LSTM time series forecast for multiple time series' ( single model vs individual model performance)

Question

I would like to use deep(stacked) lstm model to forecast the disk utilisation for all my clusters. But what I am experiencing is my individual model representing a single clusters- time series is giving more accurate performance, when compared to a single model representing all the time series'. Single model is a kind of averaging out the forecast though I am including the cluster-id as part of a feature passed to the model.

• My training sequence logic goes as given below, where my time series has [ 'utilisation','clusterID'] as two features.

  for i in range(len(sequences)):
    # find the end of this pattern
    end_ix = i + n_steps_in
    out_end_ix = end_ix + n_steps_out-1
    # check if we are beyond the dataset
    if out_end_ix > len(sequences):
      break
    # gather input and output parts of the pattern
    seq_x, seq_y = sequences[i:end_ix, :], sequences[end_ix-1:out_end_ix, 0]        
    X.append(seq_x)
    y.append(seq_y)
  return array(X), array(y)```

 - **Model**

trainX = trainX.reshape((trainX.shape[0], trainX.shape[1],features))
trainY = trainY.reshape((trainY.shape[0], trainY.shape[1]))
input = Input(batch_input_shape=(batch_size,look_back,features), name='input', dtype='float32')
optimizer = keras.optimizers.RMSprop(learning_rate=0.0001, rho=0.9, epsilon=None, decay=0.0)
model = Sequential()
model.add(Bidirectional(LSTM(800, return_sequences=True,return_state=False,input_shape=(look_back, features),stateful=stateful)))
model.add((LSTM(800, return_sequences=True,return_state=False,stateful=stateful)))
model.add(attention(return_sequences=False))
model.add(Dense(units=out_num))
model.compile(metrics=[rmse],run_eagerly=True,loss='mean_squared_error', optimizer='adam')
history = model.fit(trainX, trainY, batch_size=5000, epochs=100, verbose=2, validation_split=0.1)

 - **and prediction logic as follows**

  

testX, testY = create_dataset(predictList.values,look_back,out_num)
reshaped_test=np.reshape(testX[0],(1,look_back,2))
futureStepPredict = model.predict(reshaped_test)


I was expecting an LSTM model can be trained on multiple timeseries at one time itself and can give individual forecast with almost the same accuracy as if it was considered as a single model based on the cluster-id provided as input, is this a wrong expectation?