processor, implement the energy consumption monitoring and prediction method of any one of claims 1-6.

Images