Icon

02_​Inspect_​and_​Remove_​Seasonality

Exercise 2: Inspecting and Removing Seasonality

This workflow shows the seasonality of time series (energy consumption) in an autocorrelation plot. The seasonality is removed by differencing the time series at the lag where the maximum peak is detected in the autocorrelation plot. As an alternative approach, the time series is decomposed into its trend, first and second seasonalities, and irregular component. The distribution of energy consumption for each hour is shown in a conditional box plot for both the original and differenced time series.

URL: Extract Date&Time Fields Node https://youtu.be/Iur4s3gf6zc

Data Loading
Data Preparation
ACF Plot & seasonality removal

Hourly Box-Plots
Compare Hourly Box-Plots before and after seasonality removal

After applying a lag transformation with a lag of 24 to reduce daily seasonality, the box plot shows reduced variation across hours compared to the original. This indicates that the seasonal component has been partially removed, resulting in a more stable distribution of energy usage.

Among the tested models, ARIMA(1,1,2) has the lowest AIC value (37841.597), indicating that it provides the best fit to the data compared to the other models.

Time Series Analysis 02. Inspecting & Removing SeasonalitySummary: In this exercise we'll explore seasonality in the time series using conditional box plots and the (P)ACF plots. Instructions:1) Run the workflow up through the Missing Value node, this is where we left off in the previous exercise 2) Use the Inspect Seasonality Component to kook at the ACF and PACF plots of the Time Series. Do we have any Seasonality? 3) Use the Remove Seasonality Component to remove the seasonality we discovered 4) Apply another copy of the Inspect Seasonality component after the removal. Does the ACF plot look better? 5) Use the Extract Date&Time Fields node to extract the Hour from the timestamp (Row ID column) after the Missing Value node 6) Use the Number to String node to convert the Hour values into string 7) Use the Conditional Box Plot node to visualize the Energy Usage by hour, do we see a pattern? 8) Repeat steps 5-7 after the Remove Seasonality component, does it look better? Optional) Use the Decompose Signal component after the Missing Value node and look at the view
Introduce missing date times
Timestamp Alignment
Conditional Box Plot (legacy)
Number to String
Lag Column
Domain Calculator
R Snippet
Missing Value
Energy usage data
File Reader (deprecated)
Column Filter
Date&Time Part Extractor
convert date/time into Date&Time objects
String to Date&Time (deprecated)
Autocorrelation Plot (Labs)

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
On NodePit since: 2026-04-10
Last update: 2026-04-10
Created with KNIME version: v5.11.0
Tags: Time SeriesEnergy UsageSeasonalityEducation

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!