Energy Consumption Estimator for Building Climate Conditioning Systems

Abstract

A computer-implemented method for estimating the energy required for temperature control in a building. The method comprising a training phase on data from a plurality of buildings, adaptation phase to a target building, and estimation phase. The training phase comprises calculating a parameter k which summarizes the thermal characteristics of the building. Subsequently a computer based grey box model is trained with input data comprising the parameter k, indoor conditions, outdoor conditions, and energy consumed for each building. In the adaptation phase similar process is utilized for calculating the target building's the characteristic parameter k. In the estimating phase, the energy for temperature control is estimated based on the parameter k of the target building, indoor conditions, and outdoor conditions by using the computer trained mathematical model of the training phase. The temperature values used may comprise: measured or settings of indoor temperature, and measured or forecasted outdoor temperature.

Claims

1. A computer implemented method for estimating energy required to a target building having a climate control system associated therewith, in order to obtain desired indoor environmental conditions based on given outdoor environmental variables, the method comprising: In a training phase: a) for each of a plurality of individual buildings, each having a climate control system associated therewith, collecting and averaging building-specific characterization data over a first time period T.sub.1, the characterization data comprising outdoor environmental variables, respective indoor environmental variables, and the energy supplied to the respective individual building, the climate conditioning system being active during at least a portion of the first time period T.sub.1; b) for each individual building, utilizing one or more building-specific characterization data to calculate at least one individual building-specific characteristic parameter k; c) for each of the plurality of individual buildings, collecting building-specific training data over a second time period T.sub.2, and comprising outdoor environmental variables, respective indoor environmental variables, and the energy supplied to the respective individual building over the second time period T.sub.2, the climate conditioning system being active during at least a portion of the second time period T.sub.2; d) using a grey-box type artificial intelligence computer system, training a mathematical model of the system to output an estimate of the energy supplied to each individual building in the second time period T.sub.2, responsive to respective input data obtained at the second time period T.sub.2, and comprising outdoor environmental variables, indoor environmental variables, and the respective building-specific characteristic parameter k; in an adaptation phase: e) for the target building, collecting and averaging target building characterization data over a third time period T.sub.3, the target building characterization data comprising outdoor environmental variables, respective indoor environmental variables, and the energy supplied to the target building, the target building climate conditioning system being active during at least a portion of the first time period T.sub.3; f) for the target building, utilizing one or more target building characterization data to calculate a target characteristic parameter k in a manner similar to the calculation of building specific characteristic parameter k in step b); in one or more estimation phases: g) estimating energy E.sub.target using the computer system model of step d) by supplying thereto a value representative of targeted indoor environmental conditions, the target characteristic parameter k, and measured, estimated, and/or forecasted outdoor environmental variables.

2. A method as claimed in claim 1, wherein the training phase comprises a step of utilizing collected training data determining a comfort level for each individual building, the comfort level being related to the indoor environmental variables of the respective building and wherein in step d) the input data obtained at the second time period T.sub.2, comprise the comfort level and in step g) the value of indoor environmental conditions is the comfort level.

3. A method as claimed in claim 1, wherein the indoor environmental parameters are one or more variables selected from indoor temperature T.sub.int, desired internal temperature setting, trends of the internal temperature T.sub.int, operating intervals of the respective building climate conditioning system, indoor relative humidity, indoor ventilation, or any combination thereof.

4. A method as claimed in claim 1, wherein the outdoor environmental parameters are one or more variables selected from outdoor temperature T.sub.ext, outdoor relative humidity, wind direction, wind speed, time of day, period of the year, outdoor temperature trends, sunshine hours, intensity of the sunshine, precipitations (mm of rain or snow), month, or week or day, latitude or any combination thereof.

5. A method as claimed in claim 1, wherein the building characteristic parameter k is a function of the average of indoor temperature T.sub.int measured in the respective building during the first period T.sub.1.

6. A method as claimed in claim 1, wherein the characteristic parameter k of a building is a function of the energy supplied to the respective building, divided by the difference between the respective averaged indoor T.sub.int and average outdoor T.sub.ext temperature for the building.

7. A method as claimed in claim 6, wherein the characteristic parameter k for a building is calculated according to the formula $k=\frac{E}{\Delta t.Math.\left(T_{int}-T_{ext}\right)},$ where T.sub.int and T.sub.ext are, respectively, averaged values of the indoor temperature and outdoor temperature over a time period Δt, in which the indoor temperature and outdoor temperature and, the supplied energy E, are collected.

8. A method as claimed in claim 2, wherein the comfort level is associated with a weighted average of temporal settings of the indoor temperature T.sub.int for the individual building, and/or the target building.

9. A method as claimed in claim 2, wherein the comfort level is a weighted average of the temporal settings of indoor temperature T.sub.int in the time intervals where the climate conditioning system is active.

10. A method as claimed in claim 9, wherein the values of the indoor temperature T.sub.int for calculating the comfort level which are beyond a lower limit and an upper limit are discarded or set equal to the upper or lower limit.

11. A method as claimed in claim 1, wherein the plurality of individual buildings comprises at least 20 individual buildings.

12. A method as claimed in claim 1 wherein given two sets of values for the target building each comprising an energy provided to the building E1, E2, given indoor environmental variables IV1 and IV2 different from each other and given outdoor environmental variables OV1 and OV2 different from each other, the method comprises: a. estimating the energy E12 to be provided to the building corresponding to indoor environmental variables of the first set IV1 and to outdoor environmental variables of the second set OV2; b. calculating a change in energy chosen from an energy change due to the change in indoor environmental variables as E2-E12 or an energy change due to the change in outdoor environmental variables as E1-E12.

13. A computer system comprising a readable non-volatile memory containing program steps that when executed by computer system, causes the computer system to perform at least the following steps: in a training phase: a) for each of a plurality of individual buildings, each having a climate control system associated therewith, collecting and averaging building-specific characterization data over a first time period T.sub.1, the characterization data comprising outdoor environmental variables, respective indoor environmental variables, and the energy supplied to the respective individual building, the climate conditioning system being active during at least a portion of the first time period T.sub.1; b) for each individual building, utilizing one or more building-specific characterization data to calculate at least one individual building-specific characteristic parameter k; c) for each of the plurality of individual buildings, collecting building-specific training data over a second time period T.sub.2, and comprising outdoor environmental variables, respective indoor environmental variables, and the energy supplied to the respective individual building over the second time period T.sub.2, the climate conditioning system being active during at least a portion of the second time period T.sub.2; d) using a grey-box type artificial intelligence training method, training a mathematical model of the system to output an estimate of the energy supplied to each individual building in the second time period T.sub.2, responsive to respective input data obtained at the second time period T.sub.2, and comprising outdoor environmental variables, indoor environmental variables, and the respective building-specific characteristic parameter k. in an adaptation phase: e) for the target building having a climate conditioning system, collecting and averaging target building characterization data over a time period T.sub.3, the target building characterization data comprising outdoor environmental variables, respective indoor environmental variables, and the energy supplied to the target building, the target building climate conditioning system being active during at least a portion of the first time period T.sub.3; f) for the target building, utilizing one or more target building characterization data to calculate a target characteristic parameter k in a manner similar to the calculation of building specific characteristic parameter k in step b); in one or more estimation phases: g) estimating energy E.sub.target using the computer system model of step d) by supplying thereto a value of indoor environmental conditions, the target characteristic parameter k, and measured, estimated, and/or forecasted outdoor environmental variables

14. A computer system as claimed in claim 13, wherein the computer system comprises a distributed computer system having a plurality of processors, wherein any of the steps or portions thereof may be executed on one or more processors of the plurality of processors, and wherein any of the steps or portions thereof may be executed by different processors of the plurality of processors.

15. A computer system as claimed in claim 14, wherein at least two of the processors of the plurality of processors are in data communication with one another, forming a distributed processor system.

16. A computer system as claimed in claim 15, wherein the steps from a) to d) are executed by a first processor or a first group of processors and at least part of the steps f) or g) are executed by a second processor or a group of processors, the first and the second processors or groups of processors being in data communication with one another.

17. A distributed processor system as claimed in claim 16 wherein the second processor is chosen between a smart phone or a tablet

18. A computer system as claimed in claim 16, wherein the first group of processors and the second group of processor share at least one processors therebetween.

Description

BRIEF DESCRIPTION OF THE FIGURES

[0060] FIG. 1 shows a flowchart,

[0061] FIG. 2 shows in a graphical form a representation of the method in the training step,

[0062] FIG. 3 shows in graphical form a representation of the method in the energy adaptation and estimation step.

DETAILED DESCRIPTION

[0063] Further features of the present invention shall be better understood by the following description of possible embodiments, in accordance with the claims and described by way of a non-limiting examples, making use of the annexed figures.

[0064] The energy needed for the conditioning of a building depends on many factors, the main ones of which may be summarized in 4 macro-groups: [0065] a) thermal characteristics of the building (spaces, envelop heat losses, thermal capacity), [0066] b) indoor environmental variables (indoor temperature and/or temporal setting of the temperature, and optionally, humidity and/or indoor ventilation), [0067] c) outdoor environmental variables such as outside temperature and optionally humidity and/or wind conditions, [0068] d) further thermal inputs (people, household appliances, windows and doors opening). [0069] e)

[0070] The thermal characteristics are summarised in the at least one characteristic parameter “k”.

[0071] The method is illustrated with the aid of the references to FIG. 1, according to a possible embodiment the method comprises the following steps: [0072] phase 1 comprises training: for a plurality of buildings, [0073] during a first time period in which the conditioning system was at least partially active, collecting characterisation data 10 averaged over the period. The characterization data comprising: outdoor temperature T.sub.ext, indoor temperature T.sub.int, energy used for the conditioning E, [0074] for each building of the plurality of the buildings, using one or more respective characterisation data to calculate 20 a characteristic parameter k; [0075] for each building of the plurality of buildings, choosing a second period wherein the air conditioning system has been active at least in part, and in the second period collecting 30: [0076] the indoor temperature T.sub.int as an hourly setting or measured trend and optionally the activation time intervals of the conditioning and associating a comfort level with the indoor temperature; [0077] the outdoor temperature T.sub.ext and the energy used for the conditioning E averaged over the period; [0078] training a mathematical model that provides for each building, as an output, an estimate of the energy used for the conditioning E in the second period and has as input data at least: the outdoor temperature T.sub.ext and the comfort level of the second period, and the calculated characteristic parameter k. [0079] phase 2 comprises adaptation and estimation: for a target building to be conditioned [0080] over an initial period in which the conditioning system was at least partially active, collecting characterisation data 50 comprising: outdoor temperature T.sub.ext, indoor temperature T.sub.int, energy used for the conditioning E and calculating 60 the characteristic parameter k of the target building; [0081] for a time period or scenario of interest, collecting the indoor temperature T.sub.int as a temporal setting and/or the trend of the indoor temperature and optionally the time periods in which the conditioning system activation time intervals of the climate conditioning system for the target building has been active and associating a comfort level thereto, [0082] for a time period or scenario of interest, estimating the energy required for the conditioning E 70 using the mathematical model trained on the plurality of buildings, by providing as input data: the characteristic parameter k for the building, the outdoor temperature T.sub.ext and the comfort level, for the period or scenario.

[0083] The comfort level is a quantity associated with the indoor environmental variables, preferably with the temporal setting rather than with the measured values. According to a preferred embodiment, the comfort level is associated with the indoor temperature setting. Some examples of how to associate the comfort level with the indoor environmental variables shall be provided below.

[0084] Phase 1 adopts a supervised training method also called “supervised machine learning”. The computer system that implements this step of the method may be a process dedicated to the building or may be provided on the cloud. For the optimisation it is possible to use a gradient boosting algorithm, or other known algorithms.

[0085] In step 1, historical series acquired on at least tens, for example at least 20, or optionally at least hundreds, for example at least 200, or preferably thousands of buildings, are selected as characterisation and training data. Data is preferably collected when the contribution of other inputs may be assumed to be negligible compared to the thermal input of the climate conditioning system; therefore, averaged values are used over selected periods for the heating processes within the colder season for the heating processes and over periods in the warmer season for the cooling processes. The plurality of buildings includes buildings located in geographical areas representative of the implementation area, and preferably comprising different types of conditioning systems, among which are boilers and heat pumps.

[0086] According to a possible embodiment in phase 1 and 2, the characteristic parameter k is calculated as a ratio of the energy provided E to the difference between the indoor T.sub.int and outdoor T.sub.ext temperature of the building for the duration of the first time period during which, the supplied energy E and the indoor T.sub.int and outdoor T.sub.ext temperatures are averaged

[00002]$\begin{array}{c}P\left(t\right)=k.Math.\left[T_{int}\left(t\right)-T_{ext}\left(t\right)\right]\\ E=\underset{\Delta t}{\int }P\left(t\right)=k.Math.\underset{\Delta t}{\int }\left[T_{int}\left(t\right)-T_{ext}\left(t\right)\right]dt\\ k=\frac{E}{{\int }_{\Delta t}\left[T_{int}\left(t\right)-T_{ext}\left(t\right)\right]dt}=\frac{E}{\Delta t.Math.\left(T_{\mathrm{int},}-T_{\mathrm{ext},}\right)}\end{array}$

Where P is the instant power supplied and E is the corresponding energy, T.sub.int(t) and T.sub.ext(t) are the indoor and outdoor temperatures in the time instant the power P is referred to. The indoor T.sub.int and outdoor T.sub.ext temperatures are an integral of the trend over time divided by the time period. The integral may be conveniently replaced with an average or with a weighted average.

[0087] According to a preferred embodiment, for the calculation of the characteristic parameter k in phases 1 and 2, the indoor temperature T.sub.int value is the average value as sampled over the first period.

[0088] The thermal energy of the building E is made up of energy for the conditioning system E.sub.COND plus energy from exogenous thermal inputs “E.sub.FREE” (persons, household appliances, windows and doors opening):

E=E.sub.COND+E.sub.FREE

[0089] Optionally, the exogenous thermal inputs E.sub.FREE may be estimated using standard values proposed in the literature. According to a possible embodiment, the exogenous inputs may be estimated by the processor in a period in which the climate conditioning system is switched off. According to some possible embodiments, the component of the exogenous thermal inputs E.sub.FREE is added to the energy used for the conditioning system E.sub.COND to obtain the energy of the building E in the training data, and it is subtracted from the building energy E estimated by the model, to obtain only the energy used for the air conditioning system E.sub.COND.

E.sub.CONDE−E.sub.FREE

[0090] If an estimate for the exogenous thermal inputs E.sub.FREE is available, embodiments which takes them into account may be combined with the one or more other characteristics described in other embodiments.

[0091] For the objectives of the method, it is also possible to neglect the minor thermal inputs E.sub.FREE and to approximate the energy of the building E with the energy for the climate conditioning system E.sub.COND:

E≈E.sub.COND

[0092] In the description, reference is made to the energy used for the conditioning E.sub.COND without loss of generality with respect to the possible inclusion of the exogenous thermal inputs E.sub.FREE. Therefore, the expression “energy used for the conditioning E.sub.COND” may be replaced with the expression thermal energy of the building E.

[0093] The energy used for the conditioning system E.sub.COND may be identified both with the energy absorbed by the conditioning system E.sub.ABS (system input) and with the thermal energy that the system exchanges with the building E.sub.HVAC (energy supplied or output of the system). Both approaches are possible. Between the energy absorbed by the conditioning system EARS (system input) and the thermal energy that the system exchanges with the building E.sub.HVAC, there is the relationship:

E.sub.HVAC=E.sub.ABS*eff

Where eff represents the efficiency of the air condition system.

[0094] If a measure of the supplied energy E.sub.HVAC is used in the calculations, the characteristic parameter k is an estimate of the insulation coefficient of the building; if instead the energy absorbed by the conditioning system E.sub.ABS is used, the characteristic parameter “k.sub.eff” corresponds to the insulation coefficient multiplied by the efficiency “eff” of the conditioning system. With “k.sub.eff” specific reference is made to the characteristic parameter k multiplied by the efficiency:

[00003]$\begin{array}{c}{k}_{\mathrm{eff}}=k*\mathrm{eff}\\ k\approx \frac{E_{HVAC}}{\Delta t*\left(T\mathrm{int}-T\mathrm{ext}\right)}\\ \mathrm{keff}\approx \frac{E_{ABS}}{\Delta t*\left(T\mathrm{int}-T\mathrm{ext}\right)}=\frac{E_{HVAC}}{\Delta t*\left(T\mathrm{int}-T\mathrm{ext}\right)}*\mathrm{eff}\end{array}$

For simplicity, in the following, characteristic parameter k means the result of the formula:

[00004]$k=\frac{E_{COND}}{\Delta t*\left(T\mathrm{int}-T\mathrm{ext}\right)}$

so the same term k for the characteristic parameter is used to represent both the implementation methods in which the required energy for the conditioning E.sub.COND is identified with the absorbed energy E.sub.ABS and those in which it is identified with the supplied energy E.sub.HVAC. The choice of using the input energy EARS or the output energy E.sub.HVAC may be combined with one or more other characteristics described in optional embodiments.

[0095] The absorbed energy E.sub.ABS may be measured; the output energy E.sub.HVAC may be calculated starting from the absorbed energy EARS and from the efficiency eff. Alternatively, the output energy E.sub.HVAC may also be measured indirectly by detecting the temperature difference on the exchanger and integrating it over time utilizing known methods.

[0096] The efficiency eff of the conditioning may be considered as constant and known for heating systems such as gas boilers or electrical systems, while for heat pump systems, it is advisable to calculate the efficiency as a continuous or piecewise variable according to the temperature difference between hot source and cold source. These temperatures may be approximated to the indoor and outdoor temperature which are known. In cases where the efficiency variations are not-negligible, it is preferable to consider the energy supplied E.sub.HVAC.

[0097] It should be noted that the following relation,

P.sub.COND(t)=k.Math.[T.sub.int(t)−T.sub.ext(t)]

is strictly valid only in stationary conditions in which there are no thermal inertia effects.

[0098] It has been found that it is very advantageous to use quantities averaged over a sufficiently long period, so that the averages reflects more closely the stationary values rather than the transitory values, in this case the effect of the thermal capacity may be neglected and it has been seen that the other characteristics of the thermal system, for the intended objects, may be represented by the characteristic parameter k.

[0099] Suitable time intervals may be, as an example, one or more days or preferably one or more weeks, or even one or more months. To obtain better accuracy, it is preferable to choose a time period Δt in which the air conditioning system has worked with a certain continuity so that the influence of the transitories is not predominant in the calculation of the average values. As an example, it has been seen that with values averaged over a month, results in line with the objectives are obtained. Therefore, in the following, each temperature value is to be understood as a value averaged in the period to which the energy for the air conditioning refers.

[0100] As stated above, the comfort level is associated with the indoor environmental variables, preferably with the temporal temperature settings rather than with the measured T.sub.int values. According to a preferred embodiment, the comfort level is associated with the indoor temperature settings. The association may take place through tables, rules or a calculation, and must follow the same rule for the plurality of buildings and for the target building. Increasing comfort levels are associated, in the case of heating, with increasing indoor temperatures, in the case of cooling, decreasing indoor temperatures.

[0101] By way of example, a calculation may be a weighted average of the indoor temperature set over a time period. By way of example, the time periods may be one month.

[0102] In the weighted average, preferably within the time period, a greater weight is assigned to the temperature set or detected in the time intervals in which the conditioning system is active within the period. According to some embodiments a zero weight may be assigned to the temperature set in the time intervals in which the conditioning system is not active, therefore according to some embodiments the comfort level is a weighted average of the indoor temperature T.sub.int set in the conditioning time intervals. Alternatively, a lower limit and an upper limit may be imposed on the indoor temperature values used to obtain the comfort level; the values beyond this limit are discarded or set equal to the limit. A lower limit may be 16° C., an upper limit may be for example 26° C.

[0103] Optionally, the comfort level is associated with a vector of indoor environmental variables comprising, in addition to the indoor temperature, also humidity or ventilation, this may be useful for a cooling system that also regulates the humidity. Without loss of generality, the comfort level may be an average of the measured or set indoor temperature T.sub.int.

[0104] According to other possible variants, the outdoor environmental variables, in addition to the outdoor temperature T.sub.ext may comprise one or more of the following variables: [0105] sunshine hours, [0106] intensity of the sunshine, [0107] precipitations (mm of rain or snow), [0108] month, or week or day, [0109] latitude, [0110] average wind speed, [0111] average outdoor humidity.

[0112] Advantageously, this data may be subject to a preliminary pre-processing step. It is much preferable that the data used for the estimation in phase 2, even if collected in a second period, comprise the same variables as those used for the training.

[0113] Once the model has been obtained through the training, it is appropriate to verify it according to the prior art, using part of the data collected over the plurality of buildings that has not been used for the identification as verification data; the partition between identification data and verification data being prior art.

[0114] The training data may also comprise a parameter that indicates the setting of the conditioning system, e.g. the seasonal mode.

[0115] The characteristic parameter k is not necessarily a single value for each building, if several temperature sensors inside a building are present it is possible to calculate a characteristic parameter k associated with each indoor temperature sensor. This may be done in both phase 1 and phase 2 in the adaptation step. Therefore, the simulations of the model may be replicated possibly using more values for the characteristic parameter k, each one is associated with an energy contribution and the total energy being the sum of the contributions. This may be useful if the same conditioning system operates in spaces of a building where there are different temperatures, perhaps due to indoor spaces with different dispersion properties. The choice of using a greater number of characteristic parameters k may be combined with the one or more other characteristics described in optional embodiments.

[0116] Preferably phases 1 and 2 comprise the same number of parameters k.

[0117] In the description, each reference to a characteristic parameter k may be replaced with several values of k, calculated for different measurements of the indoor temperature T.sub.int.

[0118] The method described enables to estimate the energy required for the conditioning E.sub.COND as a function of outdoor temperature values T.sub.ext and the comfort level; by way of a non-limiting example the outdoor temperature T.sub.ext may be taken as the value provided by weather forecasts and the comfort level associated with the average indoor temperature T.sub.int set.

[0119] The estimated climate conditioning energy E.sub.COND may be communicated to the user providing an estimate of the expected consumptions at the time when a profile of temperatures is set.

[0120] The processor may also compare the actual climate conditioning energy with that which would have been obtained, with the same outdoor environmental variables (e.g. outdoor temperature) with different values for the comfort level.

[0121] According to a preferred implementation, the processor compares the climate conditioning energy E.sub.COND between two scenarios with different values both of the outdoor environmental variables and the comfort level and is able to decouple the energy variation caused by the various outdoor environmental variables from that caused by the different comfort levels. i.e., the processor may calculate the energy variation caused only by the different outdoor temperature (T.sub.ext) and that caused only by the different comfort level. In particular, the following climate conditioning energy values E.sub.COND are defined: [0122] Ea=f(k,w.sub.m,u.sub.m) outdoor environmental variables and comfort level of a first scenario [0123] Eb=f(k,w.sub.m−1,u.sub.m−1) outdoor environmental variables and comfort level of a second scenario [0124] Ec=f(k,w.sub.m−1,u.sub.m) outdoor environmental variables of a second scenario, and comfort level of a first scenario [0125] Ed=f(k,w.sub.m,u.sub.m−1) outdoor environmental variables of a first scenario, comfort level of a second scenario. Where for each variable the index “m” indicates the variables relating to the first scenario and “m−1” those relating to the second scenario. [0126] “w” is the set of the outdoor environmental variables or weather variables that do not depend on the user and includes the same variables used for the training. [0127] “u” is the set of variables that determine the comfort level.

[0128] The processor may compare pairs of energy values between which only one among the outdoor environmental variables and comfort level varies, thus obtaining the influence on the energy attributable to each variable. [0129] “Ea−Ec” indicates the component of energy variation from the first compared to the second scenario caused by the outdoor environmental variables (weather). [0130] “Ea−Ed” indicates the variation component from the first of energy with respect to the second scenario caused by the different comfort level (user setting). [0131] “Eb−Ec” indicates how the consumption could have changed in the second scenario if the comfort level of the first scenario had been used.

[0132] According to a possible embodiment, the processor is configured to estimate the energy required with a weather scenario chosen from those of a past period or chosen from those provided for a future period and with current comfort level.

[0133] According to a further possible embodiment, the processor is configured to identify a comfort level setting which respects a maximum consumption of air conditioning energy for a given scenario of outdoor environmental variables.

[0134] The processor may provide the user with an efficiency score of the building which is represented by the characteristic parameter k. The processor may repeat the calculation of the characteristic parameter k over time, any differences may be attributed to changes in the efficiency of the conditioning system, possibly the processor may monitor the efficiency of the conditioning system and signal the need for a maintenance intervention when a new value of the characteristic parameter indicates a reduced efficiency of the building.

[0135] According to a further embodiment, it is possible to detect efficiency losses of the conditioning system by comparing the conditioning energy E.sub.COND actually used with an estimated one, obtained in the same scenario of outdoor environmental variables and comfort level. A discontinuous increase in the estimation error is an important indication of a loss of efficiency of the system and therefore of a possible failure.

[0136] According to a possible embodiment, the processor has access to the information relating to other buildings, and provides the user with a comparison between his/her energy consumption and that of buildings comparable or similar by characteristic parameter k or by value of the outdoor environmental variables.

[0137] If the processor in addition has also access to the geographical area in which the other aforementioned buildings are located, the processor may provide comparisons with nearby users that therefore have similar weather conditions.

[0138] The processor that implements the method may have as input means: at least sensors for receiving indoor and outdoor environmental variables and energy measurements directly detected and as output means at least those for communicating the estimated energy for the conditioning or an ideal setting profile of indoor variables.

[0139] The input or output means may provide interfaces with other devices such as for example an electronic thermostat or also the conditioning system itself for communicating set or detected temperature values or receiving target consumption values, or also user interfaces for the setting of the indoor environmental variables and/or of the maximum consumption value; the interfaces with the user may be dedicated or implemented with an application on a personal device, or can be interfaces with the cloud for receiving weather forecasts of the outdoor environmental variables, or receiving and sending data to other buildings to make comparisons. The output means may be email messages sent to the user by the cloud.

[0140] According to further possible variants, the processor may additionally or alternatively perform the following functions: [0141] given an hourly temperature setting and a forecast of outdoor environmental variables, calculating the consumption over a period, [0142] given an energy consumption target and a forecast of outdoor environmental variables, providing a setting of indoor variables that respects such target, such setting may be communicated directly to the device that controls the air conditioning system.